Identifying Illegal Cartel Activities from Open Sources

  • Pál VadászEmail author
  • András Benczúr
  • Géza Füzesi
  • Sándor Munk
Part of the Advanced Sciences and Technologies for Security Applications book series (ASTSA)


In a truly free marketplace, business entities compete with each other to appeal and to satisfy the purchasing needs of their customers. This elegant and efficient process can only succeed when competitors set their prices independently. When collusion occurs among competitors, prices rise, quality is often compromised and the public at large loses. In all developed countries around the world, price fixing, bid rigging and other forms of collusion are illegal and prosecuted through judicial systems. The relevance of OSINT for this form of activity is two-fold: as covertly conducted activity between parties, market manipulation and price fixing is particularly difficult to detect and prove while, at the same time, it is particularly susceptible to automated information discovery which can be vital for law enforcement agencies. However, finding even weak threads of evidentiary material requires extensive human and financial resources. This chapter proposes an automated methodology for text and data analysis, which aims to save both professional time and cost by equipping investigators with the means to detect questionable behavioural patterns thus triggering a more intimate review. This is followed by working examples of how OSINT characteristics and techniques come together for law enforcement purposes.


European Union Gross Domestic Product World Trade Organization Security Model Public Procurement 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. Abrantes-Metz RM (2013) Proactive vs. reactive anti-cartel policy: the role of empirical screens. Social Science Research Network., 15 June 2016
  2. Anti-cartel Enforcement Manual (2015) International competition network., 15 June 2016
  3. Bertino E, Samarati P, Jajodia S (1997) An extended authorization model for relational databases. IEEE Trans Knowl Data Eng 9(1):85–101Google Scholar
  4. Bishop S, Walker M (2010) The economics of EC competition law. Sweet and Maxwell, Andover, UK, p 171Google Scholar
  5. Chandola V, Banerjee A, Kumar V (2009) Anomaly detection: a survey. ACM Comput Surv (CSUR) 41(3):15Google Scholar
  6. Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. arXiv preprint arXiv:1603.02754
  7. COM (2003) 317, Communication from the Commission to the Council, the European Parliament, and the European Economic and Social Committee on a Comprehensive EU Policy against Corruption. Commission of the European Communities, Brussels, 2003Google Scholar
  8. Cosnita-Langlais A, Tropeano JP (2013) Fight cartels or control mergers? On the optimal allocation of enforcement efforts within competition policy. Int Rev Law Econ 34:34–40Google Scholar
  9. Cox Dr (1958) The regression analysis of binary sequences (with discussion). J Roy Stat Soc B 20:215–242zbMATHGoogle Scholar
  10. Danger K, Capobianco A (2009a) Guidelines for fighting bid rigging in public procurement, OECD., 13 Mar 2016
  11. Danger K, Capobianco A (2009b) Detecting bid rigging in public procurement, OECD., 30 Jan 2016
  12. Daróczy B, Vaderna P, Benczúr, A (2015) Machine learning based session drop prediction in LTE networks and its SON aspects. In: 2015 IEEE 81st vehicular technology conference (VTC Spring). IEEEGoogle Scholar
  13. Fóra G (2014) Közbeszerzési eljárások dokumentumainak adatfeldolgozása 1998–2004 (Data extraction from public procurement documents 1998–2004). 8th Report. Korrupciókutató Központ, BudapestGoogle Scholar
  14. Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55(1):119–139MathSciNetCrossRefzbMATHGoogle Scholar
  15. Funderburk DR (1974) Price fixing in the liquid-asphalt industry: economic analysis versus the ‘hot document’. Antitrust Law Econ Rev 7:61–74Google Scholar
  16. Han J, Kamber M (2001) Data mining: concepts and techniques. Morgan KaufmannGoogle Scholar
  17. Harrington JE (2006) Behavioral screening and detection of cartels. In: Ehlermann CD, Atanasiu I (eds) European competition law annual 2006: enforcement of prohibition of cartels. Hart Publishing, Oxford, PortlandGoogle Scholar
