KuppingerCole's Advisory stands out due to our regular communication with vendors and key clients, providing us with in-depth insight into the issues and knowledge required to address real-world challenges.
Meet our team of analysts and advisors who are highly skilled and experienced professionals dedicated to helping you make informed decisions and achieve your goals.
Meet our business team committed to helping you achieve success. We understand that running a business can be challenging, but with the right team in your corner, anything is possible.
The harm that the misuse of AI/ML can have is obvious, from the ProPublica Recidivism piece from 2016 to the latest discovery of bias in facial recognition classifiers by Joy Buolamwini.
The need for tools to use AI/ML ethically is concentrated in two particular areas: transparency and fairness. Transparency involves knowing why an ML system came to the conclusion that it did—something that is essential if we are to identity bias. In some forms of ML, this is difficult. We’ll cover two tools to assist with transparency: LIME and SHAP. We’ll highlight where each of these tools performs well and poorly, and provide recommendations for utilizing them in unison where appropriate.
Once transparency is established, we’ll pause to evaluate potential sources of bias that would affect the fairness of a particular algorithm. Here the number of tools available is far-reaching. We’ll start with an explanation of bias metrics, explaining the roles that true/false positives and true/false negatives play in calculating various accuracy metrics. The basics of fairness established, then we will explore various tools used against a few, publicly available sample ML implementations. Tools in this review will include: Aequitas, AIF360, Audit-AI, FairML, Fairness Comparison, Fairness Measures, FairTest, Themis™, and Themis-ML. We’ll compare these tools, providing recommendations on their usage and profiling their strengths and weaknesses.
The harm that the misuse of AI/ML can have is obvious, from the ProPublica Recidivism piece from 2016 to the latest discovery of bias in facial recognition classifiers by Joy Buolamwini.
The need for tools to use AI/ML ethically is concentrated in two particular areas: transparency and fairness. Transparency involves knowing why an ML system came to the conclusion that it did—something that is essential if we are to identity bias. In some forms of ML, this is difficult. We’ll cover two tools to assist with transparency: LIME and SHAP. We’ll highlight where each of these tools performs well and poorly, and provide recommendations for utilizing them in unison where appropriate.
Once transparency is established, we’ll pause to evaluate potential sources of bias that would affect the fairness of a particular algorithm. Here the number of tools available is far-reaching. We’ll start with an explanation of bias metrics, explaining the roles that true/false positives and true/false negatives play in calculating various accuracy metrics. The basics of fairness established, then we will explore various tools used against a few, publicly available sample ML implementations. Tools in this review will include: Aequitas, AIF360, Audit-AI, FairML, Fairness Comparison, Fairness Measures, FairTest, Themis™, and Themis-ML. We’ll compare these tools, providing recommendations on their usage and profiling their strengths and weaknesses.