Integrating induction and deduction for finding evidence of discrimination

ABSTRACT

Automatic Decision Support Systems (DSS) are widely adopted for screening purposes in socially sensitive tasks, including access to credit, mortgage, insurance, labor market and other benefits. While less arbitrary decisions can potentially be guaranteed, automatic DSS can still be discriminating in the socially negative sense of resulting in unfair or unequal treatment of people. We present a reference model for finding (prima facie) evidence of discrimination in automatic DSS which is driven by a few key legal concepts. First, frequent classification rules are extracted from the set of decisions taken by the DSS over an input pool dataset. Key legal concepts are then used to drive the analysis of the set of classification rules, with the aim of discovering patterns of discrimination. We present an implementation, called LP2DD, of the overall reference model integrating induction, through data mining classification rule extraction, and deduction, through a computational logic implementation of the analytical tools.

REFERENCES

• 1: O. Ashenfelter and R. Oaxaca. The economics of discrimination: Economists enter the courtroom. The American Economic Review, 77: 321--325, 1987.
• 2: Australian Legislation. (a) Equal Opportunity Act -- Victoria State, (b) Anti-Discrimination Act - Queensland State. http://www.austlii.edu.au.
• 3: B. Baesens, T. V. Gestel, S. Viaene, M. Stepanova, J. Suykens, and J. Vanthienen. Benchmarking state-of-the-art classification algorithms for credit scoring. J. of the Operational Research Society, 54(6): 627--635, 2003.
• 4: M. Bell, I. Chopin, and F. Palmer. Developing Anti-Discrimination Law in Europe. 2007. http://ec.europa.eu/employment_social/funda-mental_rights.
• 5: P. S. Calem, K. Gillen, and S. Wachter. The neighborhood distribution of subprime mortgage lending. J. of Real Estate Finance and Economics, 29: 393--410, 2004.
• 6: Chen-Fu Chien , Li-Fei Chen, Data mining to improve personnel selection and enhance human capital: A case study in high-technology industry, Expert Systems with Applications: An International Journal, v.34 n.1, p.280-290, January, 2008 [doi>10.1016/j.eswa.2006.09.003]
• 7: E. Ellis. EU Anti-Discrimination Law. Oxford University Press, 2005.
• 8: European Union Legislation. (a) Racial Equality Directive, (b) Employment Equality Directive. http://ec.europa.-eu/employment_social/fundamental_rights.
• 9: J. L. Gastwirth. Statistical reasoning in the legal setting. The American Statistician, 46(1): 55--69, 1992.
• 10: D. J. Hand and W. E. Henley. Statistical classification methods in consumer credit scoring: a review. J. of the Royal Statistical Society, Series A, 160: 523--541, 1997.
• 11: R. Hunter. Indirect Discrimination in the Workplace. The Federation Press, 1992.
• 12: Benjamin Johnston , Guido Governatori, Induction of defeasible logic theories in the legal domain, Proceedings of the 9th international conference on Artificial intelligence and law, June 24-28, 2003, Scotland, United Kingdom [doi>10.1145/1047788.1047834]
• 13: F. Kamiran and T. Calders. Classification without discrimination. In IEEE Int.'l Conf. on Computer, Control&Communication (IEEE-IC4). IEEE press, 2009.
• 14: R. Knopff. On proving discrimination: Statistical methods and unfolding policy logics. Canadian Public Policy, 12: 573--583, 1986.
• 15: P. Kuhn. Sex discrimination in labor markets: The role of statistical evidence. The American Economic Review, 77: 567--583, 1987.
• 16: M. LaCour-Little. Discrimination in mortgage lending: A critical review of the literature. J. of Real Estate Literature, 7: 15--49, 1999.
• 17: N. Lerner. Group Rights and Discrimination in International Law. Martinus Nijhoff Publishers, 1991.
• 18: T. Makkonen. Measuring Discrimination: Data Collection and the EU Equality Law. 2006. http://ec.europa.eu/-employment_social/fundamental_rights.
• 19: Dino Pedreshi , Salvatore Ruggieri , Franco Turini, Discrimination-aware data mining, Proceeding of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining, August 24-27, 2008, Las Vegas, Nevada, USA [doi>10.1145/1401890.1401959]
• 20: Henry Prakken , Giovanni Sartor, The Role of Logic in Computational Models of Legal Argument: A Critical Survey, Computational Logic: Logic Programming and Beyond, Essays in Honour of Robert A. Kowalski, Part II, p.342-381, January 2002
• 21: P. A. Riach and J. Rich. Field experiments of discrimination in the market place. The Economic Journal, 112: 480--518, 2002.
• 22: T. Sowell, editor. Affirmative Action Around the World: An Empirical Analysis. Yale University Press, 2005.
• 23: G. D. Squires. Racial profiling, insurance style: Insurance redlining and the uneven development of metropolitan areas. J. of Urban Affairs, 25(4): 391--410, 2003.
• 24: L. Sterling and E. Shapiro. The Art of Prolog. The MIT Press, 1986.
• 25: Andrew Stranieri , John Zeleznikow, The evaluation of legal knowledge based systems, Proceedings of the 7th international conference on Artificial intelligence and law, p.18-24, June 14-17, 1999, Oslo, Norway [doi>10.1145/323706.323711]
• 26: Pang-Ning Tan , Michael Steinbach , Vipin Kumar, Introduction to Data Mining, (First Edition), Addison-Wesley Longman Publishing Co., Inc., Boston, MA, 2005
• 27: L. C. Thomas. A survey of credit and behavioural scoring: forecasting financial risk of lending to consumers. Int. J. of Forecasting, 16: 149--172, 2000.
• 28: U.K. Legislation. (a) Sex Discrimination Act, (b) Race Relation Act. http://www.statutelaw.gov.uk.
• 29: United Nations Legislation. (a) Convention on the Elimination of All forms of Racial Discrimination, (b) Convention on the Elimination of All forms of Discrimination Against Women. http://www.ohchr.org.
• 30: U.S. Federal Legislation. (a) Equal Credit Opportunity Act, (b) Fair Housing Act, (c) Intentional Employment Discrimination, (d) Equal Pay Act, (e) Pregnancy Discrimination Act. http://www.usdoj.gov.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.2 DATABASE MANAGEMENT
      H.2.8 Database applications

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.3 Deduction and Theorem Proving

General Terms:
Algorithms, Design, Legal Aspects

Keywords:
classification, data mining, direct and systematic discrimination, logic programming, scoring systems