AI

Making Monitoring AI Bias a Little Easier

Share this post:

When we launched Watson OpenScale late last year we turned a lot of heads. With this one solution, we introduced the idea of giving business users and non-data scientists the ability to monitor their AI and machine learning models to better understand performance, help detect and mitigate algorithmic bias, and to get explanations for AI outputs. But we’re just getting started.

Since then we’ve continued to work on and advance OpenScale to help organizations ensure fair outcomes from their AI models in production. Starting today, we are making it easier to detect and mitigate bias against protected attributes like sex and ethnicity with Watson OpenScale through recommended bias monitors.

Up till now, users manually selected which features or attributes of a model to monitor for bias in production, based on their own knowledge. With the new recommended bias monitors, Watson OpenScale will now automatically identify whether known protected attributes, including sex, ethnicity, marital status, and age, are present in a model and recommend they be monitored. Such functionality will help users avoid missing these attributes and ensure that bias against them is tracked in production.

In addition, we are working with the regulatory compliance experts at Promontory to continue expanding this list of attributes to cover the sensitive demographic attributes most commonly referenced in data regulation.

In addition to detecting protected attributes, Watson OpenScale will recommend which values within each attribute should be set as the monitored and the reference values—recommending, for example, that within the “Sex” attribute, the bias monitor be configured such that “Female” and “Non-Binary” are the monitored values, and “Male” is the reference value. If you want to change any of Watson OpenScale’s recommendations, you can easily edit them via the bias configuration panel.

Recommended bias monitors help to speed up configuration and ensure that you are checking your AI models for fairness against sensitive attributes. As regulators begin to turn a sharper eye on algorithmic bias, it is becoming more critical that organizations have a clear understanding of how their models are performing, and whether they are producing unfair outcomes for certain groups. Learn more about how Watson OpenScale can help by trying our Lite Plan on IBM Cloud for free.

If you are interested in becoming a sponsor user of Watson OpenScale, to provide feedback and help us determine the future direction of this product, please let us know.

Offering Manager, IBM Watson OpenScale

More AI stories

How AI, IoT and Weather Tech Can Help Better Detect Deadly Wildfires

As summer temperatures in the northern hemisphere rise, so too does the risk of wildfires and the threat to life and property from the western U.S., to Europe and across Siberia. In fact, firefighting teams are working to contain wildfires across central Portugal as I write. Unfortunately, this trend shows no signs of slowing. According […]

Continue reading

FOX Sports, IBM Team Up to Transform Production

The eighth edition of the FIFA Women’s World Cup™ is well underway, with teams from 12 countries battling it out for the championship title. While millions of soccer fans stay tuned to the excitement in France, IBM is teaming up with FOX Sports to help transform production of the event by infusing AI analysis and […]

Continue reading