The importance of demand forecasting is clear. Robust forecasting improves critical KPIs like customer service levels, inventory turns, and cash. 

However, demand planning is only as effective as the data informing it. Demand forecasters may find the results less trustworthy and reliable if the content fed into a forecasting system has errors or duplicate records. Creating and adhering to a thorough information collection and processing strategy prevents such outcomes.

Decide Which Data to Use

The first step is determining which data the company will use for its demand planning. The information collected in a point-of-sale system could be valuable for highlighting sales patterns, such as which times of the year specific products are most popular and what other things people typically buy at the same time. A practical approach for companies with numerous retail outlets is to gather data showing which stores have the most robust or slowest sales.

“Inventory tools give a broader picture by showing how stock levels change over time”

Alternatively, inventory tools give a broader picture by showing how stock levels change over time. Seeing that historical context can help decision-makers determine how long upswings and downturns might last, whether these events previously occurred and what caused them.

A related question is whether those working on data quality within the organization know the location of the information identified as worth using. Many companies still maintain rigid silos that create challenges for collecting and using information across departments or teams.

Establish a Data Quality Baseline

What’s the current state of the company’s data for demand planning? A data quality baseline answers that question. People must start by identifying the critical data elements (CDE). These collectively represent the information that will shape leaders’ future decisions.

Examples of CDEs in demand planning include:

• Supplier and customer names
• Order quantities and dates
• Restock frequency
• Merchandise prices
• Average order fulfillment timelines
• Dates associated with short-term promotions
• Most and least-popular product names and descriptions
• Inventory management system reports
• Distributor names and locations

The next step is to establish data quality indicators with input from those who understand and value the importance of demand forecasting in modern businesses. We should typically measure the following:

• Timeliness
• Uniqueness
• Accuracy
• Consistency
• Completeness
• Validity

They often rely on specialized tools to show data quality gaps and begin developing improvement plans. However, it’s also important to discuss challenges experienced by the people who collect and use it daily in their roles. They’ll likely have valuable input for changes that might have been overlooked.

Understand Data Governance Needs

Data governance encompasses keeping information usable, secure and available while retaining its high quality. Maintaining it is a team effort of ongoing collaboration to create and uphold standards. People on the data governance team will also help establish organizational norms by training employees to handle them and reduce the chance of errors.

Data governance policies will differ in an organization depending on the type of information used for demand planning. Anything containing payment details or personal info must be treated with more care.

“Many companies use third-party service providers to meet their data-handling needs”

Many companies use third-party service providers to meet some of their data-handling needs. In such cases, data governance plans must include steps to take so those outside businesses don’t compromise quality.

Documentation is also a major part of data governance. Keeping an ongoing record of the data source, location and associated security protections helps organizations use the information and address oversights.

It’s becoming more common for companies to collect data with Internet of Things (IoT) sensors. This gives a more detailed view of what’s happening with the information. Although confirming data sources can initially be time-intensive, the increased analysis opportunities are worthwhile. Estimates indicate the IoT sensor market will experience 24.9% growth in 2027, suggesting decision-makers are interested in using them.

Create and Maintain Data Preparation and Use Processes

Those overseeing data quality and usage within the organization must develop a preparation process everyone can use before feeding the information into platforms for further analysis.

For example, people must check the data for anything that could skew the results. Under- or overestimating demand can add to the organization’s costs, and mistakes often cause these outcomes. Thorough preparation requires looking for duplicate records, misspelled product or customer names, and any information in the wrong format. All those things could result in miscalculations or data not being included in an analysis.

The resultant process must be well-documented and easy for others to follow. Those qualities will be instrumental in getting usable, consistent results within the organization.

Next, people must make a framework for how people within the organization can and should use the data for demand planning. Which tools will they use? Must leaders invest in automated solutions or other products to support the process? Which employees will be directly involved in collecting or using the information? Getting feedback from those parties before and after making the data usage framework should optimize outcomes.

Teach the Importance of Demand Forecasting to Employees

Once the responsible parties design the processes for preparing and using data, they must communicate and teach it to all others handling the information. When all relevant employees understand the importance of demand forecasting, they’ll play important roles in upholding the requirements.

Allow plenty of time for people to get used to new tools or processes. Encourage them to give feedback about everything new and provide insights about further improvements.

Some organizations still use spreadsheets to track activities across the global supply chain. Lasting change will take longer to enact in such companies, and people may feel overwhelmed initially. However, most can adapt to new processes if their managers are patient.

“Employees who understand how to maintain high data quality will feel empowered”

Discuss how seriously the organization takes the importance of demand forecasting and explain why. Employees who understand how to maintain high data quality will feel more motivated and empowered.

Leaders should also be open to hearing about any problems, concerns or challenges that arise as employees work to keep data quality high within the organization. People are more likely to be honest about the highs and lows of this transition if they know managers will hear and respect them.

