What is Business Forecasting?

Business forecasting is the process of using analytics and experience to make predictions about future customer/consumer demand. The goal is to go beyond knowing what has happened to arrive at the best assessment of what will happen in the future so a company can make optimal business decisions, whether that be operational or strategic. Business forecasting incorporates a lot of different data and viewpoints, uses forecasting tools for modelling, and generates numbers (forecasts) that be used in multiple areas of the business.

What is Demand Planning?

Demand planning is the process of identifying and managing customer/consumer demand for a company’s goods or services and formulating responses to meet that demand. The idea is to balance demand and supply, i.e. serving the customer with the products they want while optimizing the operational elements that go into it.

People use the terms ‘demand planning’ and ‘forecasting’ almost synonymously but there are some differences. Demand planning is the process that drives operational supply chain activities like resource planning, production, logistics, and inventory policies. Forecasting generates the numbers used to inform those activities.

Demand planning is typically manifest in cross-functional processes like Sales & Operations Planning (S&OP) or Integrated Business Planning (IBP) that bring different functions together to decide on what the company can deliver and manage the trade-offs between Production, Supply Chain, Finance, Sales & Marketing etc.

Whatever you call it, you’re trying to predict what a company will sell in the future to successfully be able to supply it when it’s needed.

What Happens When a Company Doesn’t Have Good Forecasts?

If you have bad demand forecasts you may make poor decisions. If you underestimate demand, it can result in lost sales or, even worse, lost customers. If you overestimate demand, it can mean wasting money on inventory you can’t sell and tying up capital that could be better utilized elsewhere.

With a good forecast you give the customer what they want, when they want it, thereby maximizing sales and helping deliver on the strategic goals of the company. With an idea of what’s going to happen before it occurs, you can set inventory policies, set production schedules, determine investments, predict market impacts, control costs, and understand the lifecycles of your products.

What are the Key Steps in Demand Planning?

Demand planning is about more than just a number – it’s a process with a lot of different elements.

Data Collection: Data can come from multiple sources. We must understand what exactly is out there as far as inputs and insights and know how we can bring those into the forecast. Data typically includes historical sales data and qualitative information from Sales about key customers and from Marketing who can reveal how promotional activity will impact demand.

Data Analysis: The data you get won’t always be clean and usable in its current format it will require some preparation before analysing it. We need to look for anomalies in the data as well as formatting issues, determine what data is relevant and what isn’t, and make sure we’re using the right amount of data.

Forecast modelling: Multiple time series methods can be used to take the data, extrapolate it forward, and arrive at a forecast. Increasingly companies are turning to advanced systems to do machine learning and AI which use a wider range of data and automate much of the process.

Gaining Consensus: A challenging part of the process for a lot of companies is arriving at one number used by the different functions. You need everyone on the same page in terms of what you think is going to happen in the future – and collaboration is fundamental to this. This where collaborative planning forums like S&OP and IBP come in.

Communicating the forecast assumptions: This is often overlooked. We need to explain the expected result (forecast) and the reasons behind as this is key to those forecasts being trusted and therefore used across the business.

What Data is Used in Business Forecasting?

It can be internal data such as sales orders, or external data which a lot of companies are starting to look at now. External data includes customer information, macro information, and demographic data, as well as causal information like sales promotions or weather data.

Data is either structured (easily managed in a spreadsheet and easily accessible) or unstructured (not easily managed in a spreadsheet and often difficult to access). Unstructured represents over 85 percent of the data out there and includes data from social media comments, product reviews, and audio and video content.

What Forecasting Models are Used in Business Forecasting?

There are a lot of different models available. This is because there’s a lot of different types of data out there which require different forecasting approaches. At one extreme we have pure qualitative and knowledge based judgements. This could be a sales team giving their own estimate of sales and then you’re aggregating those things up. At the other extreme you have pure quantitative approaches like machine learning with less human judgement and intervention.

In the middle there are various types of Time Series methodologies and causal models. There’s no right or wrong model or approach – rather we must choose the best approach for the data we have and the resources and time we have to generate a forecast. According to IBF research, right now most companies use Time Series types of data in their modelling and their preferred method is exponential smoothing. Does that mean exponential smoothing is the best? Not necessarily, but it is versatile method and it’s good for a lot of Time Series data.

What is Bias in Forecasting?

Bias is consistent over-or under-forecasting. It can be conscious or unconscious. For example, Sales may always forecast higher sales numbers because they want the inventory on hand in case they make the sale, or Finance may always push the number down to to avoid tying up cash in inventory. Whether it is high or low, bias is dangerous and gives a false picture of the future. It creates bad decisions and deteriorates the trust in the forecasting process. Bias is actually often worse than uncertainty.

To learn the fundamentals of business forecasting and demand planning, join us for IBF’s Chicago Demand Planning & Forecasting Boot Camp from March 15-17, 2023. You’ll learn how to forecast demand and balance demand and supply from world-leading experts. Click here for more information. 

It seems people have drawn their proverbial line in the sand and taken one side or the other. On one extreme, there is an argument which states forecasts are always wrong, “why do them at all?”. At the other end of the spectrum is the argument that, when it comes to forecasting, in the land of the blind the one-eyed man is King, and that forecasts are the only way to see what is going to happen next.

I am never short on opinions, so here’s what I think.

Demand Driven MRP Vs Forecasting: Who Wins?

So, what is the right answer? To be fair and in full disclosure, I have an obvious bias. To better understand my perspective: I have been in the Demand Planning field for over fifteen years, I am a Certified Professional Forecaster, I won the 2016 Business Forecasting & Planning award, and I am currently Director of Thought Leadership at the Institute of Business Forecasting – so I may have a slight prejudice. That said, you may also decide after reading this article that my background may just add credibility to my sentiments. In this article, I have attempted to put those biases aside and address the concepts of Demand Driven and Demand Planning. What’s more, I will discuss why my own profession is responsible for this debate.

Demand Driven Plans For What Is Known, Rather Than Anticipating Unknowns

One of the main arguments I hear in support of Demand Driven is that forecasts are always wrong. To fix this, a Demand Driven approach is employed where downstream activities such as production or supply are based on actual orders rather than forecasts. This means a company reacts to known demand rather than anticipating it. This in theory would eliminate the dependency on forecasts, at least operationally. I have no problem with the underlining concept, and there is no doubt that a bird (or an order) in the hand is worth two (forecasted orders) in the nest.

