2011 Edelman Finalist Tax Collection Optimization for the State of New York

2011 Edelman Finalist The State of New York

Abstract: The New York State Department of Taxation and Finance (NYS DTF) collects over $1 billion annually in assessed delinquent taxes. A novel solution was developed to address the challenge of optimizing tax collection activities, in the presence of complex dependencies between business needs, resources and legal constraints. The solution is a unique combination of data analytics and optimization based on the unifying framework of constrained Markov Decision Processes (C-MDP). The developed system optimizes the collection actions of agents with respect to maximization of long term returns, and generates a customized collections policy that is efficient and adaptive. The system became operational in December 2009, and there has already been an $83M increase in revenue from 2009 to 2010 (8%), using the same set of resources. Given a typical annual increase of 2-4%, the expected benefit of the developed system is approximately $120M to $150M over the next three years, far exceeding the initial target of $99 million.

C.I.S.S. = Case Identification and Selection System