Tuesday, June 19 | 3:35-4:50 PM
Recommended Prerequisite: Knowledge of analytics (general knowledge or applied)
Field of Study: Auditing
This session will explore how Elder Research data scientists applied machine learning techniques and graph database technology at numerous federal agencies including the Internal Revenue Service (IRS) to identify networks of tax preparers working together based on information appearing on tax returns. By applying these techniques, investigators and analysts dramatically reduced the time required to identify the most egregious and suspicious actors in a network while also creating a force multiplier for efficient targeting of due diligence treatment resources.
You Will Learn How To:
Managing Director, Fraud and Risk Analytics Practice Lead, Elder Research Inc.
Robert Han is managing director at Elder Research. He oversees Elder Research's Washington, D.C. office and its Fraud and Risk Analytics practice. At Elder Research, he has led advanced data science teams that have tackled some of the most challenging fraud and risk analytics problems in both the federal government and private sector. Some examples include applying machine learning techniques to identify and prioritize highly suspicious actors (financial market players, medical providers, unemployment insurance recipients and workers compensation beneficiaries) for investigators and analysts; building text mining models that ingest large amounts of documents to build risk profiles from unstructured text; and leveraging network analysis and graph modeling techniques to detect highly suspicious social network behaviors and potential collusion between highly connected actors amidst the opioid crisis.
Thanks for signing up!