Navigating the challenges: declining portfolio forecastability 

In the vibrant landscape of forecast and demand planning, portfolio forecastability faces turbulence due to various factors. Market shifts driven by geopolitical events, technological advancements, and unforeseen global crises introduce an element of unpredictability that challenges traditional forecasting methods. Evolving consumer preferences, shaped by trends, cultural shifts, and societal changes, add layers of complexity that demand planners must skillfully navigate. External factors, such as economic fluctuations and supply chain disruptions, amplify the challenge, making accurate demand anticipation increasingly elusive. 

The XYZ analysis, a renowned method of categorizing products based on demand volatility, vividly illustrates increased variability and reduced predictability of sales across nearly all industries in the last 12 months. For a growing part of company portfolios statistical approach is no longer sufficient.  More and more items need meticulous manual planning or the adoption of more agile and adaptive inventory strategies.

The path forward: agile and adaptive forecasting approaches 

In turbulent times, the limitations of relying solely on statistical forecasts become strikingly apparent. While statistical models excel in capturing historical patterns, they may struggle to swiftly adapt to sudden market changes. The assumptions underpinning these models—based on historical data and relatively stable conditions—can falter in the face of rapid changes. 

So, how can demand planners respond effectively to the challenge of declining forecastability in turbulent times? It demands a strategic shift towards agile and adaptive forecasting approaches, incorporating not only historical data but also real-time insights, forward-looking statistical methods, and the ability to swiftly adjust to changing circumstances. An increasing number of companies are dipping their toes into driver-based forecasting, a strategic approach identifying and leveraging key drivers influencing demand.  

This method employs machine learning techniques and artificial intelligence to enhance predictive accuracy. Driver-based approach builds on the statistical model foundation, recognizing that not all products or services are influenced by the same factors. By understanding the specific drivers affecting each portfolio component, demand planners can tailor their forecasting strategies accordingly. 

Driver-based forecasting relies on a detailed analysis of the various factors impacting demand for each product or service. These influencing factors can be categorized into both internal and external aspects. In specific industries, external factors such as weather conditions, economic indicators, and market trends play a significant role. Conversely, in different sectors, internal indicators like contract positions and order books carry more relevance. Incorporating these drivers into the forecasting model enhances the accuracy and relevance of predictions.

Difficulties in adopting driver-based forecasting 

The adoption of driver-based forecasting comes with inherent challenges. Organizations are required to invest substantially, leveraging advanced analytics tools that align with this methodology. Equipping demand planners with the requisite skills and establishing a resilient feedback loop for continuous enhancement are integral components of this implementation. Many supply chain managers grapple with the evaluation of the necessity for such an investment, recognizing the complexities involved in this decision-making process. It’s a decision that involves not only financial considerations but also a comprehensive understanding of the specifics and volatility of the demand dynamics, what statistical forecast still brings and where additional drivers would be required. 

In order to help companies to solve this puzzle, EyeOn came with the Fast Forecast Scan. It is a quick tool to provide rapid insights into demand characteristics and forecastability. The Fast Forecast Scan expedites the identification of improvement opportunities, guiding strategic decision-making on proper forecasting methods, be it statistical or driver-based. The scan unveils the highest possible statistical forecast accuracy for each product in your portfolio, identifying key improvement opportunities in your current forecast setup. Our experienced specialists identify items challenging to forecast with statistical methods and that can have potential for further driver-based analysis. Witness the transformative power of the Fast Scan through our on-demand demo.

The post Declining forecastability: Can your portfolio still be forecasted? appeared first on EyeOn.

 3-minute read 

How do we get to accurate forecasting? The truth is simple: Our forecast should be a reflection of the plans we develop and the assumptions we make on our demand drivers. In reality, creating a plan is one thing, while making a demand-driver-based forecast is another thing.

In a poll, we asked our network what you find the most challenging in making a realistic forecast. The response was clear. You struggle to define your sales plans and the assumptions on your demand drivers. And when you manage that, turning the agreed plans into a forecast is the second hurdle.

Because creating the plan and the forecast is already challenging, actually bringing focus to where you can improve and to learning from your performance are the least of your worries.

