Meeting service levels without tying up too much capital in your stock is a tough balancing act – especially across more than one echelon. How to decide how much stock you need in which location?
Work smarter, not harder – with reinforcement learning
The traditional way to solve this problem would be by using approximations, heuristics, or simulation. We say, this is a challenge for machine learning!
Reinforcement learning is a branch of machine learning that trains the computer to take the right decisions. In the beginning the accuracy is low but as you keep training the results get better. Imagine you are training a dog to bark when a stranger is approaching by giving it a treat when it does it correctly and telling it off when it barks at a friend. With time it learns to identify when to do what.
Reinforcement learning solves your inventory challenge by finding the most cost-effective policy. This way, you don’t need to evaluate all the policies, saving you time and effort. With reinforcement learning you can solve complex inventory problems, and yet maintain an interpretable solution and simple decision rules. It can handle not only constant but also changing demand patterns, a major advantage in today’s volatile environment!
We get your business years ahead
To enrich the offering to our customers, we at EyeOn explore and apply the latest methodologies and techniques. The project of our intern Floor van Helsdingen is the perfect example: Floor successfully applied reinforcement learning to a complex inventory problem of one central depot supplying multiple local customer-serving depots. There is hardly a hotter topic these days than machine learning, and we have demonstrated its potential for inventory challenges.
Next to classical reinforcement learning methods, we are exploring deep reinforcement learning. With this innovative method, based on artificial neural networks, we will be able to achieve even better solutions and handle even larger product portfolios.