Treat Data Quality Standards as Works in Progress

High data quality allows leaders to make effective and confident demand planning decisions, no matter what a company sells or how many customers it serves. However, even those who will never act on what the information says are instrumental in gathering and preparing it.

Although these steps will assist company representatives in creating data quality processes, people must periodically revisit the current procedures and assess whether they’re still working as intended. It’s not a sign of total failure if they aren’t. However, it’s a strong indicator it’s time to get to the bottom of what’s going wrong and work to improve the shortcomings.

Data quality standards may also change as a company grows, begins offering new products or must follow updated regulatory requirements. People who understand this and know data quality is never a static measure will collectively help their organizations reach new demand planning goals.

To read more of Emily’s work across business, science and technology, head over to her online magazine, Revolutionized.

To get up to speed with the fundamentals of S&OP and IBP, join IBF for our 2- or 3-day Boot Camp in Miami, from Feb 6-8. You’ll receive training in best practices from leading experts, designed to make these processes a reality in your organization. Super Early Bird Pricing is open now. Details and registration.

 We all work with data but we’re not all data people. We must recognize that everybody who interacts with data plays an important part in cleaning and maintaining it so that it is reliable and can be fully exploited by all stakeholders in a business. Of course, we’re not all professionals in that area and it can be quite intimidating to some people.

The Very Real Problems Caused By Data Errors

 One common problem is not getting documents to match up because the dates are in different formats (UK vs USA, for example), causing someone to spend ages manually reconciling the different formats.

I see people waste hours or even days on something basic that could have easily been avoided. When dealing with clients, I might see specifications labeled with incorrect measurements like centimeters instead of meters, and a whole host of other errors that are easy to make but can cause the wrong things to be ordered or in the wrong quantity or in the wrong size which can cause huge disruption to the business.

Rogue zeroes are a classic case, “I only meant to order ten, not a thousand!”

Data errors can mean excess stock in your warehouse or fines from your customer for not delivering on time. All kinds of problems can result from one small little data error. Rogue zeroes are a classic case, “I only meant to order ten, not a thousand!”

 Let’s say we sell sticky notes online and in stores and we have 3 suppliers. Supplier A calls them ‘Post-It notes’, Supplier B calls them ‘Sticky Notes’ and Supplier C calls them ‘notepads’. They’re all the same thing so we need to categorize them as the same thing if we want an accurate picture of how much you’re selling, buying, or forecasting.

When you have bad data or missing data, your forecasts will be compromised.

 Now we see this problem especially with forecasting. When you have bad data or missing data, your forecasts will be compromised. I’ve seen seven ways to format ‘United States’. If you’re forecasting products sold within the US, you need all the data points labeled in the same way which means getting everybody to agree a set standard about how to input data.

Maintaining Data Discipline

You can facilitate this by controlling what people can put into certain columns; some might be mandatory or maybe sometimes you can do drop-down lists (although those have problems because people are lazy and naturally we’ll just pick the first thing). Expectation setting and getting people to understand the importance of data classification is key – letting your colleagues know that just by putting a little bit more information in a spreadsheet means somebody else isn’t to waste two hours doing unnecessary work down the line.

Check Your Data Regularly

I’m a real strong believer in data maintenance because you cannot keep your data clean if you don’t maintain it. You have to check it regularly and make sure that it’s still the way it’s supposed to be because people can delete things and people can cut and paste over things.

The most important thing is to look at your data on a daily or weekly basis because you’ll know if it doesn’t look right. For example, if somebody accidentally inputs a thousand units instead of a hundred, and you know that every week you’re ordering 100 units, you’re going to spot that difference and be able to fix it.

Driving Consistency In Data Management

I’ve categorized retail data, I’ve categorized food data, procurement data – I’ve categorized everything. The one thing that is true across all datasets is the importance of maintain standards and consistency. I came up with something to help clients remember that which is making sure your data has its “C.O.A.T” on. Your data should always be:

Consistent: Your data should always be consistent so everybody’s using the same terminology, the same units of measure, the same formats, and the same processes for data input.

 Organized: Categorize data in such a way that if you need it you can pull out that information really quickly. If you need to look at it by country or division or region or by buyer or by department, categorize it like that and then you can pull off a report quickly. How many people within companies trying to cut and paste different spreadsheets together to get what they want when all you need to do is a quick VLOOKUP?

Accurate: Make sure it’s as accurate as possible. I would never claim that you could get your data 100% accurate – if you do it’s not going to stay like that for very long because too many people involved. But striving for 100% accuracy means it’ll be accurate enough to have utility in the business.  

