An explainable attention network for fraud detection in claims management

Abstract Insurance companies must manage millions of claims per year. While most of these are not fraudulent, those that are nevertheless cost insurance companies and those they insure vast amounts of money. The ultimate goal is to develop a predictive model that can single out fraudulent claims and pay out non-fraudulent ones automatically. Health care claims have a peculiar data structure, comprising inputs of varying length and variables with a large number of categories. Both issues are challenging for traditional econometric methods. We develop a deep learning model that can handle these challenges by adapting methods from text classification. Using a large dataset from a private health insurer in Germany, we show that the model we propose outperforms a conventional machine learning model. With the rise of digitalization, unstructured data with characteristics similar to ours will become increasingly common in applied research, and methods to deal with such data will be needed.

[1]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[2]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[3]  Cheng Guo,et al.  Entity Embeddings of Categorical Variables , 2016, ArXiv.

[4]  Tao Shen,et al.  DiSAN: Directional Self-Attention Network for RNN/CNN-free Language Understanding , 2017, AAAI.

[5]  Sida I. Wang,et al.  Dropout Training as Adaptive Regularization , 2013, NIPS.

[6]  Praveen Pathak,et al.  Detecting Management Fraud in Public Companies , 2010, Manag. Sci..

[7]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[8]  Jun Zhao,et al.  Recurrent Convolutional Neural Networks for Text Classification , 2015, AAAI.

[9]  Guido Dedene,et al.  A Comparison of State-of-The-Art Classification Techniques for Expert Automobile Insurance Claim Fraud Detection , 2002 .

[10]  Sharon Tennyson,et al.  Claims Auditing in Automobile Insurance: Fraud Detection and Deterrence Objectives , 2002 .

[11]  P. Picard,et al.  Economic Analysis of Insurance Fraud , 2013 .

[12]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[13]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[14]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[15]  P. Picard,et al.  Auditing claims in the insurance market with fraud: The credibility issue , 1996 .

[16]  Joel Goh,et al.  Evidence of Upcoding in Pay-for-Performance Programs , 2015 .

[17]  Georges Dionne,et al.  Optimal Auditing with Scoring: Theory and Application to Insurance Fraud , 2009, Manag. Sci..

[18]  Michael McAleer,et al.  An alternative approach to estimating demand: neural network regression with conditional volatility for high frequency air passenger arrivals. , 2008 .

[19]  Yan Liu,et al.  Deep residual learning for image steganalysis , 2018, Multimedia Tools and Applications.

[20]  The Role of Overbilling in Hospitals’ Earnings Management Decisions , 2018 .

[21]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[22]  Jörg Schiller.  The Impact of Insurance Fraud Detection Systems , 2003 .

[23]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[24]  Eric W. Bond,et al.  Hardball and the Soft Touch: The Economics of Optimal Insurance Contracts with Costly State Verification and Endogenous Monitoring Costs , 1997 .

[25]  Victor S. Sheng,et al.  Cost-Sensitive Learning , 2009, Encyclopedia of Data Warehousing and Mining.

[26]  Ying-Chan Tang,et al.  Detecting hospital fraud and claim abuse through diabetic outpatient services , 2008, Health care management science.

[27]  Byron C. Wallace,et al.  Attention is not Explanation , 2019, NAACL.

[28]  Michael McAleer,et al.  A neural network demand system with heteroskedastic errors , 2008 .

[29]  Manaal Faruqui,et al.  Attention Interpretability Across NLP Tasks , 2019, ArXiv.

[30]  Joel Goh,et al.  Evidence of Upcoding in Pay-for-Performance Programs , 2015, Manag. Sci..

[31]  Francesca Ieva,et al.  Statistical Medical Fraud Assessment: Exposition to an Emerging Field , 2018 .

[32]  Monique Snoeck,et al.  GOTCHA! Network-Based Fraud Detection for Social Security Fraud , 2017, Manag. Sci..

[33]  Alex Graves,et al.  Supervised Sequence Labelling with Recurrent Neural Networks , 2012, Studies in Computational Intelligence.

[34]  Andreas Gottschling,et al.  Mixtures of t-distributions for Finance and Forecasting , 2008 .

[35]  Jionghua Jin,et al.  A survey on statistical methods for health care fraud detection , 2008, Health care management science.

[36]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[37]  David J. Hand,et al.  Statistical fraud detection: A review , 2002 .

[38]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[39]  Hanming Fang,et al.  Detecting Potential Overbilling in Medicare Reimbursement Via Hours Worked , 2016, The American economic review.

[40]  Razvan Pascanu,et al.  On the Number of Linear Regions of Deep Neural Networks , 2014, NIPS.

[41]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[42]  Martin L. Puterman,et al.  Early Detection of High-Risk Claims at the Workers' Compensation Board of British Columbia , 2003, Interfaces.

[43]  R. Townsend.  Optimal contracts and competitive markets with costly state verification , 1979 .

[44]  Daniel P. Kessler,et al.  Detecting Medicare Abuse , 2004, Journal of health economics.

[45]  Dilip Mookherjee,et al.  Optimal Auditing, Insurance, and Redistribution , 1989 .

[46]  Halbert White,et al.  Artificial neural networks: an econometric perspective ∗ , 1994 .

[47]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[48]  Yann LeCun,et al.  Generalization and network design strategies , 1989 .