OpenRules, Inc. was among the first rule engine vendors who introduced the integrated Machine Learning and Business Rules approach. Rule Learner as a component of OpenRules open source BRMS was available since 2007 and was successfully applied to several real-world projects. Over the years, it was used to discover business rules by analyzing large datasets of historical data in different problem domains. Here are a few examples:
- Discovering “red-flag” rules based on successful and unsuccessful tax return audits
- Discovering and adjusting service profiles of field engineers including services territories and skills based on the actual services history
- Recommend the best flash-sale prices based on historical sales.
Applying Rule Learner to IRS Historical Data
In 2007 OpenRules applied its Rule Learner, a machine-learning component of its popular open source business rules management system, to the Internal Revenue Service (IRS) National Research Program data provided by NHQ Research. As a result, the Rule Learner was able to successfully generate business rules that model the issue selection domain. OpenRules applied different ML algorithms to a large volume of historical data and generated the learned rules in a form automatically executable by the OpenRules engine. The achieved classification results are comparable to or better than results previously achieved by manual tax return selection. The resulting approach demonstrated a generic, yet fully automated integration of the learned rules into a Business Rules Management System. Read the Press Release.
In 2008 IRS awarded OpenRules, Inc. another contract, “Integrating Machine Learning Models With Business Rules Environment”, with the objective of integrating machine learning results into a standard business rules environment in a way that allows IRS subject matter experts to easily identify any gaps between the rules developed by its experts to detect potential non-compliance, and the rules automatically developed by the machine learning system. Read Press Release.
During 2009-2012 OpenRules successfully completed two more IRS contracts related to the integrated use of machine learning and business rules technologies: “Integrating Machine Learning Models With Business Rules Environment” and “Machine Learning Models Research and Development with NRP and LMSB Data”.
The IRS Performance Report stated: “IRS Management was satisfied with the services being performed by the Contractor and its staff members. No complaints about the key personnel working under this order. The overall performance of Dr. Jacob Feldman and staff on behalf of The OpenRules, Inc., was very good. This company would be highly recommended to work for the Internal Revenue Service in the future in regards to Machine Learning (ML) Models Performance in IRS Enforcement Programs.”