Using Human-Centered AI to Fight Fraud, Waste, and Abuse by CMS Open Data

When the industry talked about AI in the past few years, we focused a lot on Machine Learning. However, just like in our school system, “Learning” is only half of the equation - the other half is Teaching. And we are missing Machine Teaching which is where the Human-centered portion comes in. In 2020, Linux Foundation ODPi has done some researches with different industry leaders and vendors to explore this technical topic. This session will reveal the findings and intersect this technical discussion with a real business context: Fraud, Waste and Abuse.
In order for a business to thrive, besides finding ways to increase the income, cutting down expanses is also important. In some industries like Insurance, Financial and Healthcare, “Fraud, Waste and Abuse (FWA)” are considered one of the top expenses that cost companies billions of dollars. Traditionally, this is handled by a group of expert and investigator to identify potential fraudulent cases, which is a time-consuming and labor-intensive process. With the rise of AI, there are more options to assist human to identify and prevent it from harming our community. 
This session will show not only “why” we should use AI to fight against FWA, but also “how” it can be achieved practically with 3 main steps:

1. Supervised Learning: Explore how basic algorithms like decision trees, logistic regression and support vector machines can help in FWA and the corresponding results
2. Unsupervised Learning: See how techniques like clustering can complement and improve results.
3. Leveraging the latest finding of Generative Adversarial Network (GAN): Investigate the use of GAN, employed on image generation, on FWA, and see how this more sophisticated model can help fight FWA.

The session demonstrates by utilizing open data set, which is available online. We will also include latest researches in this area to strength the cases presenting here.