How To Leverage Machine Learning ' In Your Demand Planning Process

• Published date: 10 July 2023
• Law Firm: Implement Consulting Group
• Author: Mr Mike Weisbjerg, Simon Lundmark and S'ren Skj'dt

What if you could greatly improve your forecast quality by combining human and artificial intelligence?

The rise of advanced analytics, artificial intelligence (AI) and machine learning (ML) has challenged status quo and what best in class looks like in many business processes - and demand planning is no exception.

However, the three key elements of an efficient demand planning process are still the same - that is trust, purpose and accuracy.

At Implement, we believe that machine learning models will bring an evolution to demand planning and, if applied correctly, improve your forecast accuracy. Some parts will change within capabilities and processes as well as obviously also which advanced models to use, while other parts - such as importance of transparency, incorporating knowledge from sales, measuring and follow-up - will remain the same.

Based on our experience in working with organisations across different industries, we typically see the following challenges of applying machine learning models in demand planning processes:

• They do not have the ability to continuously evaluate the models used
• They expect planners to learn the capabilities of advanced models
• They have unclear rules about what the forecast model should cover and what input is needed
• They fail to measure the quality of the models as well as the human input
• They try to apply advanced models to poor data sets

To solve these challenges, we believe that:

• You can only use the model that you are able to explain the results of
• The future demand planner is a team that combines data knowledge with classic demand planning expertise
• The boundaries between human and machine must be clear
• You need to measure the accuracy of both
• Forecasting what will happen next year for S&OP requires another model than forecasting what will happen next week
• Start by ensuring that the right data foundation and quality are in place before starting to decide which models to use

In the next sections, we will explain these solutions more in depth.

Only use the car you know how to drive

Machine learning is praised and hyped, and it is thus tempting to start looking into using it for your demand planning process too. However, applying machine learning to any process requires new capabilities of your demand planning team and IT.

In machine learning and time series forecasting, there are different model types, e.g. linear models, tree-based models and neural networks - all with different advantages and disadvantages. If your organisation is not ready to support the more advanced models, such as neural networks, or if your data pipeline is not streamlined, the most advanced models will be difficult to implement. Thus, we recommend starting with linear models or tree-based models - even if you have access to neural networks and deep learning in your IT stack.

You can improve your forecast accuracy by using machine learning models compared with simple statistical models. However, using machine learning is not a guarantee for high forecast accuracy.

In the field of time series forecasting, the M forecasting competition is often used as a reference for how mature machine learning models and teams are in forecasting the demand of Walmart. In the most recent competition (the M5 competition), only 7.5% of the almost 6,000 submitting teams beat a simple exponential smoothing in accuracy (Makridakis et al. 2020, The M5 accuracy competition: Results, findings and conclusions). However, those who beat the simple benchmark did it with a good margin, which indicates that there definitely is potential for improvement.

The fact that 92.5% of the teams were not able to get an improved accuracy by using machine learning shows the...