So, how do you get to accurate forecasting then? You will need all 4 elements to drive change. Let’s start with the most pressing challenge:

Defining your plans and assumptions

Every business will have a few big drivers of demand based on which you can make assumptions for the future. When an organization focusses on assumptions first, the reasoning that leads to  the forecast immediately gets less biased. To get there, we advise the following steps:

1. A version of an S&OP process is a prerequisite to ensure the decisions on plans and assumptions can take place.
2. A pragmatic solution to capture plans and assumptions is imperative to support your S&OP decision making.

With a focused process and a pragmatic solution to support it, you have the necessary foundation in place.

Turning your plans into an accurate forecast

Once you have the plans in place, how can you avoid that the forecast ends up simply being a copy of the past? The more focus you put on qualitative plans and assumptions, the less time you actually need to spend on creating a forecast. With techniques like driver-based forecasting the machine delivers the forecast for you. A machine learning forecasting technique incorporates decisive aspects such as your sales data, and past and future information about your demand drivers, into a forecast. At EyeOn we currently have multiple customer cases where the machine generated forecasts outperform the manual forecasts with a substantial workload reduction.

Spotting vital review areas

But is the machine always the better option? We recommend smart-touch planning. The best forecasts are the result of a machine doing the heavy lifting and planners stepping in where their expertise is needed. With the right insights, the planners instantly spot where they can make a difference. Eventually, the more the machine learns about the products, customer, and drivers, the less intervention is needed. Want some more inspiration on this, stay tuned for the launch of our EyeOn Promo app which offers actionable insights on your promotional plan based on machine learning.

Accurate forecasting: Learning from performance

Finally, planning and forecasting is not an exact science, but there must be more science to it than covered by manual forecasting. And like for every science, learning is imperative.

On the one hand, the machine learns from every single data point in combination with your qualitative plans and assumptions in a way no planner could match that.

On the other hand, also the planners need to learn. They should learn about how the machine delivers the forecast. We believe, a forecasting set-up should have machine learning elements at its core, but always in combination with explainability functionality. Next to the technical learning, the planners should also understand how they contributed to the forecast. You can create this awareness by bringing in concepts like cognitive insights. As soon as you adopt a mindset of continuous learning, forecasting isn’t a challenge anymore, but rather a way to unlock potential and achieve success.

Are you ready to take the steps towards a more realistic forecast? Please feel free to contact our expert Erik De Vos to discuss your situation and explore solutions together.

The post What is your biggest challenge in accurate forecasting? appeared first on EyeOn.

4-minute read 

A snowy predicament: how machine learning models can learn the wrong things

Imagine a machine learning model that’s supposed to tell the difference between a wolf and a husky, but instead, it’s learned to recognize snow. This might sound like a joke, but it’s a real-world example of the limitations of current machine learning models. Researchers have found that a model trained with inadequate data can make mistakes in classifying images of wolves and huskies, and instead learn to identify snow as the main characteristic! The key message here is that for demand planners to trust a machine learning model, we need to have a way of asking the model how it arrived at its predictions.

From wolfs and huskies to machine learning in demand planning

In the field of supply chain demand planning, we’re in the middle of a shift towards the use of machine learning models. At EyeOn we often refer to this as driver-based forecasting. These models offer great potential to provide more accurate and less biased forecasts by incorporating external drivers. However, with an increased use of machine learning also come challenges. One of the main challenges is that these models are often considered to be black boxes, making it difficult for demand planners to understand how the model arrived at its predictions.

To truly reap the benefits of driver-based forecasting, demand planners need to effectively work together with these machine learning models. And to do this, trust is key. But how do we establish trust in a model that we can’t fully understand?

Explainability addresses this challenge by providing demand planners with a clearer understanding of the predictions and decision-making processes of machine learning models. This transparency helps build trust in the models as practitioners can see how the model arrived at its predictions. By having insight into the model’s prediction processes, planners can more effectively collaborate with the model; trusting it when it is correct and recognizing when it might be off. Additionally, explainability can also lead to a deeper understanding of the underlying business dynamics and challenge previously held assumptions.

From theory to practice: explaining the demand forecast

Let’s bring this to life with a concrete example: Imagine you are a demand planner working with machine learning models to generate a demand forecast planning for your portfolio. You have a good understanding of the drivers that influence demand for your products, including the impact of promotions. However, it can be challenging to get a clear picture of how the different drivers interact and affect your forecasts. To validate your understanding, gain trust in the model, and make better-informed decisions, two visualizations can be of great help.

