A Controlled Natural Language for Tax Fraud Detection

Addressing tax fraud has been taken increasingly seriously, but most attempts to uncover it involve the use of human fraud experts to identify and audit suspicious cases. To identify such cases, they come up with patterns which an IT team then implements to extract matching instances. The process, starting from the communication of the patterns to the developers, the debugging of the implemented code, and the refining of the rules, results in a lengthy and error-prone iterative methodology. In this paper, we present a framework where the fraud expert is empowered to independently design tax fraud patterns through a controlled natural language implemented in GF, enabling immediate feedback reported back to the fraud expert. This allows multiple refinements of the rules until optimised, all within a timely manner. The approach has been evaluated by a number of fraud experts working with the Maltese Inland Revenue Department.

[1]  Robert P. W. Duin,et al.  Data domain description using support vectors , 1999, ESANN.

[2]  Tobias Kuhn,et al.  A Survey and Classification of Controlled Natural Languages , 2014, CL.

[3]  Gordon J. Pace,et al.  A Controlled Natural Language for Business Intelligence Monitoring , 2015, NLDB.

[4]  Aarne Ranta,et al.  Implementing Controlled Languages in GF , 2009, CNL.

[5]  Simon L. Peyton Jones,et al.  Composing contracts: an adventure in financial engineering (functional pearl) , 2000, ICFP '00.

[6]  Anna Freud,et al.  Grammatical Framework Programming With Multilingual Grammars , 2016 .

[7]  Aarne Ranta,et al.  Multilingual grammar for museum object descriptions , 2011 .

[8]  Aarne Ranta,et al.  Controlled Language for Everyday Use: The MOLTO Phrasebook , 2010, CNL.

[9]  Gordon J. Pace,et al.  Safe Runtime Verification of Real-Time Properties , 2009, FORMATS.

[10]  Divya Murli,et al.  Credit Card Fraud Detection Using Neural Networks , 2015 .

[11]  Gordon J. Pace,et al.  Fast-Forward Runtime Monitoring - An Industrial Case Study , 2012, RV.

[12]  Martin Leucker,et al.  A brief account of runtime verification , 2009, J. Log. Algebraic Methods Program..

[13]  Gordon J. Pace,et al.  A Domain Specific Property Language For Fraud Detection To Support Agile Specification Development , 2014 .

[14]  Gordon J. Pace,et al.  Offline Runtime Verification with Real-Time Properties: A Ca se Study , 2009 .

[15]  Gordon J. Pace,et al.  LARVA --- Safer Monitoring of Real-Time Java Programs (Tool Paper) , 2009, 2009 Seventh IEEE International Conference on Software Engineering and Formal Methods.

[16]  Richard Power,et al.  What You See Is What You Meant: direct knowledge editing with natural language feedback , 1998, ECAI.