How to make a next step in forecasting with machine learning

Driver-based forecasting’ with machine learning

Data is everywhere in today’s world. Every single event in your supply chain generates data, and the opportunities to utilize all that data seem endless. At the same time, there are many tools and technologies out there claiming to solve all your data problems. No wonder many professionals feel overwhelmed!

Which key opportunity can you unlock by using your data better? Reducing latency! Quicker data collection, better dashboards, and suitable tools help you get the right information on the right person’s desk at the right time – effectively reducing the delay from event to decision, and thereby dramatically increasing the impact of your decisions. Machine learning can help.

Results from a benchmark conducted by EyeOn in 2021 show that:

  1. companies are most eager to start applying machine learning in the area of demand forecasting
  2. only 10% are actually doing this at that moment.


machine learning models used in forecasting


While the goal for each company is straightforward – trying to improve forecast performance with less effort spent by demand planning, sales, and marketing altogether – there is no one-size-fits-all solution that can do the job.

Do you want to improve your forecast performance and accelerate decision-making in the supply chain? Watch our video on driver-based forecasting!


What is driver-based forecasting?

Let’s start from the core. Why do companies want to apply machine learning? This is because traditional forecasting methods, such as time series forecasting, do not take into account impactful demand drivers. In many industries, there are additional drivers that have a far greater effect on demand than for example seasonality.


in which situations does machine learning benefit forecasting?


In machine learning models we incorporate data that relates to these demand drivers, with the aim to learn from their impact in the past in order to reflect this in the forecast. Depending on the industry, internal or external (market) drivers are more relevant to the forecast. In general, internal drivers often have a focused impact on forecasting, such as planning a promotion for a certain range of products at a specific customer or introducing a new product to your biggest customer.


demand drivers necessary for applying machine learning in forecasting


Creating a value-adding machine learning model takes effort and time but can really have a big impact on your forecasting performance. Two of our projects have shown that by applying driver-based forecasting the final forecast (including all manual input from sales and marketing) can be improved by even 12%pt of forecast accuracy and can bring bias within the 2% bandwidth. Another big advantage is that since the most important known demand drivers are already taken into account, only exceptional changes are needed to come to a final forecast.


comparing time series forecasting with machine learning forecasting


How to start applying machine learning in forecasting?

As mentioned in the introduction, it is not easy to start applying machine learning in demand forecasting in a proper way. Tooling and knowledge are the biggest hurdles that companies face.

IT departments often have a long-term IT roadmap and need to see how applying machine learning in demand planning would fit in there. On the other side people currently involved in the demand planning process often do not have the technical capabilities to build a small proof-of-concept themselves.

Surprisingly, most companies do not think that the quality and availability of their data should be a roadblock. Let’s take the example of a company, with access to suitable tooling, people with the right skill set, and high-quality data available, then still there is another hurdle to overcome and that is the question of what it will bring? Preparing a proper business case is crucial.


Requirements for applying machine learning in forecasting


Luckily, that is something where EyeOn can be of help. We can build a proof-of-concept in a very short amount of time. Our data scientists build and apply machine learning models in a very pragmatic and robust way. The proof-of-concept offers you:

  • Quick insights into the value of demand drivers on the forecastability of your business
  • The maximum forecast performance that can be reached by using driver-based forecasting
  • A quantified improvement potential versus current forecasting methods (in efficiency and effectiveness)

The proof-of-concept shows great potential and you would like to grasp the benefits immediately? Our Planning Services team is ready to build and operate your driver-based forecasting process from the start. In the meantime you can work on getting tooling and knowledge to the required level, so we can transfer the operation back to your internal organization.


Tooling, knowledge and business cases needed for applying machine learning in forecasting

In this video we further explain the EyeOn driver-based forecasting proof-of-concept:


We are here for you!

Do you want to improve your forecast performance? At EyeOnwe’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. Witness the transformative power of the Fast Scan through our on-demand demo.

You prefer to speak to one of our specialists? Please reach out to us and see how driver-based forecasting can be of added value to your organization: Contact Erik de Vos, Willem Gerbecks, or André Vriens!

Search for