First of all, let’s say you have a demand forecast of 73.64 for a specific product in a certain time period. The ‘waterfall plot’ can show us how the model arrived at this forecast. The plot starts with the baseline forecast, then each row shows the positive (red) or negative (blue) impact of each driver (or feature) on the forecast. In this example, we can see that the forecast is higher than the baseline due to the presence of a promotion for this product and a high number of open orders for the same period.

Secondly, for a higher level summary of the impact of each driver, the ‘beeswarm plot’ is a useful tool. It displays the impact of the top drivers on the model’s forecast in a compact and clear format. Each forecast for a product-time period combination is represented by a dot on each feature row. The dot’s position is determined by the driver’s impact and the dots pile up along each feature row to show density. Colour is used to show the original value of the driver. It becomes evident that the presence of a promotion (represented in red) has a positive effect on the forecast, whereas its absence (represented in blue) has a negative effect. Likewise, the number of open orders is also seen to have a direct impact on the forecast, with a higher number generally resulting in a more positive influence.

Conclusion on using machine learning in demand planning

Machine learning models are rapidly becoming a crucial tool in supply chain demand forecasting. However, their black box nature often makes it challenging for demand planners to understand and trust the predictions made by these models. That’s why explainability is becoming increasingly important, as it provides planners with transparency into the models’ decision-making processes and helps build trust in the results. In conclusion, explainability can act as a catalyst for change in the supply chain planning and forecasting process, as it allows practitioners to challenge business assumptions, learn about underlying business dynamics, and eventually make better-informed decisions.

Are you interested to learn more about driver-based forecasting?

Please contact us to see how driver-based forecasting can be of added value to your organization! Reach out to Rijk van der Meulen or Willem Gerbecks.

The post The importance of interpretability for effective demand planning in the age of machine learning appeared first on EyeOn.

Today’s increasingly volatile market requires dynamic and accurate forecasting, but good demand planners are hard to find, and even harder to keep! Planners are rethinking what meaningful work looks like for them – and wading through thousands of line items each forecast cycle to produce reliable forecast numbers, often does not fit that bill. Machine learning can help.

There is an abundance of data available today, but the sheer volume of it makes for days of processing effort, or in practice, just accepting that a lot of your data is under-utilized, especially in forecasting. But what if you could truly leverage the predictive value of your data to generate high-quality forecasting outcomes quickly? What if your planners could instead spend their time focusing on enriching only a limited number of forecast exceptions while closely collaborating with business?

In this webinar we show how machine learning can use the relevant demand drivers for your business and learn from their historical data to enhance the predictive power of your forecast. Creating a value-adding machine learning model is challenging, but we explain how our approach to get started instantly using Planning Services gradually builds up your forecasting capabilities. We share real-life cases on how our approach has proven to be successful in practice.

Below is a snippet from the webinar. Watch the complete on-demand webinar here!

Watch the complete on-demand webinar!

The post On-demand webinar: Leverage your data with driver-based forecasting appeared first on EyeOn.

Why driver-based forecasting is the key ingredient to success

The biggest challenge in forecasting is how to come to a fact-based and realistic plan and forecast. Although in every business there are internal and/or external factors that have a causal relation to demand, it can be hard to bring the right drivers for demand into your forecast. What if your forecasting method would do this for you, so you can focus on more important business decisions? By using demand drivers as the basis for forecasting, you can process and deliver the right information to the right person’s desk at the right time.

How does driver-based forecasting work: Complement your forecast with the right spices

The already mentioned internal and/or external factors can help you foresee how the demand of your products is going to develop. Examples for internal drivers are promotions, orders, or a product plan. External drivers are for example point of sale information, holidays, or the weather.

Traditional forecasting methods, such as time series forecasting, don’t take this data into account. The statistical forecast needs to be manually enriched by your planners. This requires a lot of time and skill from the planners and introduces a risk of human bias.

With machine learning, we can identify demand drivers for your business and learn from the past data of these drivers to enhance the predictive power of your forecast. This approach is much more fact-based, offers an automated way to get insights, and enables the planners to balance time and effort.

