AI Explainability 360 - Demo
Data: FICO Explainable Machine Learning Challenge
Machine learning models are used to support an increasing number of important decisions. These decisions are consumed by various users, who may have different needs and require different kinds of explanations. For this reason, AI Explainability 360 offers a collection of algorithms that provide diverse ways of explaining decisions generated by machine learning models.
To explore these different types of algorithmic explanations, we consider an AI-powered credit approval system using the FICO Explainable Machine Learning Challenge dataset and probe into it from the perspective of different users. We illustrate how different users – a data scientist, a loan officer, and a bank consumer – require different explanations.
FICO, a credit scoring company, released an anonymized dataset of Home Equity Line of Credit (HELOC) applications made by real homeowners. A HELOC is a line of credit typically offered by a bank as a percentage of home equity (the difference between the current market value of a home and the outstanding balance of all liens, e.g., mortgages). The customers in this dataset have requested a credit line in the range of $5,000 - $150,000. The fundamental task is to use the information about the applicant in their credit report to predict whether they will make timely payments over a two-year period. This is the machine learning task that we focus on. The machine learning prediction is then used by loan officers to decide whether the homeowner qualifies for a line of credit and, if so, how much credit should be extended. Learn more about the dataset.
Next, choose between a data scientist, loan officer, and bank consumer to explore which AI Explainability 360 algorithms are best suited for their needs.