Predictive Analytics as A Service on Moroccan Tax Evasion

  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract

    Tax evasion is a global problem in governments. It affects society by damaging public accounts and compromising government performance. The government must take a multidisciplinary approach to face this phenomenon. Analytics on big data enables government organizations to improve existing processes and operations and engage in entirely new types of analyses that weren’t possible before. Predictive analytics combines the capabilities of machine learning, statistical analysis and data mining to forecast the future and allows tax authority to prevent tax fraud, reduce the cost of managing taxes and optimize public spending.

    The purpose of this paper is to predict income from direct Moroccan taxes based on the linear regression model as a first step in the fight of the tax evasion.



  • Keywords

    Predictive Analytics, linear regression, Statistical Computing, Tax evasion.

  • References

      [1] Amori Mohammed, El Mokhtar Zbair (2016) ‘Système Fiscal et Croissance Économique, Etude Empirique : Cas Du Maroc’, Sciences Economiques, Université Mohammed V, and Sciences Juridiques 18 (2): 438–44.

      [2] Earley, Christine E (2015) ‘Data Analytics in Auditing: Opportunities and Challenges ‘Business Horizons 58 (5). “Kelley School of Business, Indiana University”: 493–500.

      [3] Gray, Glen L., and Roger S. Debreceny (2014) ‘A Taxonomy to Guide Research on the Application of Data Mining to Fraud Detection in Financial Statement Audits’, International Journal of Accounting Information Systems 15 (4). Elsevier Inc.: 357–80.

      [4] Chandola, Varun, Arindam Banerjee, and Vipin Kumar (2009) ‘Anomaly Detection’, ACM Computing Surveys 41 (3): 1–58.

      [5] Wu, Roung Shiunn, C. S. Ou, Hui Ying Lin, She I. Chang, and David C. Yen( 2012) ‘Using Data Mining Technique to Enhance Tax Evasion Detection Performance’, Expert Systems with Applications 39 (10): 8769–77.

      [6] Tian, Feng, Tian Lan, Kuo Ming Chao, Nick Godwin, Qinghua Zheng, Nazaraf Shah, and Fan Zhang(2016) ‘Mining Suspicious Tax Evasion Groups in Big Data’, IEEE Transactions on Knowledge and Data Engineering 28 (10): 2651–64.

      [7] Dan Bogdanov, and J Marko ( 2017)’Financial Cryptography and Data Security’,9603: 227–34.

      [8] Basta, Stefano, Fabio Fassetti, Massimo Guarascio, Giuseppe Manco, Fosca Giannotti, Dino Pedreschi, Laura Spinsanti, Gianfilippo Papi, and Stefano Pisani (2009) ‘High Quality True-Positive Prediction for Fiscal Fraud Detection’, ICDM Workshops 2009 - IEEE International Conference on Data Mining, 7–12.

      [9] Babu, S Kishore, and S Vasavi (2017) ’Predictive Analytics as a Service on Tax Evasion Using Gaussian Regression Process’.

      [10] Yaram, Suresh. (2016) ‘Machine Learning Algorithms for Document Clustering and Fraud Detection’, 2016 IEEE International Conference on Data Science and Engineering (ICDSE).

      [11] Rahimikia, Eghbal, Shapour Mohammadi, Teymur Rahmani, and Mehdi Ghazanfari (2017) ‘Detecting Corporate Tax Evasion Using a Hybrid Intelligent System: A Case Study of Iran’, International Journal of Accounting Information Systems 25. Elsevier Inc.: 1–17.

      [12] Bakar, Zuriana Abu, Rosmayati Mohemad, Akbar Ahmad, and Mustafa Mat Deris(2006) ‘A Comparative Study for Outlier Detection Techniques in Data Mining’




Article ID: 23253
DOI: 10.14419/ijet.v7i4.32.23253

Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.