The recipe for starting driver-based forecasting

Are you ready to steer your business based on more precise forecasts but don’t know where to start? Creating a value-adding machine learning model can be challenging. In our next blog, we will talk about the hurdles companies might face when implementing driver-based forecasting and how to overcome them.

Can’t wait to start improving your forecast performance? Taste the future with driver-based forecasting: Contact us now!

Or learn more about our Fast Forecast Scan. The EyeOn Fast Scan provides organizations with a clear stick in the ground of current forecast maturity and the potential that can be reached. This can be used as a great starting point for taking the right improvement steps.

The post Taste the future: What is driver-based forecasting? appeared first on EyeOn.

Meta-learning will better capture your demand pattern

A straightforward and robust way of matching a statistical forecasting method to a series of historical demand values is to simply try them all and select the statistical forecasting model which achieved the best forecast accuracy during a rolling forecast. However, the main downside of this approach is that this requires a significant number of computations. In addition, the information used to select the statistical model is confined to the data of that single demand pattern.

What if we could somehow store the decision for one statistical model over all the others for every demand pattern? Meta-learning offers a way to do just that. Meta-learning in demand forecasting is a method that uses descriptive statistics of a demand pattern to match the way the pattern ‘looks like’, to a statistical model that offers a high accuracy and low bias forecast. Which comes down to a multi-class classification problem within the field of machine learning.

Assigning statistical forecasting model to a time series

We can utilize a two-step machine learning classification approach of assigning a statistical forecasting model to a time series. By first encoding a time series into context-independent descriptive statistics, we can train a decision tree classifier to assign a statistical forecasting model. In the second step, a multitask neural network handles the conditional question of which parameters the assigned model should use. Once a training set of observations has been labeled, both classifiers can be trained. Assigning a statistical forecasting model to a new time series comes down to calculating its descriptive statistics and allowing the classifiers to recognize the best-fitting model plus parameters.

One of the benefits of meta-learning is the reduced number of computations to be performed in exhaustively searching the performance during a rolling forecast test run each period. In addition, an increase in forecast accuracy is anticipated on very variable demand patterns, such as strongly intermittent demand. These two benefits are especially relevant today, where the ability to accumulate data and have access to an increasing number of demand patterns, increases the number of forecasts to be generated.

Staying ahead in the demand forecasting game

To stay ahead in the practice of demand forecasting, EyeOn continuously explores new techniques to further increase the value we can offer our customers. Recently our intern Robert Duijfjes explored the possibilities and added value that meta-learning can offer in demand forecasting across industries. He concluded that the added value is mostly visible in extremely volatile demand patterns, which is exactly the part of the portfolio where customers often encounter challenges. Applying meta-learning to these cases results in more focus and therefore a major time-save for the customer because the demand planners only need to perform forecast enrichments on a smaller part of the portfolio.

Next to meta-learning, we are exploring other options to improve your forecast performance. With these innovative methods we will be able to achieve improved forecast accuracy and bias, whilst handling larger portfolios.

To make sure our clients can benefit most from these new innovations, we’ve developed the Fast Forecast Scan: a quick tool that provides you with rapid insights into the demand characteristics and forecastability of your business. As a first step, we perform a thorough deep-dive into your data and provide actionable data quality insights. With improved data quality, the Fast Forecast Scan provides you, within a few days, with data-backed insights on the highest possible forecast accuracy that can be reached and identifies the main opportunities for improvement. Learn how the Fast Scan can help you reveal your forecast optimization potential.

Curious to hear more about meta-learning or other forecasting innovations? Reach out to our expert Rijk van der Meulen!

The post How can SKU time series improve forecasting accuracy with meta-learning? appeared first on EyeOn.

Curious about the potential of driver-based forecasting for your business? Get in contact with us for a proof-of-concept!

The post Video: Discover the benefits of driver-based forecasting appeared first on EyeOn.

EyeOn offers a framework to leverage the full potential of your demand planners. In this webinar we presented how our framework can guide your demand planners.

Watch the webinar recording below to learn more, or contact us directly!

The post Demand planning 2.0 – Take control of your role! appeared first on EyeOn.

Read here the article (in Dutch)

The post Keep control during a hurricane appeared first on EyeOn.