FACT SHEET NY State Dept. of Taxation & Finance Competing for INFORMS Edelman Prize


Ashley Smith
Public Affairs Coordinator

HANOVER, MD, March 21, 2011 – The New York State Department of Taxation and Finance’s analytics team is among six finalists that will compete for the INFORMS 2011 Franz Edelman Award for Achievement in Operations Research and the Management Sciences in Chicago on April 11 at the Marriott Chicago Downtown.

The finalists for the competition, sponsored by the Institute for Operations Research and the Management Sciences (INFORMS®), include:

New York State Department of Taxation and Finance with IBM for “Tax Collection Optimization for the State of New York.”

The state of New York collects over $1 billion annually in assessed delinquent taxes. Recent economic conditions, including the need to reduce growing state deficits, require that every dollar that can be collected is collected---and in the most efficient way possible. The Tax Collections Division is being asked by the governor to increase collections to reduce the budget deficit, but to do so in a manner that respects the rights of citizens by taking actions commensurate with the individual situations of each debtor. This needs to be accomplished within an environment that also includes limited resources that, if anything, will become more limited in the future.

The debt collection process is highly complex, with a large number of legal and business constraints involved. Because of this complexity, it is common practice to follow rigid, manually constructed rules to guide the collection activities. Even in state-of-the-art rule-based systems for collections, the role of data analytics is typically limited to augmenting the rule engine with scores given by analytics. Manually constructed rules are not adaptive to changes in the environment, and hence the need for a more adaptive approach has been recognized.

In collaborative work between the New York State Department of Taxation and Finance and IBM’s Research and Global Business Services divisions, a novel tax collections optimization solution was developed to address this challenge. The solution is a unique combination of data analytics and optimization based on the unifying framework of constrained Markov decision processes (C-MDP). It optimizes the collection actions of agents with respect to maximization of long-term returns while taking into account the complex dependencies between business needs, resources, and legal constraints.

The C-MDP system became operational in December 2009, and the results to date are compelling.

New York State has seen an $83 million increase in revenue from 2009 to 2010 (8%), using the same set of resources. In addition, the department has increased the productivity from primary enforcement actions with, for example, a 22% increase in the dollars collected per warrant and an 11% increase in the dollars collected per levy. (A warrant is effectively a “tax lien,” and a levy compels financial institutions to turn over debtors’ assets.) Additional good news is that the department has seen a 10% decrease in age of case when it is assigned to a field office. (Older cases tend to have lower probability of collection.) Given a typical annual increase of 2%-4%, the expected benefit of the developed system is approximately $120-150 million over the next three years, far exceeding the initial target of $99 million, and is expected to improve still more in the future as the system further adapts.

The developed system possesses a number of notable characteristics. First, via the tight coupling of data analytics and optimization in the C-MDP framework, it realizes a level of automation that has never been achieved before. With the optimization process being guided by data analytics, the resulting collection policy is adaptive to various changes in the environment.

Another advantage is its ability to optimize the collection rules with respect to long-term return, which is critical in this domain because not all collections actions (for example warrants as prerequisites to levy) enjoy immediate rewards. Indeed, this aspect is key in freeing the department from reliance on manual sequential workflow rules, which to date has hindered automation of collections processes. Although the sequential dependencies between various collection stages are automatically discovered, the system also accepts hard constraints expressed as rules for use in its optimization process.

Hence, the system brings together three principal elements of operations research---analytics, optimization, and rules---in a novel, coherent, and effective manner, and simultaneously attains their corresponding benefits of adaptability, optimality, and practicality.

The New York State Department of Taxation and Finance is responsible for two major functions: the administration of the state’s tax laws, including the administration of related local taxes, and the management of the State Treasury. In the fiscal year ending March 31, 2010, the department collected over $55 billion in state revenue and nearly $36 billion on behalf of localities.

International Business Machines Corporation is a global technology and innovation company headquartered in Armonk, New York. IBM is the largest technology employer in the world, with more than 400,000 employees serving clients in 170 countries.

The six 2011 Franz Edelman finalists are:

  1. CSAV
  2. Fluor Corporation
  3. The Industrial and Commercial Bank of China Limited (ICBC)
  4. IHG (InterContinental Hotels Group)
  5. Midwest Independent Transmission System Operator
  6. New York State Department of Taxation and Finance

 This is the 40th year of the prestigious Franz Edelman competition. The winner will be announced at a special awards banquet on April 11, 2011 during the INFORMS Conference on Business Analytics & Operations Research. The conference takes place at the Marriott Chicago Downtown from April 10-12.


The Institute for Operations Research and the Management Sciences (INFORMS®) is an international scientific society with 10,000 members, including Nobel Prize laureates, dedicated to applying scientific methods to help improve decision-making, management, and operations. Members of INFORMS work in business, government, and academia. They are represented in fields as diverse as airlines, health care, law enforcement, the military, financial engineering, and telecommunications. INFORMS serves the scientific and professional needs of operations research analysts, experts in analytics, consultants, scientists, students, educators, and managers, as well as their institutions, by publishing a variety of journals that describe the latest research in operations research. INFORMS Online (IOL) is at www.informs.org. Further information about operations research can be found at www.scienceofbetter.org.