So far so good for Demand Driven MRP.

Demand Driven Dismisses Value of Forecasting Whilst Simultaneously Relying On It

Things start to get cloudier when you begin to place inventory as buffers using historic actuals. I do not care what you try to call it – what you have is a forecast. Using an average daily usage, for example, is a crude, naïve forecast. Adding a seasonal index or factor to this is a rudimentary seasonal random walk, or another type of unsophisticated forecast. Adding other variables such as promotional lifts, trends, or other factors and you are recreating a different forecast for operations that may be disconnected from the rest of the organization.

Unfortunately, by not calling this a forecast, we do not apply the same scrutiny as we do to demand plans. We are even unaware how much more inaccurate we may be, or be ignorant of the variability or bias we may be adding with our assumptions.

Demand Driven therefore seeks to debase forecasting but still uses forecasts, but ends up with forecasts that are unproven and may not be fit for purpose.

Demand Planning Can See Beyond Just The Order

Yes, it is true that the demand plan will always be wrong, but what we have seen is that taking an average of historical demand then layering on assumptions is no longer actual demand either. Demand Planning is defined as “using forecasts and experience to estimate demand for various items at various points in the supply chain.” A good demand plan or planner injects discipline into the process to minimize error and bias for a proven and tested signal. Demand Planning best practices should use performance indicators such as Forecast Value Added (FVA) and measure against naive. If naive is better, the demand plan should use it. If not, it uses better statistical or judgmental models, or probabilistic forecasts.

Naturally, you also want to use the truest form of demand that is available to you. In many cases that may very well be sales orders. It could also be vendor managed inventory demands, point-of-sale, or even unstructured data such as website or social media interactions. A well-developed demand planning or forecasting process will drive beyond just orders even closer to consumer demand to provide even greater insights.

So far so good for Demand Planning.

Few Companies Actually Use Downstream Data

The problem (according to 2015 data) is that less than 15% of companies are able to exploit the use of downstream data for any advantages. In a 2012 SAS article, under 50% said they used any point-of-sale to create their forecast. In addition to these, there are some that are even worse and are still generating constrained forecasts based on shipments or supply chain constraints, or trying to use their profit or budget plan as the operational plan.

A potentially even bigger problem is the dirty little secret that most forecasts are not only wrong, but they are not even beating the naive. There have been studies that show everything humans keep trying to do to improve the forecast is often making things worse. So, as far as Demand Planning and our forecasts are concerned some of the criticism from Demand Driven about forecast is justified – “we have been weighed, we have been measured, and we have been found wanting.”
[bar group=”content”]

Which Approach Is Better, Demand Driven MRP Or Demand Planning?

When there is a void in business operations, there is a natural instinct and obligation to try to fill it. The Demand Driven approaches have all been inspired out of necessity – that there is a known gap in planning and it was going unfilled.

In many ways, I cannot blame them. If you think about it, it is our fault.  Demand Driven was inspired because demand planning has not done its job. Demand planning across a lot of organizations – either out of ignorance or indolence – is falling short of its capabilities. We were not delivering what the business needed to be more responsive and operate more efficiently. Even worse, the basic principles of Demand Planning and best practices in many companies are still being neglected or abandoned entirely.

Demand Planners Need To Wake Up And Start Doing Their Jobs

I do not know how else to say this or sugarcoat it, but the answer is simple: we must start doing what we are being paid to do. We cannot bury our heads in the sand and refuse to accept that we, as a profession, have failed to live up to our potential.

We must take proactive steps to deliver the results we are capable of delivering. Here’s how:

Plan According To What You Know    

We need to plan according to more of what we do know, and get as close as possible to the source of demand. We are uniquely positioned to go further upstream, sort through the noise and scrutinize the demand signals and look at probabilities to offer the best picture of what is happening. In the operational planning horizon, demand sensing (the use of predictive analytics and pattern recognition) can replace rules-based consumption to drive better replenishment.

Focus on Forecasts Beings Accurate, Not Precise

Knowing we are wrong, we need to work on being more accurate rather than being precise. Many Demand Planners get hung up on the forecast number and neglect the forecast range. Ranges are more accurate and many supply chains can absorb some variability. Focusing on demand flow and setting up buffers helps with this, but we need to work in collaboration to determine optimal levels based on the greatest precision, as well as the accuracy we can attain.

Eliminate Latency

We need to try to eliminate latency in our process. If it requires a monthly process to produce the forecast for next week, you might have a problem. Demand Planning needs to be lean and become more agile and responsive. Utilize more demand sensing techniques to help identify demand trends, provide advanced warning of problems, and remove the latency between plan and operational response.

Go Beyond Forecasts

Understand it is not all about forecasts. There is more to the Demand Planning role than just creating a forecast number – we must intimately get to know our data and attributes. Use error to improve, not just to measure. We need to better understand the drivers and flow of demand. Understanding demand drivers and error, as well as demand flows, helps with building ‘what-if’ capabilities. If we are truly intimate with what is happening and why, we have the ability to do one better than demand-driven: we can actually drive demand through prescriptive analytics and figure out how to make demand happen.

So Where Do We Go From Here?

The first step is admitting we have a problem. One of the reasons there is even a debate between Demand Driven and Demand Planning is because Demand Planning was not living up to their side of the bargain. It is not that one is better, but we need to (at least) do better than we have. For Demand Planning, this means both companies and professionals. To do this we need to continue to learn, share, and advance:

• Learn new techniques as well as best practices. You can stay current with articles in publications like the Journal of Business Forecasting, and engage with the wider forecasting and planning community. (I’d love to see more of you at our IBF conferences and tutorials.)
• Better understand the role of Demand Planner and learn how to structure your team and recruit the best employees, and maximize their potential. Assess and improve your current capabilities through demand-planning functional maturity models.
• Share with other functions what you can do and how you can add value to their processes. Share your learning with other professionals so that together we can continue to grow.
• Not just individually or as a profession, but as a company. Between Demand Driven and Demand Planning, it is not that one is better than the other; as we learn better practices and collaborate, we advance together and find the right answers.

