Auto-Generated Decision Models
Rule Learner™ is a Machine Learning (ML) component of OpenRules Decision Intelligence platform. Its main goal is to assist business analysts in building decision models by automatically discovering major decisioning components like glossaries, business rules, and test cases.
Watch Video “Learning Decision Models from Examples“
Rule Learner was initially developed in 2007 to combine the power of Rule Engine and Machine Learning. Rule Learner utilizes proven ML algorithms for the extraction of patterns from large collections of historical data to present them in the form of readable and executable business rules. Over the years it was successfully applied to real-world projects for automatic discovery of business rules from historical data.
The latest release of Rule Learner allows subject matter experts to quickly convert business problem examples into an executable decision model and continue to enhance it using the core OpenRules decision modeling tools. A top-level diagram above show how Rule Learner can “Learn from Examples“. At the start of a decisioning project, subject matter experts provide samples of their business problem with various input parameters and expected output. Problem samples can be provided in CSV, Excel, or JSON format. Using only these samples, Rule Learner will quickly generate a working Decision Model in OpenRules format including:
- Business Glossary with decision variables, their technical attributes, types, and possible values
- Business Rules that can be understood by subject matter experts and executed by a rule engine:
- GeneratedRulesTest.xls – corresponding to the samples
- GeneratedRulesRipper.xls – generated by ML algorithm RIPPER
- GeneratedRulesC45.xls – generated by ML algorithm C4.5
- All generated rules are accompanied by their measures of accuracy
- Test Cases in JSON and Excel formats
- Configuration Files for the Decision Model testing, enhancing, and execution.
The generated decision models are ready to be tested using the standard OpenRules rule engine. Subject mater experts can analyze the generated decision models using Graphical IDE with automatically build Decision Diagrams, execute them under control of graphical Debugger, and enhance them based on their understanding of the business logic.
Rule Learner includes training capabilities. It enables a subject matter expert to define business rules for filtering the provided samples to exclude outliers and/or generate different decision models that concentrate on selected issues within large sets of historical data. This provides users with greater control over the generated decision model, ensuring the accuracy and relevance of the business logic.
Rule Learner is a stand-alone component of OpenRules Decision Intelligence Platform. You may install it for free and analyze various examples of the automatically generated decision model by looking the installed folder “openrules.learner“.
Rule Learner is also available on the cloud without any downloads. Read about “Rule Learner on Cloud” or just click on the button “Saas Rule Learner” on the right and start generating business rules using the provided or your own problem samples.
Decision Intelligence Platform 