Faculty Advisor

Balistrieri, Thomas J.

Faculty Advisor

Pavlov, Oleg V

Center

Russia

Abstract

The Central Bank of Russia has revoked 20% of all bank licenses since 2012. This project sought to determine a computational method for forecasting the probability of license revocation. To do this, we compared two classification algorithms, logistic regression and random forest. Using a Random Forest classifier produced higher F1 scores than logistic regression. We recommend that Deloitte continues the development of a random forest model by investigating clustering and additional features to improve the model’s performance.

Publisher

Worcester Polytechnic Institute

Date Accepted

October 2016

Project Type

Interactive Qualifying Project

Accessibility

Unrestricted

Advisor Department

Social Science and Policy Studies

Project Center

Russia

Share

COinS