Ultimately this debate comes down to everyone working together and putting the pieces together.  There are principles and techniques in Demand Driven that drive value and there are principles and techniques (if we apply them) in Demand Planning that drive value. Entrenching yourself on one side of the debate doesn’t help anyone.

The Sales Department’s primary function is to sell the firm’s product or service. They are judged on their sales performance based on what is achievable according to market conditions. If the market is buoyant and there are tailwinds, we would expect Sales to perform well. [bar group=”content”]

At the same time, you would expect Operations to plan ahead so sales have what they need, and Management to revise targets upwards to make sure the team is pulling their weight and maximizing sales opportunities. Conversely, if the market deteriorates, then we need to look at reducing cost and minimizing inventory, and to revise sales targets down so that the sales staff have realistic targets and their hard work is still recognized.

This requires a few things: a robust forecasting process and demand planning function; regularly updated forecasts; a culture whereby Sales contributes with insights on changed assumptions based on the latest information; and for Sales operations to be closely connected with Operations so that potential gaps can be identified and closed. The key objective in all of this is a succinct, integrated, and collaborative process that everyone including sales participates in.

Integrated Business Planning – ‘Integrated’ Being The Operative Word

A major part of the process goal is to operate as effectively and profitably as possible. All of this may be accomplished through an integrated Sales and Operations (S&OP) process with cross-functional communication and collaboration that connects Sales with Demand Planning and other major functions in a structured way. Not having a good cross-functional collaboration or S&OP process in place may lead to missed opportunities for Sales, or unneeded risk for the company. Imagine the all too familiar scenario below and consider where it leaves your Sales Department and your company’s bottom line.

The Scenario:

The forecasting Team generates an annual forecast which is revised to some agreeable number by top management as per the budget. This forms the basis for Production plans. Subsequently, this provides Production with a guideline for how much to produce each month (and what the annual production budget should be). At the same time, Sales has created stretch goals or targets for their salespeople and are planning to hit those numbers. Unfortunately Production, which is still tied to the budget, is not prepared. When Sales begins to outpace the plan and begins hitting their target, the corresponding production is not available. With no S&OP process in place, sales targets are regularly missed, with little understanding why. Left in the dark about the stretch goals, Sales is constantly fighting an uphill battle. Sales staff miss targets, miss out on expected bonuses and are seen to underperform. Sales blames Operations for not having the product and Operations blames Sales for not giving a good forecast.

This kind of approach is all too common for organizations with underdeveloped Sales and Operations Planning processes. We see obvious negative consequences in Sales missing targets and experiencing high staff turnover, but this belies other structural and systemic weaknesses in the understanding of how forecasts are created, and the importance of cross-functional collaboration in creating those forecasts. Below are the systemic and cultural problems in our above scenario.

Sales and Production Work toward Different Figures

Sales are working towards different figures to Production. Whilst Sales are trying to hit targets based on updated assumptions, Production was not able to provide enough stock on time. This means that Sales teams are habitually missing their targets when the market is developing positively, and unnecessary stock accumulates when market conditions have deteriorated.

This creates unrealistic expectations and dissatisfaction … and missed opportunities. If you’re a sales manager hoping for your team to hit bonus every month, you would consider it unfair to not have the necessary stock available to do so. This would also impose clear limitations in increasing the company’s top and bottom line. He/she should seek to instigate changes in the S&OP process to resolve this issue.

The Sales Team Is Excluded from the S&OP Process or There is no S&OP Process

If the Forecasting team does not receive Sales input into the forecast, it means it is impossible to identify gaps between forecast and targets. We are not asking Sales to create an entirely new forecast every week or after any new market intelligence but they do own the assumptions and have a responsibility to provide insights. The exclusion of Sales input means they are not having any input into the projected figures and no companywide consensus is being reached.

If our fictitious company had the benefit of a mature S&OP environment, the revised forecasts that they send to Production would be discussed at the Monthly Demand Plan Meeting, where they are presented to Management, Sales and Marketing, Finance, Production, and Operations. This is the opportunity for all to reach a consensus and decide on a final unbiased and unconstrained figure for the month that all departments will work towards achieving. In our scenario above, these meetings simply aren’t happening.

From the Sales department’s point of view, they may not generate the forecast but they should own the assumptions and need to be involved in the process to make a decision as to whether, and how, they can close the gap between forecast and target based on previous performance, production capacity, and available resources like marketing initiatives. In our scenario, Sales cannot be expected to hit targets when the overall market doesn’t allow for it, nor should Management allow for sales opportunities to be missed by not having realistic quotas.

The Sales Team is Not Helping to Establish True Demand

There is an important concept that is going unnoticed in the above scenario: Sales and Marketing, along with forecasting, must be aggressive in their efforts for forecasts to reflect true demand. Sales and Management should help work to identify the true demand drivers, and the levers they can pull to affect these demand drivers. In our scenario above, none of this is happening. To get Sales to realistically hit the targets set by Management, discussions must take place about what marketing initiatives would be taken to close the gap, enabling Sales to hit their target.

What’s more, Sales has great insight into the latest developments in the market, particularly at a regional level. They know about competitors entering the market and they gauge the sentiment of their clients in real time. They know what products are accelerating in demand, which accounts are growing, and client expectations before anyone else. Sales are the firm’s eyes and ears into the market. It should go without saying that Forecasting should use their information and assumptions when creating forecasts.

The Bottom Line: Join The Dots For Effective Forecasting and Demand Planning

Within an effective S&OP environment, it’s not just Statistical models, Management, or Operations that work with (and help create) the number created by the Demand Planning team, it is the Sales department as well, and their role in helping to paint an accurate picture of demand. If the above scenario sounds familiar, your Sales Team must move beyond simply reacting to sales targets and start to help shape the demand plan and be a part of a collaborative process. It must work with others, such as Demand Planning teams and strive to establish plans for closing potential gaps.

