SolasAI: Improving Model Fairness by Reducing Algorithmic Discrimination

Nicholas Schmidt, CEO & Larry Bradley, COO
As enterprises, especially financial institutions, lenders, and insurers, increasingly adopt artificial intelligence (AI) and machine learning (ML) models for unlocking potential business opportunities, they recognize the need to monitor and review these models to ensure fairness and compliance with regulatory standards. However, companies often struggle to understand what is expected by regulators, what should be done to make an algorithm fair, how to measure fairness, and what constitutes an efficient and effective process for fixing any issues that may be found. Failure to evaluate and justify model fairness can expose them to regulatory, legal, and reputational risks.

This is where SolasAI comes into the picture.

Combining explainable AI and deep industry expertise, SolasAI offers a platform to detect discrimination in models, improve fairness, and drive innovation. SolasAI’s cutting-edge technology is at the forefront of responsible AI and incorporates the most recent developments in machine learning.
By identifying opportunities to minimize disparities, the SolasAI platform generates viable alternative models with less disparity while maintaining the overall model quality. This enables modelers and compliance stakeholders to review, analyze, and make informed decisions on models’ fairness efficiently and transparently.

“We combine advanced data science with our experts’ extensive experience and knowledge of algorithmic fairness, responsible AI, explainable AI, and fair lending to build our software. We enable customers to effectively resolve problematic issues related to algorithmic fairness in-house, which significantly lowers costs,” says Nicholas Schmidt, CEO of SolasAI.

"customers' legal, compliance, and data science teams appreciate our ability to supplement their tools rather than replace them"

Resolving Potential Discrimination

SolasAI begins the first step to fairer model reconstruction by enabling users to feed the details of the developed models to the platform to look for evidence of unfairness and discrimination. If there are no issues, they can verify the models and produce the necessary documentation.

If there is a problem, SolasAI uses explainable AI to figure out how individual pieces of data, variables, or features that constitute a model drive the predictive quality, as well as potential discrimination. This information gives users a direction to follow to resolve the discrimination problems while maintaining the model’s predictive value and business-driven quality.

Following this, SolasAI identifies the least discriminatory and the highest quality algorithm, leveraging optimized search methodology. Once the best models are selected, the AI learns to iteratively improve itself and make the algorithms fairer and of better quality. Through this process, users can continually enhance their models over time.
In the next step, the SolasAI software provides relevant information about the models that can be reviewed by the customers and stakeholders, business owners, modelers, and compliance groups to make informed decisions. They can check whether a model is innovative enough to meet their business needs or presents any issues that need rectifying. This provides customers with a choice either to proceed with the SolasAI-generated model or to use their original model. The company's software also produces documentation of the work done to make the model fairer.

Bridging the Gaps in Existing Models

SolasAI’s design choices perfectly fit customers' modeling and production processes, allowing customers to bridge the existing gaps and mitigate problems without disruption while continuing to innovate and grow their business. While, due to the sensitive nature of data, certain companies prefer their compliance analysts to check the fairness of models utilizing SolasAI, others encourage their data scientists to use the platform to complement their existing tools and create fairness earlier in the process.

“Customers’ legal, compliance, and data science teams appreciate our ability to supplement their tools rather than replace them,” says Larry Bradley, COO, SolasAI.

In one instance, a customer from the healthcare industry was struggling to address the queries they were receiving from various regulators about their algorithms’ potential to cause or exacerbate bias. Their data scientists weren’t prepared to answer the regulators’ questions and proceed further. The customer approached SolasAI to help them identify potential bias in their models, especially those at the highest risk. With SolasAI, the company discerned that one of the models for a vulnerable population provided fewer favorable outcomes for women than men. SolasAI was able to bridge this gap without causing any predictive deterioration in the model, allowing the customer to create effective outreach for both women and men.

We combine advanced data science with our experts’ experience in algorithmic fairness, responsible AI, and explainable AI to build our software

SolasAI’s ability to drive the success of its customers stems from an incredible team comprising industryleading consultants and data scientists who are pragmatic problem solvers. They regularly interact with regulatory bodies to stay abreast of the latest and upcoming regulations and incorporate the insights in the SolasAI software.

In addition to facilitating fair models, SolasAI continually helps customers work in industries that deal with strict regulatory oversight and the potential for costly lawsuits, as well as those in industries that are experiencing a changing legislative environment, where increased legal, reputational, and regulatory scrutiny is forcing innovative companies to address questions of model fairness and discrimination. Also, as institutional investors pivot their focus on environmental, social, and corporate governance (ESG), the company supports customers with social and governance aspects to ensure clean social scorecards in their portfolio.


Philadelphia, PA

Nicholas Schmidt, CEO & Larry Bradley, COO

SolasAI offers a platform to illuminate and reduce the causes of disparities in predictive models. The platform is designed to help enterprises easily detect discrimination in their models and clarify trade-offs between business value and reducing inequalities.