The integrated use of Rule Engine and Machine Learning (ML) products becomes more and more popular. OpenRules Rule Learner is a good example of such integration. While there are plenty of powerful Machine Learning algorithms available off-the-shelf, it can be quite practical to use rules-based machine learning instead. The classical rules-based technology may address learning problems considering historical and constantly changing operational data. In such situations a “Rule Engine” plays a role of a “Rule Learner”. Here is a good example.
One of our customers provides field scheduling software that usually requires a lengthy configuration process to setup “who can do what and where”. So, they wanted to use Machine Learning to learn this information from the actual historical work assignments. After considering different ML algorithms, they ended up defining intuitive business rules that analyze work assignments and automatically generate the proper configuration information. For example, this simple decision table
shows how they define a skill level for a field worker who does installations based on the numbers of actual installation assignments. They use a rule engine (OpenRules) to define skills, service territories, and preferences for each worker, and feed this information to the scheduling system customized for every service provider.
More importantly such use of rules-based machine learning empowered their product by supporting:
- Minimal initial product configuration for every new customer
- Learning rules are defined and easily adjusted by subject matter experts
- Ever learning cycle as the actual work assignments keep changing.
You may find more information about this use case here.