In an established S&OP environment, there are two key ingredients that comprise the forecast:

• A statistical forecast based on historical data and other variables (what we know)
• Sales input based on changing market assumptions (what we need to know)

This allows the organization to capture what we know in current sales levels and trend and seasonality, whilst adjusting it for what we need to know about and anticipated variables as perceived by Sales. Whilst there is a lot of debate surrounding a true “one-number forecast”, companies need at minimum a “one-number attitude”. Any S&OP process must be truly cross-functional and collaborative if it is to succeed, where each department has a clear understanding of the others’ objectives, resources, biases, and assumptions. Any differences in opinion must be resolved within the understanding of each department wanting to revise figures where possible, and presenting realistic plans to achieve them. To succeed you need a robust Demand Planning and S&OP process and Sales must be part of both those processes and contribute with insights. That way, everyone operates under the same set of assumptions, and that is how successful companies achieve the wider goal of increased efficiency and profitability.

[bar id=”527″]

It is only October and already it is beginning to look a lot like Christmas. For many people, they call it the holiday season – for business forecasters, we call it seasonality. For some companies, the next few months can see over a twenty or thirty percent increase in their average sales or even make up sixty percent or more of their total volume for the entire year. With so much at stake, having an accurate plan or forecast is critical for any business to meet customer demand.

So, as we go into this holiday season, what are the key factors to consider when planning for this all-important time of year?

More people will stay home this year

No, we are not saying sales will be down but there is an obvious trend that will continue, and that is more and more consumers will be using their computers, tablets, or smart phones to do their shopping this year. When comparing current trends to the prior year, we can see 4% – 6% more consumers deciding against the hassle of finding a parking space, fighting the crowds, and waiting in checkout lines. Instead, they are shopping at home in their PJ’s. Organizations such as the NRF (National Retailer Federation) are forecasting that online spending and other non-store sales will rise 11% to 15% this season.

There are a couple of impacts caused by these trends that we need to keep in mind. First, back to this thing we call seasonality: historically, back in the ‘good old days’ before Amazon, stores would need to have inventory ready by mid-October. For distributors or manufacturers, our holiday season would start in September and run through Thanksgiving. You may have got a small replenishment but, for the most part, the bulk of our sales came in the third fiscal quarter. The current trend of online sales is also skewing our traditional seasonality and we cannot rely as much on the prior year’s seasonal index, and need to adjust it every year according to these new trends. Store shelves are being replaced by distribution centers with lower buffer stock. What’s more, we are seeing smaller orders with greater frequency, and sales later and later into the season creating completely different seasonal patterns.
Next, consumers continue to demonstrate their preference for making purchases through a variety of channels including in-store, online, and click and collect. According to the International Council of Shopping Centers (ICSC):

• 90% of holiday shoppers will take advantage of omnichannel retailers with 40% of them buying online and picking up in-store
• 81% of those shoppers plan to make additional purchases when collecting their item(s)

For planning, this means not only forecasting what and when the consumer will buy, but adding the complexity of where they will buy and where you need to have it available.

The holiday season will be longer than prior years

Not only do planners and forecasters face a challenge in the season starting earlier, we also need to consider where the holidays fall in each given year. This year, it appears we have one extra day of shopping. Christmas falls 32 days after Thanksgiving this year, one day more than last year. It is on a Monday instead of a Sunday, giving consumers an extra weekend day to complete their shopping. This may not seem like much to some industries, but for those in the retail and distribution sectors who look at year over year comps, this is a big opportunity.

Not only is there an extra day at the end, trends are seeing consumers buying earlier – and this year, hopefully more often. While November and December remain the anticipated busiest shopping months, ICSC estimates an uptick in the number of people planning to shop before Thanksgiving at 66%—with almost one third (27%) starting as early as August. If you are only learning this now, it is already too late.

Planning must evolve beyond historical models given changes in consumer behavior

Over all, with the increase in online sales and the expected extension of the shopping season, it all adds up to the potential for more retail sales. Bear in mind that 46% of shoppers say they plan to spend more this holiday season. No matter who you poll or which report you look at, most forecasters have this year’s sales increasing by 3% – 5%. At the same time, what we are also seeing for planning is that it is not as easy as taking last year’s number and just adding something.

We are seeing new seasonality, longer selling seasons, increased complexity of distribution, and our job getting harder at the exact point when it is becoming more important. Exciting (and challenging) times to be a demand planner or forecaster. Happy Holidays…

Hurricane Harvey will certainly ripple through many organizations’ supply chains for months to come and what they may discover is that this could be costlier than any hurricane of the past. To understand this, we not only need to look at the cost, but also what this may mean for sales.

Historically, hurricanes that hit the United States have led to an obvious slowdown in economic activity right after they occur. We generally see a downturn in other regions that are not even directly impacted by the storm or its flooding. There is also an economic slump with regards to consumer sentiment across the United States correlating to major events; for instance, it is likely that more people stay at home and wait for the catastrophe to unfold. Following this initial negative trend, there is a less obvious rebuilding phase, which leads to an equal, if not greater, economic rebound.

Rebuilding After Hurricanes Drives Economic Activity

Over time, we have consumers and retailers replacing what they have lost and Federal aid flowing into the area, giving rise to an increase in economic activity. Just like the downturn, other unaffected regions feel this recovery as well. These stimulus dollars—compounded by some pent-up demand of consumers—seem to trickle through the economy to other regions that are not directly impacted by the storm and boost sales everywhere.

This is all well and good, but just like in a storm where no two neighborhoods are affected the same—the impact on your business may not follow this perfect trend. You need to look a little deeper at how your business sector reacts during these times and what your consumers’ behaviors will be going forward.

The need for this and to understand sales during and after the impact of such a storm is critical to planning and succeeding. If you overreact to the initial downturn in sales, you may not be properly prepared for the retail storm surge coming when things settle down. If you ignore your consumer behavior, you may be overstocked and all your money may be tied up in inventory.

How To Forecast For Your Industry After Hurricanes Strike

What exactly will occur in your specific market and how will Hurricane Harvey impact your forecast? It all depends. Here are just a few key factors that a demand planner may want to consider because they could impact your forecast and business.

While we may have big winners of this tragedy (if we can call them that), like construction companies and related industries, other sectors are going to feel the storm surge of lost sales and then the aftershock of those sales not returning. Many companies have a distinct summer selling season that a good portion of their sales comes between Memorial Day and Labor Day. This can be anything from drink cups, to outdoor sports, to mattresses. For these sectors, the storm that formed on August 24, 2017, then slammed into the Texas and Louisiana coasts, and stalled there for four days while dumping as much as 52 inches of rain in some parts with consequential flooding that will last well beyond Labor Day. This is losing the entire last week of summer and time and sales they will not be able to get back.

