InRule Technology® Enhances Machine Learning Platform with Bias Detection to Reduce Risk and Deliver Fairness Through Awareness

  • Updated

Published: February 3, 2022

CHICAGO – InRule Technology®, provider of AI-enabled, end-to-end automation for the enterprise, today introduced bias detection features within InRule Machine Learning, the company’s suite of machine learning modeling engines.

The bias detection features within InRule Machine Learning support organizations whose machine learning models are associated with predictions that could contain bias toward a protected class (gender, race, age, etc.) or impact an individual’s well-being, such as clinical trials, population health management, incarceration recidivism, loan origination, insurance policy rating and more.

Bias detection in InRule delivers “fairness through awareness” and minimizes risk for organizations that leverage machine learning predictions at scale within business operations. Augmenting InRule Machine Learning with bias detection allows enterprises to quantify and mitigate potential hazards when complying with federal, state and local regulations or corporate policies.

“Fairness through awareness” means an organization is empowered to evaluate their machine learning models for bias with all elements and data that are relevant to a prediction, even if those characteristics are not used to train the model itself. Conversely, “fairness through blindness” refers to selectively excluding elements and data from the modeling process.  The risk with this blind approach is that it does not account for the potential correlation of remaining data to the variable excluded. And, it gives no transparent comparison to determine if the remaining proxy characteristics led to harmful bias even with the obvious element removed.

Unlike platforms that exclusively measure whether the distribution of data has changed over time, InRule bias detection evaluates the fairness of the model, ensuring people who are similar (on the basis of reasons most relevant to make the modeled decision) receive equal treatment. Additionally, the bias detection in InRule scours to the deepest subsets of the model, exploring millions of data paths to ensure that the model operates with equal fairness within groups and between groups. In contrast, most machine learning platforms that offer bias detection only pursue bias at the model’s highest, most overarching, global level.

“Organizations leveraging machine learning need to be aware of the harmful ways that bias can creep into models, leaving them vulnerable to significant legal risk and reputational harm,” said David Jakopac, Ph.D., vice president, Engineering and Data Science, InRule Technology. “Our explainability and clustering engines provide unprecedented visibility that enables organizations to quantify and mitigate harmful bias through action in order to advance the ethical use of AI.”

In addition to reducing risk and preventing harmful algorithmic bias, the automated bias detection in InRule Machine Learning helps minimize bottlenecks in the model ops lifecycle by giving data science teams a set of automated tools to accelerate their development process, leading to faster model deployments with greater confidence.

Learn more about AI fairness and algorithmic bias detection in the on-demand webinar, Risk and Ethical AI: The Impact of Fairness Through Awareness on Bias.

#  #  #

About InRule Technology

InRule Technology provides AI-enabled, end-to-end automation for the enterprise. IT and business personnel rely on the company’s decision automation, machine learning and digital process technologies to increase productivity, grow revenue and delight customers. The InRule Decision Platform empowers both technical and business rule authors to write and manage automated decisions and business logic. InRule Machine Learning, the company’s suite of modeling engines, provides unparalleled explainability by delivering machine learning predictions with the why®. InRule Technology’s low-code digital process automation technology, brings efficiency, consistency, and transparency to processes and workflows. More than 500 InRule User Community members across 40 countries depend on InRule to reduce development and change cycles by 90 percent for their mission-critical systems and customer-facing applications. InRule Technology has been delivering measurable business and IT results in high-performance environments since 2002. For more information, visit

Follow InRule Technology on Twitter and LinkedIn.

InRule and InRule Technology are registered trademarks of InRule Technology, Inc. All other trademarks and trade names mentioned herein may be the trademarks of their respective owners and are hereby acknowledged.

Was this article helpful?

0 out of 0 found this helpful



Article is closed for comments.