Machine Learning in Financial Services Conference

Event Information

Share this event

Date and Time

Location

Location

Clayton Hall

100 David Hollowell Drive

Newark, DE 19716

View Map

Event description

Description


Machine Learning in Financial Services

Sponsored by the Institute for Financial Services Analytics

Friday, November 8, 2019

Itinerary

8:00 AM Registration/Continental Breakfast

8:30 AM Welcome Remarks

8:45 AM Featured Speaker - Prashant Dhingra, ML Solutions, JPMorgan Chase - "Overcome ML Challenges in Enterprise: Lessons Learned from Hundreds of ML Projects"

9:45 AM Featured Speaker - Dr. Stefania Albanesi, University of Pittsburgh - "Predicting Consumer Default: A Deep Learning Approach"

10:45 AM Morning Break

11:00 AM Featured Speaker - Sarah Davies, Nova Credit - "Capturing the Value of Machine Learning in Credit Risk Score Development"

11:45 AM Featured Speaker - Sanchit Arora, Possible Finance - "Machine Learning for the Underbanked: Using Machine Learning to Help Americans Improve Their Financial Well-Being"

12:30 PM Networking Lunch & Poster Session

2:00 PM John Cavazos Student Research Presentation Session - PhD Students from the Financial Services Analytics PhD program

3:00 PM Student Presentation Feedback and Discussion Session - Featured Speakers and IFSA Faculty

3:30 PM Networking/Poster Session (light refreshments will be served)

Complimentary parking is available in the upper parking lot (7S).

Predicting Consumer Default: A Deep Learning Approach

Stefania Albanesi, Professor of Economics, University of Pittsburgh

In this research, we develop a model to predict consumer default based on deep learning. We show that the model consistently outperforms standard credit scoring models, even though it uses the same data. Our model is interpretable and is able to provide a score to a larger class of borrowers relative to standard credit scoring models while accurately tracking variations in systemic risk. We argue that these properties can provide valuable insights for the design of policies targeted at reducing consumer default and alleviating its burden on borrowers and lenders, as well as macroprudential regulation.

Stefania Albanesi is Professor of Economics at the University of Pittsburgh, a Research Associate at the NBER and a CEPR Research Fellow. She is a macroeconomist whose research interests include the determinants and implications of various dimensions of inequality and the distributional implications of government policies. Prior to her appointment to the University of Pittsburgh, she was a professor at Bocconi University, Duke University, Columbia University and a Research Officer at the Federal Reserve Bank of New York. She also held visiting positions at NYU-Stern, the University of Pennsylvania, Ohio State University and Princeton University, and was a national fellow at the Hoover Institution.

She has studied the political economy of inflation, the optimal taxation of capital and labor income, and the evolution of gender disparities in labor market outcomes. Her current research concerns the distribution of debt and defaults in the lead up and during the 2007-09 financial crisis and the determinants and consequences of personal bankruptcy. She is also working on the impact of changing trends in female participation on aggregate business cycles and on using machine learning to develop accurate and interpretable models of consumer default. Professor Albanesi completed her PhD in economics at Northwestern University and has a bachelor's degree in economics from Bocconi University.


Machine Learning for the Underbanked: Using Machine Learning to help Americans Improve their Financial Well-Being

Sanchit Arora, Head of Machine Learning & Data Science, Possible Finance


Sanchit Arora is the Head of ML and Data Science at Possible Finance. After completing his Master's in Robotics and Machine Learning at UPenn, Sanchit co-founded machine learning firm Dextro, which was acquired by TASER maker Axon in 2017. With experience building machine learning systems for robots, video analytics, law enforcement systems and now financial products, Sanchit believes in the potential for Machine Learning to aid in solving hard problems at scale and automating processes while maintaining fairness and transparency.



Capturing the Value of Machine Learning in Credit Risk Score Development

Sarah F. Davies, Credit Risk & Analytics - Nova Credit

Ms. Davies leads credit risk and analytics for Nova Credit. She has over 20 years experience in the financial services sector, serving as an executive leader and innovator in the analytics and decision science field. Prior to joining Nova Credit, she was Senior Vice President of Product, Analytics and Research at VantageScore Solutions, where she led the development of the VantageScore credit scoring models. She has also served as a Principal at American Airlines Decision Technologies. Additionally, she has authored numerous whitepapers and research insights on consumer credit behavioral analysis. She holds several patents in both the credit analytics and airline optimization fields and is a frequent speaker and educator on credit risk and consumer behavioral analytics.Sarah holds a Bachelor of Science in Management Science and Operations Research, a Masters degree in Industrial Engineering with a concentration in Operations Research and Statistics and a Masters degree in Theological Studies.

Overcome ML Challenges in Enterprise: Lessons Learned from Hundreds of ML Projects

Prashant K. Dhingra, ML Solutions, JPMorgan Chase

Prashant has 26 years of experience, including 11 years of machine learning experience. At present Prashant heads development of ML solutions at JP Morgan Chase. Prior to this Prashant was head of ML for Manufacturing at Google. He led the development of machine learning models for smart factories and has worked with multiple enterprise customers to build machine learning solution on Google Cloud. At Google he defined AI vision for Industry 4.0

Before this Prashant also worked at Microsoft in Azure Machine Learning, Bing Research and SQL Server Product.

Prashant also built ML Model to predict water flow in rivers and led flood prediction initiative for USA. He wrote a chapter in NOAA Machine Learning book and authored SQL Server book too.

Dress: Business Casual

Date and Time

Location

Clayton Hall

100 David Hollowell Drive

Newark, DE 19716

View Map

Save This Event

Event Saved