Replenishment of Destroyed Inventory Costs Time And Money

Next, do not forget: it is not just homes but also retailers and manufacturers that need to replenish what they lost as well. As an example, there are an estimated 500,000 automobiles that may have been damaged with many of them sitting in car lots needing to be replaced. Warehouses and retail stores full of products have been flooded and before these companies open back up for business, they will need new replacement products. This will be new channel inventory and a spike in demand for many sectors and products that needs to be forecasted appropriately.

Footfall Decreases

There are still many retailers with primarily brick and mortar stores that rely heavily on foot traffic created over Labor Day weekend sales. These are stores focusing on back-to-school, fashion, or many other consumer products just to name a few. These sectors missed a critical weekend of in-store traffic and as more consumers stayed home, online traffic reaped the rewards. While in-store sales have been trending down for some time, thanks to mega online giants such as Amazon, we will most likely see traditional stores take another hit from Hurricane Harvey. Understanding your company’s omnichannel presence and market share may be equally important as understanding consumer habits during major storms.

Higher Costs For Logistics and Goods

Finally, we cannot kid ourselves. This hurricane is going to cost supply chains and consumers a lot of money. In the impacted area, there are hundreds of factories, warehouses, distribution centers, and major ports. Sixty-eighty key chemicals and intermediates originate from the Texas region and much of the country’s polymers and resins come from this area. Around 10% of manned oil platforms in the Gulf were evacuated, according to the Bureau of Safety and Environmental Enforcement. While the fallout is still being determined, gas prices have risen an average of 23 cents already and it is estimated that they will to continue to go higher. All of this adds up to higher costs for fuel, higher costs for logistics, higher costs for goods, and lower sales for non-essential items for some people. As prices continue to climb and people spend $3.00 or more a gallon at the pump—sectors that rely on discretionary income will continue to see a decline and be hardest hit.

Less Discretionary Selling

For the sectors that have lost the final week of their summer selling season, lost foot traffic for back to school and Labor Day weekend, or have been impacted by higher costs and less discretionary spending—it means estimates as much as $15 billion in economic activity will be missing. That constitutes a 1% drop in total U.S. GDP measured on a month-over-month basis. That said, the government will most likely spend that much in its first round of spending alone.

Impact on Companies Can Be Severe But Impact On Overall Growth Is Minimal

Overall, at the aggregate level, the storm is likely to have a relatively minimal effect on overall economic growth, once we factor in the stimulus effect of the reconstruction phase (estimated depressing real spending growth by estimated 0.3% in quarter three). For your company, the impact may be much greater. The real question should be this: what does it mean to your business and how can you forecast the effect on your sales?

Forecasting this is not only tricky, but it is much like the hurricane: you can end up with a large cone of uncertainty in trying to predict your demand after this type of storm. While we cannot predict the weather, we can better anticipate consumer behavior during and after a hurricane with good tools, data, and skilled business forecasting professionals. If you would like more information, please contact info@ibf.org

We wish for all who are affected by this tragedy, a speedy recovery.

Globalization has intensified competition. Every day, thousands and thousands of new products enter the market, but their window of opportunity is very narrow because of shorter life cycles. Plus, too much uncertainty is associated with new products. Their success rate is from poor to dismal—25% according to one estimate. Despite that, they are vital for fueling growth. Big box retailers are putting more pressure on suppliers to provide differentiated products. Consumers want more choices and better products. All these factors contribute to the greater than ever number of products and product lines, making management of their demand more complex, increasing working capital to maintain safety stock, raising liability of slow-moving and obsolete inventory, and increasing cost of production because of smaller lots and frequent change overs. Product portfolio optimization deals with these matters.

Product portfolio optimization includes the following: one, how to rationalize products and product lines and, two, how to manage most effectively their demand. Product rationalization includes deciding which products and product lines to keep and which ones to kill, based on the company’s policy. Demand management, on the other hand, is leveraging what Larry Lapide from University of Massachusetts and an MIT Research affiliate calls 4Ps (Product, Promotion, Price, and Place) to maximize sales and pro‑t. The sales of low-performing product lines may be bumped up with a price discount, promotion, line extensions, or by finding new markets.

[bar group=”content”]
Although the S&OP process has a component of product portfolio optimization, its team members pay nothing more than lip service to it. Pat Bower from Combe Incorporated discusses in detail the process of product portfolio optimization in the framework of new products. How new products should be filtered from ideation to development and, after launch, how they should be leveraged. Their window of opportunity is very small; most CPG products flame out within the first year of their existence, says Pat.

Mark Covas from Coca-Cola describes in detail 10 rules for product portfolio optimization. He suggests companies should divest low margin brands, no matter how big they are. Many companies such as ConAgra Foods, General Mills, Procter & Gamble, and Estée Lauder are doing it. This makes the allocation of marketing dollars more productive—taking funds away from low performing brands and giving to high performing ones.

Charles Chase from SAS and Michael Moore from DuPont recommend the Pareto principle of 80/20 to determine which products or product lines to concentrate on in their portfolio optimization e­fforts. Greg Schlegel from SherTrack LLC. Goes even further and proposes that this principle should be extended even to customers. He categorizes customers into four: 1) Champions, 2) Demanders, 3) Acquaintances, and 4) Losers. He then describes a strategy for dealing with each one of them. Greg Gorbos from BASF points out hurdles, political and others, that stand in the way of implementing the optimization policy, and how to deal with them. Clash occurs among different functions because of difference in their objectives. Sales looks to achieve revenue targets, while Marketing looks to hold market share and increase profit. Finance also looks at profit, but seeks to reduce cost and increase capital flow, while Supply Chain looks at cost savings. Communication is another issue Greg points out. The company may decide to deactivate a product, but information about it is not communicated to all the functions. Je­ff Marthins from Tastykake talks, among other things, about the exit strategy, which he believes is equally important. He says that we cannot deactivate a product without knowing its inventory position, as well as holding of raw and packaging materials for it.

For survival and growth in today’s atmosphere, it is essential to streamline the product portfolio to reduce costs, and increase revenue, profit, and market share. This issue shows how.

I encourage you to email your feedback on this issue, as well as on ideas and suggested topics for future JBF special issues and articles.

Happy Forecasting!