Trustworthy: This is where the magic happens. Trustworthy data means you know you can go to your senior decision makers and say these are the right numbers – this is exactly what we’re doing, this is what we’re buying, this is what we’re selling, this is what we’re forecasting etc. Data facilitates decisions, after all, and we need to have faith in the numbers.

Data Classification Is Key To Business Efficiency

All too often I see businesses taking weeks to prepare reports for end of month and in every case it’s easy to streamline that process and get that reporting process done in a few days rather than weeks. Rather than spending hours resolving queries, we can create lookups and formulas in Excel and get the data we need so much quicker.

It’s only when you fix these data issues that you realize how long these things were taking – so often people just sit in a time vacuum when you’re working through these things and nobody raises an eyebrow because in the absence of a better system, it just has to get done. I’ve seen that many, many times. 

Cleaning your dirty data means greater productivity, whatever your role or functional area

And that’s the value driver of proper data management – speeding up processes to make your business more efficient. It means your people can work on more value-added activities instead of manual, repetitive tasks. Cleaning your dirty data means greater productivity, whatever your role or functional area. – Send comments to the Editor at andrews@ibf.org

It’s your first day at a new company and you’re tasked with implementing S&OP. What’s the first thing you do?  The best starting point is to figure where to get the data for your forecast, and how you’re going to prepare it for input.

When we start with S&OP implementation it is essential to have the support of senior management and key people in each function to put all the pieces together. We’re talking Sales, Operations, Finance, Logistics and Purchasing. This collaboration is crucial for many reasons but primarily because this is how we get data, and without data, you don’t have an S&OP process.

The S&OP process must be aligned with Finance, making sure data inputs for both forecasts come from the same source. But before you start thinking of preparing your forecast, it is necessary to understand the following:

1. Know The Financial Performance Of The Company

The income statement of the company provides insight into what is really going on in the company. I consider it highly advisable to spend some time studying these statements and talking with the Finance people to identify the burning issues of the moment that are driving the decision-making process. Never lose sight of the fact that the S&OP process is a decision-making tool that directly impacts the income statement. Work to build the trust of senior management to reinforce this idea.

2. Know How Finance Uses Financial Statements

If Finance is using this information to plan for demand, the company will almost inevitably have planning problems. Using only this information is limiting because it is simply sales, dispatches and credit and debit notes applied to the account of each client. Dispatches and sales are not enough to plan effectively. It may happen that the difference between billing and dispatches is minimal, but either way, we need to know what the difference is in order to align the objectives of the business with those of Supply Chain and Operations.

3. Use Finance’s Data For Your Forecast Input

Use the same dispatch/sales information used by the Finance team as the input for your forecast. Why? Because we must use the same data if our forecasts (and subsequently plans) are to align. In every S&OP process, shipments to customers valued in USD is the first information we get from Finance. Use this data as the main input for your sales forecasts. If we skip this step and use Sales’ data for our capacity planning, we can end up Production not having the required resources, because Finance has developed the budget using completely different assumptions.

Once we have covered these 3 points, we can move onto data management.

Data Management

1. Look At The Data In Different Ways

Breakdown the data by client, by product, by production plant etc. This allows us to identify customers and their buying patterns. We can manually check for quirks that, if not picked-up on, can create errors in the forecast. One such quirk is a customer who used to buy products from one of your production plants, for but for whatever reason now buys from another. It can look like two different customers in two different locations, but in reality is the same customer. Another example is a customer changing its business name – it looks like two different customers but is again the same customer. Statistical forecasting without this manual override will not identify these quirks and will result in forecast error that is easily avoidable.

This bit of the process is repetitive and, frankly dull, but it’s important at the beginning because we need to cleanse our data that goes into the forecast. The old adage of garbage in, garbage out applies.

2. Look At product Mix

Looking at product mix is valuable because it allows use to identify changes in consumer behaviour, drops in demand of a particular product, changes in a specific customer’s behaviour etc. We can gain insight into what customers are doing and why, relating their behavior to specific demand influencing factors.

3. See If New Products Will Be Released

The S&OP process pays special attention to new products. Why? Because there is no historic demand to help us understand how many we’ll sell. We have very little idea how it’ll perform until it’s released into the market, by which time the initial planning phase is already completed. This means we must leverage the S&OP process, with its benefit of cross-functional collaboration, to gather as much qualitative insight as we can. We may not have hard data, but this knowledge can help us predict how it’ll perform.

With these steps completed we can start our forecasting process and arrive at numbers we can take into the pre-meeting. In the pre-meeting you’ll sit down with representatives from the Sales team and gain their input into short term demand and another factors that may influence demand that salespeople have unique insight into. This qualitative knowledge will help us refine our statistical forecasts. We’ll then be ready to go to develop a one number forecast all functions will work from. And when we have done that, we will have achieved the core component of S&OP – the creation of an integrated approach to understanding and fulfilling demand.