Auditing Government Purchases with a Multicriteria Anomaly Detection Strategy
Keywords:anomaly detection, government purchases, data mining
Government purchases are the usual instrument for public acquisition of goods and services. Despite extensive legislation, several control and auditing mechanisms, frauds are still diverse and commonplace at all levels of public administration, wasting public resources. Through the use of frequent patterns, temporal correlation and combined analysis of multi-criteria, this work proposes a methodology for detecting anomalies in government purchases. The methodology promotes several levels of filtering with respect to entities involved and purchases are considered as fraudulent based on diverse criteria. The applicability and effectiveness of the methodology is demonstrated through a real case study where we were able to identify a long term provider collusion.
Agrawal, R. and Srikant, R. Fast algorithms for mining association rules in large databases. In Proceedings of the 20th International Conference on Very Large Data Bases. VLDB ’94. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, pp. 487–499, 1994.
Balaniuk, R., Bessiere, P., Mazer, E., and Cobbe, P. Corruption risk analysis using semi-supervised naïve bayes classifiers. International Journal of Reasoning-based Intelligent Systems vol. 5, pp. 237 – 245, 2013.
Cao, B., Mao, M., Viidu, S., and Yu, P. S. Hitfraud: A broad learning approach for collective fraud detection in heterogeneous information networks. CoRR vol. abs/1709.04129, 2017.
Cao, S., Yang, X., Chen, C., Zhou, J., Li, X., and Qi, Y. A. Titant: Online real-time transaction fraud detection in ant financial. CoRR vol. abs/1906.07407, 2019.
Decreto. Decreto n.10.024/2019 - pregão, 2019. Acessado: 09 mar. 2020.
Fraga, A. Detecção de Casos Suspeitos de Fraude em Licitações Realizadas no Município da Paraíba. Ph.D. thesis, Universidade Federal da Paraíba, Brasil, 2017.
Ghedini Ralha, C. and Sarmento Silva, C. V. A multi-agent data mining system for cartel detection in brazilian government procurement. Expert Syst. Appl. 39 (14): 11642–11656, Oct., 2012.
Grilo Junior, T. Aplicação de Técnicas de Data Mining para Auxiliar o Processo de Fiscalização. Ph.D. thesis, Universidade Federal da Paraíba, 2010.
Gutflaish, E., Kontorovich, A., Sabato, S., Biller, O., and Sofer, O. Temporal anomaly detection: calibrating the surprise. CoRR vol. abs/1705.10085, pp. 1705.10085, 2017.
Haldar, M., Abdool, M., Ramanathan, P., Xu, T., Yang, S., Duan, H., Zhang, Q., Barrow-Williams, N., Turnbull, B. C., Collins, B. M., and Legrand, T. Applying deep learning to airbnb search. CoRR vol. abs/1810.09591, 2018.
Hallac, D., Vare, S., Boyd, S. P., and Leskovec, J. Toeplitz inverse covariance-based clustering of multivariate time series data. CoRR vol. abs/1706.03161, pp. 1706.03161, 2017.
Licitações, L. lei n.8666/93 - licitações e contratos, 1993. Acessado: 09 jun. 2019.
Nian, K., Zhang, H., Tayal, A., Coleman, T., and Li, Y. Auto insurance fraud detection using unsupervised spectral ranking for anomaly. The Journal of Finance and Data Science 2 (1): 58 – 75, 2016.
Pregão, D. Decreto n.5450/2005 - pregão, 2005. Acessado: 09 mar. 2020.
Pregão, L. lei n.10.520/2002 - pregão, 2002. Acessado: 09 jun. 2019.
Ramakrishnan, J., Shaabani, E., Li, C., and Sustik, M. A. Anomaly detection for an e-commerce pricing system, 2019.
Ren, H., Xu, B., Wang, Y., Yi, C., Huang, C., Kou, X., Xing, T., Yang, M., Tong, J., and Zhang, Q. Time-series anomaly detection service at microsoft. CoRR vol. abs/1906.03821, 2019.
Schulze, J.-P., Mrowca, A., Ren, E., Loeliger, H.-A., and Böttinger, K. Context by proxy: Identifying contextual anomalies using an output proxy. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. KDD ’19. ACM, New York, NY, USA, pp. 2059–2068, 2019.
Siddiqui, M. A., Fern, A., Dietterich, T. G., Wright, R., Theriault, A., and Archer, D. W. Feedback-guided anomaly discovery via online optimization. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. KDD ’18. ACM, New York, NY, USA, pp. 2200–2209, 2018.
Song, D., Xia, N., Cheng, W., Chen, H., and Tao, D. Deep r -th root of rank supervised joint binary embedding for multivariate time series retrieval. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. KDD ’18. ACM, New York, NY, USA, pp. 2229–2238, 2018.
Tian, K., Zhou, S., Fan, J., and Guan, J. Learning competitive and discriminative reconstructions for anomaly detection. CoRR vol. abs/1903.07058, pp. 1903.07058, 2019.
Yagoubi, D. E., Akbarinia, R., Kolev, B., Levchenko, O., Masseglia, F., Valduriez, P., and Shasha, D. Parcorr: efficient parallel methods to identify similar time series pairs across sliding windows. Data Mining and Knowledge Discovery vol. 32, 08, 2018.
Zaki, M. J. and Meira Jr., W. Data Mining and Machine Learning: Fundamental Concepts and Algorithms. Cambridge University Press, 2020.
Zaki, M. J., Parthasarathy, S., and Li, W. A localized algorithm for parallel association mining. In Proceedings of the Ninth Annual ACM Symposium on Parallel Algorithms and Architectures. SPAA ’97. Association for Computing Machinery, New York, NY, USA, pp. 321–330, 1997.
Zheng, P., Yuan, S., Wu, X., Li, J., and Lu, A. One-class adversarial nets for fraud detection, 2018.