Chaman L. Jain
Chief Editor, Journal of Business Forecasting (JBF)
Professor, St. John’s University
EMAIL:  jainc [at] stjohns.edu

DOWNLOAD a preview of this latest Journal of Business Forecasting (JBF) Issue

Click HERE to join IBF and receive a JBF Complimentary Subscription

While I don’t obsessively worry about every possible risk, I am aware of the possibilities and I take measures to lower both the odds and severity of a mishap. I keep my vehicle well maintained, I buckle up and I pay my auto insurance. Similarly, today’s supply chain professionals must be more conscientious and proactive in their efforts to mitigate the risk of a supply chain disruption and to minimize the impact when the inevitable does occur.

As much as we may feel at the mercy of disruptions from severe weather, natural disasters, economic instability or political and social unrest, members of today’s high tech supply chain have never been better equipped to minimize the risks and capitalize on the opportunities that may arise from a supply chain disturbance.

One of the most simple, but powerful, tools at our disposal is information. Twenty-four hour news stations, social media and cellular communications give us literally instant access to events occurring in the most remote reaches of the world.

More tactically, mapping the physical network of the supply base, including manufacturing facilities, warehouses and distribution hubs, is an important part of any risk management strategy. The key here is mapping the entire supply chain network, not just top-spend suppliers or first-tier contract manufacturers. Most of this information is relatively accessible through supplier audits and, with the help of Google maps, you can create a pretty comprehensive picture of your physical supply chain.

[bar group=”content”]

Remember, though, supply chains are much more fluid than they have ever been. Today’s multinationals are likely to rely on three to five different contract manufacturers (CMs) and original design manufacturers (ODMs), and scores of other suppliers around the world for the tens of thousands of parts needed to build and maintain their products. With outsourced production so commonplace, production lines can be shifted between locations within a matter of weeks, so frequent monitoring and updating of supply chain shifts is critical.

IoT technology such as sensors and RFID tracking can also provide meaningful intelligence that may be used to identify and mitigate risk throughout the end-to-end supply chain process. The ability to gather and analyze these constant data inputs is a recognized challenge throughout the supply chain profession. Those who master the digital supply chain sooner, will enjoy a substantial competitive advantage.

Once these various vehicles are used to create a composite picture of the risk landscape, then risk mitigation strategies take center stage. These efforts can range from traditional techniques such as the assignment of a cache of safety stock to more intricate maneuvering of storage facilities and full network design. Deployment of these mitigation strategies requires a detailed recovery and communications plan.

In my upcoming presentation at IBF’s Supply Chain Forecasting & Planning Conference at the DoubleTree Resort by Hilton in Scottsdale, AZ, February 22-23, 2016, I will delve deeper into the growing range of potential disruptors in the high tech supply chain. I will outline the core elements of a comprehensive supply chain risk management strategy, including how to define and map the physical supply chain, the landscape around supply chain risks and their impact on financial metrics, and how to proactively assess potential risk. I hope to see you there.

Forecast Error

The first session I attended on Tuesday was “How to Measure & Reduce Error, and the Cost of Being Wrong” an advanced session presented by Dr. Chaman Jain from St. John’s University.  Dr. Jain reviewed the basic methods and mechanics of how to compute forecast error and the pros and cons of each technique. It was interesting that IBF has found that more and more companies are moving from MAPE (Mean Absolute Percentage Error) to a Weighted MAPE (WMAPE) to focus their attention on errors that have a relatively larger impact or little to no impact at all.  Standard MAPE treats all errors “equally”, while WMAPE places greater significance on errors associated with the “larger” items. The weighting mechanism can vary, typically unit sales are used, but I was intrigued by the notion of using sales revenue and profit margin as well.  If a company has low volume items but they are big revenue and profit items, they would not want to miss an opportunity to focus attention on why they have significant errors on these items.

Another interesting concept that Dr. Jain discussed was the use of confidence intervals around error measurements.  Many companies report their error measurement as a single number and rarely present the error measure in terms of a range of potential errors that are likely. Having a view into the potential range of errors can allow firms to exercise scenario planning to understand the impact to supply chain operations and the associated sales based upon multiple forecast errors instead of a single number.

My last takeaway is related to the question of how much history should be used to support time series analysis. Dr. Jain stated, and I believe rightly so, that it depends. Are there potential seasonality, trend, business cycles, or one-time events? How much does one need to see these? What if the past is really not a good indicator anymore of the future? What if the drivers of demand for a product have substantially shifted? One technique suggested that seems sound is to test the forecasting model’s performance using different periods of historical data. Use a portion of the history to build the model, and the remaining portion to test the accuracy of the forecast against the actuals held out of model construction. Try different lengths until you find the one that has the lowest error and also allow the process to have different history lengths for each time series forecast.

Lean Forecasting & Planning

Next I attended another advanced session led by Jeff Marthins from Tasty Baking Company/Flowers Foods on “Lean Forecasting & Planning: Preparing Forecasts Faster with Less Resources”. The session focused on doing more with less, a common theme that has permeated the business world these last several years. Marthins’ session was really about how to focus on what matters in demand planning: looking at the overall process, agreeing to and sticking with the various roles and responsibilities in the process, and understanding how the resulting forecasts and plans are to be used by various consumers in the business which drives the level of detail, accuracy and frequency of updates.

To gain an understanding of the demand planning process, Marthins asked the participants to look at a picture of his refrigerator and answer “Do I have enough milk?” This relatively simple, fun question elicited numerous inquiries from the participants around consumption patterns, replenishment policies and practices, sourcing rules, supplier capacity and financial constraints that illustrated the various types and sources of information that are required to develop a solid, well-thought-out demand plan. It was a very effective approach that can be applied to any product in any company.

To illustrate the need to understand the level of accuracy required of a forecast, Marthins used the weather forecast. How accurate is the weather forecast? How often is it right? How precise does it need to be? Once we know the temperate is going to be above 90 degrees fahrenheit, does it matter if is 91 or 94 degrees?  Is there a big difference between at 70% chance of rain or an 85% chance of rain?  What will you do differently in these situations with a more precise weather forecast? Should I plan to grill tonight? Will I need to wear a sweater this evening? Can we go swimming?  If the answer is nothing, then the precision does not really matter and spending time and effort creating or searching for greater forecast accuracy is a “waste” and wastes should be eliminated or reduced in Lean thinking. Marthins also stressed the value of designing your demand planning process with the usage of information in mind. Adopting a Forecast Value Add (FVA) mentality to assess whether each step in your forecasting and demand planning process is adding value will help to accomplish this. Start by asking if the first step in your forecasting process results in greater accuracy than a naïve forecast such as using the same number as last time you forecasted, or a simple moving average? When your accuracy improves with each step in the process, is it worth the effort or time it takes? Can I be less accurate and more responsive and still not have a negative impact? If I can update my forecast every day with 90% accuracy versus once a week with 92% accuracy, or once a month with 96%, which is better? How responsive can I be to the market by making daily adjustments that are nearly as accurate as weekly ones?

In yet another session, the topic of scenario analysis was raised. The team at IBF are getting this one right making sure it is discussed in multiple sessions. What I wonder is how many companies are adopting scenario analysis in the demand planning and S&OP processes? From my experience it is not the norm.  Marthins suggested testing the impact of various forecasts, and hence forecast accuracies, would have on supply chain performance and even using scenario analysis to understand if a systematic bias, either high or low, might make sense. I have known companies that have employed the policy of allowing overestimating to ensure their resulting demand plan was on the high side. Carrying more inventory even with all the associated costs was of greater benefit to the company than a lost sale or backorder. Bias is not a bad thing if you understand how it is used and its resulting impact, just like inventory is not an evil when used in a planned and methodical manner.
[bar group=”content”]

Data Cleansing

After lunch I attended my second session delivered by Mark Lawless from IBF “Data Cleansing: How to Select, Clean, and Manage Data for Greater Forecasting Performance”. As in any analytical process, the quality of the inputs are crucial to delivering quality results. Unfortunately I had another commitment during the session and I could not stay for all of it.

Lawless discussed a variety of ways to look at the data available, decide if it should be used, update or modify it, fill in missing values and apply various forecasting techniques.  Simple reminders and tips such as consideration and awareness for how data is provided in time periods, e.g., fiscal months (4/4/5) or calendar months, and how they should be reported was a good reminder to make sure the data inputs are clearly understood as well as how the output from the forecasting process will be used.

While most of what I heard was related to the data going into the forecasting process, Lawless did spend time talking about various analytics associated with assessing the output of the process. You might be expecting me to talk about various error and bias metrics again but that is not the case. Rather, the idea is to look at the error measurement over time.  What is the distribution of errors? Do they have a pattern or random? If there is a pattern, there is likely something “wrong” with the forecasting process. It made me think about the application of Statistical Process Control (SPC) techniques that are most often applied to manufacturing processes but can be applied to any process. SPC control charts can be applied to check for patterns such as trends, systematic sustained increases, extend periods of time at unexpected very high or very low errors, randomness of errors, and many more. It gets back to the notion that in order to improve the quality of the demand planning process it must be evaluated on a regular basis and causes for its underperformance understood and corrected as much as possible or warranted.

Regression Analysis/ Causal Modeling

The final advanced session of the Academy was delivered by Charles Chase from the SAS Institute on “Analytics for Predicting Sales on Promotional Activities, Events, Demand Signals, and More”.  This session was about regression modeling on steroids.  As someone who has used regression models throughout my career I could easily relate to and appreciate what Chase was discussing.  In two hours Chase did a great job exposing attendees to the concepts, proper use, and mechanics of multivariate regression modeling that would typically be taught as an entire course over weeks.

While time series models are a staple used to forecast future demand, they provide little to no understanding of what can be done to influence the demand to be higher or lower. They can be used to decompose the demand into components such as trend, seasonality and cycles which are important to understand and respond to.  They are focused on the “accuracy” of the predicted future.  Regression models however describe how inputs effect output. They are an excellent tool for shaping demand. Regression models can help us understand the effect internal factors such as price, promotional activity, and lead-times, as well as external factors such as weather, currency fluctuations, and inflation rates have on demand. The more we can create predictive models of demand based on internal factors the more we can influence the resulting demand as these factors are ones we control/influence as a firm. If external factors are included, forecasts for the future values of these inputs will be needed and we become more reliant on the accuracy of the input forecasts to drive our model demand.

In case you missed it, you can see pictures from the 2015 IBF Academy HERE.

I trust I have brought some insight into IBF’s recent Academy in Las Vegas and perhaps offered a nugget or two for you to improve your forecasting and demand planning activities. If only I would have learned something to apply forecasting success at the gaming tables :).

The key question becomes what do we do with all this data? In the past, companies have always struggled with managing and analyzing large sets of data and could seldom generate any insights.

However, what’s different today vis-à-vis five years ago, is that we now have the ability to cleanse, transform and analyze this data to generate actionable insights. Moreover, today’s retail consumers are extremely demanding and want choices on “When”, “Where” and “How” to purchase product. Whether it is a traditional stand-alone retail store, shop-in-shop, website or mobile app; consumers want the flexibility to research, purchase and return product across multiple channels.

Today, many retailers and wholesalers have a vast amount of POS data available. However, many of them still don’t use the data at the lowest level of detail in their demand planning cycle. The result is significant out of stocks and inability of consumer to find product at the stores.

For a company to be successful in today’s Omni-channel environment, three key steps are needed:

1) Use Point-of-Sale (POS) data as a key input into demand plans: POS is the data that is closest to the consumer and is the purest form of demand- it is critical to leverage this data at the right level of detail into a product’s demand plans. Information available at stock-keeping-unit (SKU) level- should be aggregated and disaggregated to ensure that all attributes of a product are factored into the planned forecast.
[bar group=”content”]

2) Link Point-of-Sale (POS) data to your Allocation & Inventory Management Systems: Today’s allocation systems have the ability to read sell-thru at POS and react and replenish based on what product is selling and what is not. It is critical to make sure that these systems are linked together so that the process is automated and seamless. Linking these systems will allow retailers to send the right product to the right store at the right time- thereby maximizing the chances of making a sale. This will not only contribute to top-line, but will also make our inventory investments more productive.

3) Collaboration with Value Chain Partners to share Point-of-Sale (POS) data: Today’s retail world is complex, many companies have multi-channel operations and work with a number of channel partners to distribute their products. In such a scenario, it is not always easy to gain access to POS data. However, it is important for companies to invest in a CPFR program (Collaborative Planning, Forecasting and Replenishment) that can give them access to downstream POS data which can be used to build better forecasts. It is critical to emphasize a “Win-Win” relationship for both companies and channel partners to bring everyone along on the collaboration journey

Along with Rene Saroukhanoff, CPF, Senior Director at Levi’s Strauss & Co, we’ll be talking about the above, as well as how to use size forecasting, optimized allocation, and visual analytics at IBF’s Business Planning & Forecasting: Best Practices Conference in Orlando USA, October 18-21, 2015.  I look forward to hopefully meeting you at the conference!  Your comments and questions are welcomed.

Each educational session, organized as introductory or advanced level, was two hours in length allowing for a deeper dive into content with plenty of opportunity for participant interaction. The instructors were academics, industry practitioners, and software providers giving the attendee a nice blend of viewpoints and experiences.

The first session I attended on Monday was conducted by Dr. Larry Lapide from MIT on Designing and Implementing a Successful Collaborative Demand Forecasting Process. The introductory level session was hands on and highly interactive. Participants were placed into four teams and asked to focus on a case study with questions around organizational design of the demand planning function, reporting needs of the Sales & Marketing, Operations and Finance organization, and various forecasting methods to employ. Dr. Lapide “challenged” the various answers provided by the teams in a manner that allowed for deeper understanding and awareness.

One of my takeaways from the session, and one I heard in several others, is the ongoing challenge companies have to not take the unbiased, unconstrained statement of demand, or for that matter the demand plan, and replace it with the financial budget. Too often firms are not paying attention to the demand signals in the market and turning the projection of future demand (forecast) into a demand plan that mirrors the financial budget created anywhere from weeks to months to quarters before.

Another takeaway was the reminder to design a forecasting process that incorporates multiple methods based upon the various characteristics of the customers, markets, channels and products. Applying segmentation approaches prior to selecting techniques such as time series forecasting, lifecycle forecasting, and collaboration to gain real time knowledge and expertise, will allow for a more robust and effective process tailored to the needs of each segment.

Next I attended the introductory session How to Sell Forecasts to Top Management and Understand the Power of One Number Planning given by Jeff Marthins, Director Supply Chain Operations, Tasty Baking Company/Flower Foods. This was a very pragmatic session with Marthins sharing Tastykake’s journey with S&OP starting in 2005. He spoke about the value of running the business from one set of numbers and using the budget as a benchmark rather than the demand plan or forecast. He made it clear that the forecasts need to be in terms that the various consumers of information can relate to: revenue, units, capacity, etc…

I was intrigued by one of his questions related to demand planner capabilities: if you could pick between analytical or communication skills which would you choose? While both are needed, I believe the analytical skills are the easier of the two to become good at. I would start with solid communication skills. To develop a comprehensive plan that is adopted, a demand planner needs to be an excellent listener, taking information and insights from various sources; an engaging and thoughtful facilitator to guide consensus dialogues; and a crisp, clear, and confident speaker to communicate and defend the rationale for the demand plan being presented and ultimately agreed to by senior leaders and stakeholders.

Marthins’ discussed the need to spend more time to understanding why the plan is different than the actual demand. Was the forecast and/or demand plan low or high because of promotional lift errors; unforeseen market changes; new production launch timing, trajectory, or cannibalization estimates of existing product; or outside influencers such as weather and competitor actions to name just a few? Root cause analysis is something that as a supply chain planning and analysis community we need to do more. Demand plans and forecasts will always be wrong. Hopefully over time they will become more and more accurate. But if we are not researching the reasons why our plans and KPI targets are not being met, we should not have high expectations that they will be achieved in the future.
[bar group=”content”]

I had a huge smile and kept nodding my head when Marthins started praising the need and benefits of scenario management and contingency planning as part of the S&OP process. While the output of an S&OP cycle is typically an agreed to set of numbers, they should not be obtained by looking at only one set of “inputs”. Understanding the implications of various scenarios with changes to demand and supply is needed to have a comprehensive understanding and agreement for a course of action. Scenario management is an excellent means to show decision makers the impact of their opinions about the future while keeping the discussion fact based. Contingency planning allows for a higher degree of responsiveness for risk mitigation actions to be put in place.

The final session of the day I attended was presented by Mark Lawless, Senior Consultant from IBF on Long Term Demand Planning & Forecasting: The Key to Corporate Strategic Planning. Lawless did a nice job throughout the session educating the attendees on the differences between long term (three to five years) and short term demand planning and forecasting. It was helpful to be reminded of the difference between a forecast – an unbiased prediction or estimate of an actual value at a future time and a demand plan – a desired outcome at a future time. Time was spent discussing how firms can shape the future demand, the more aggregated levels of detail to plan with, and the need to engage external subject matter experts in the planning process.

Looking three to five years into the future is not just about applying a time series technique. Companies must rely on internal and external domain experts to assist with potential changes in markets, competitors, customers, and consumers; technology and business cycle impacts; changes in demographics and regulatory environment and many other areas of potential impact. Thinking about where competition will come from is not always obvious. Five or more years ago, would the camera manufacturers have seen their market being potentially challenged by smart phones? Totally not related to the event, but I was intrigued to search for more: in 2000, 86 billion photos were taken with 99% analog (film), in 2011, over 380 billion photos were taken 1% analog. If you were the long range demand planner for camera film would you have seen this coming? Another crazy statistic, that shows that history alone is not always a great gauge for developing future demand plans, in 2011 we snapped as many photos in two minutes as humanity as a whole snapped in the 1800’s. Would this long range trend have been detected by a time series technique?

Long range demand planning requires us to understand the drivers of our demand even more so than short term demand. Our ability to respond to short term sharp changes may be limited, while changes in long term demand can be addressed. Regression, ARIMA, or ARIMAX models are very helpful in this area. Developing models that help explain demand as a function of price, feature/function, market trends, economic factors, age, income, education, marketing, and numerous others allows us to not only see the impact to demand of changes in these variables, but enables us to determine the levers to pull to shape the demand in our favor.

See my next post on the highlights from day two of the Academy. Your thoughts and feedback are always welcomed!  You can also see pictures from the IBF Academy HERE.