  18. Harrington JE (2008) Detecting cartels. In: Buccirossi P (ed) Handbook in antitrust economy. MIT PressGoogle Scholar
  19. Hinloopen J, Martin S (2006) The economics of cartels, cartel policy, and collusion: introduction to the special issue. Int J Ind Organ 24(6):1079–1082Google Scholar
  20. Hölzer H (2014) Checklist of the Swedish Competition Authority in Harmonization of public procurement system in Ukraine with EU standards, Report on the development of diagnostic tools and Guidelines for the AMCU for identifying and preventing bid-rigging cases, Annex 3., Crown Agents Ltd., 2 Oct 2014., 10 Jan 2016
  21. Hüschelrath K (2010) How are cartels detected? The increasing use of proactive methods to establish antitrust infringements. J Eur Compet Law Pract 1(6)Google Scholar
  22. Hüschelrath K, Veith T (2011) Cartel detection in procurement markets. Discussion Paper No. 11-066. Centre for European Economic Research, MannheimGoogle Scholar
  23. Ivaldi M, Khimich A, Jenny F (2014) Measuring the economic effects of cartels in developing countries, published in the framework of the CEPR PEDL program., 7 Feb 2016
  24. Jeh G, Widom J (2002) SimRank: a measure of structural-context similarity. In: Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining. ACMGoogle Scholar
  25. Joachims T (1998) Text categorization with support vector machines: learning with many relevant features. In: European conference on machine learning. Springer, BerlinGoogle Scholar
  26. Krizhevsky A, Sutskever I, Hinton GE (2012). Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systemsGoogle Scholar
  27. Lee H, Pham P, Largman Y, Ng AY (2009) Unsupervised feature learning for audio classification using convolutional deep belief networks. In: Advances in neural information processing systems. pp 1096–1104Google Scholar
  28. Lewis TG (2011) Network science: theory and applications. WileyGoogle Scholar
  29. Marshall RC, Marx LM (2007) Bidder collusion. J Econ Theory 133(1):374–402Google Scholar
  30. Morgan EJ (2009) Controlling cartels—implications of the EU policy reforms. Eur Manage J 27(1):1–12Google Scholar
  31. Morozov I, Podkolzina E (2013) Collusion detection in procurement actions. Working Paper. National Research University, Higher School of Economics (Russia), MoscowGoogle Scholar
  32. Nemeslaki A, Pocsarovszky K (2011) Web crawler research methodology. In: 22nd European Regional ITS Conference, Budapest 2011: Innovative ICT Applications—Emerging Regulatory, Economic and Policy Issues 52173, International Telecommunications Society (ITS)., 7 Feb 2016
  33. Nicholls SN (2011) Detecting, mitigating & fighting bid rigging in public procurement, fair trading commission., 30 Jan 2016
  34. OECD (2012) Recommendation of the OECD council on fighting bid rigging in public procurement. OECD Council, Paris, 2012Google Scholar
  35. OECD (2013) Ex officio cartel investigations and the use of screens to detect cartels. Policy Roundtables. OECD, 2013Google Scholar
  36. Padhi SS, Mohapatra PKJ (2011) Detection of collusion in government procurement auctions. J Purchasing Supply Manage 17(4):207–221Google Scholar
  37. Pálovics R, Ayala-Gómez F, Csikota B, Daróczy B, Kocsis L, Spadacene D, Benczúr AA (2014, Oct). RecSys Challenge 2014: an ensemble of binary classifiers and matrix factorization. In: Proceedings of the 2014 Recommender Systems Challenge. ACM, p. 13Google Scholar
  38. Porter RH, Zona JD (1992) Detection of bid rigging in procurement auctions, No. w4013, National Bureau of Economic ResearchGoogle Scholar
  39. Powers DMW (2011) Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation (PDF). J Mach Learn Technol 2(1):37–63MathSciNetGoogle Scholar
  40. Safavian SR, Landgrebe D (1998, May/June) A survey of decision tree classifier methodology. IEEE Trans Syst Man Cybern 22:660–674Google Scholar
  41. Swets JA (1996) Signal detection theory and ROC analysis in psychology and diagnostics: collected papers, Lawrence Erlbaum Associates, Mahwah, NJGoogle Scholar
  42. Tan PN, Steinbach M, Kumar V (2013) Data mining cluster analysis: basic concepts and algorithmsGoogle Scholar
  43. Tong S, Koller D (2001, Nov) Support vector machine active learning with applications to text classification. J Mach Learn Res 2:45–66Google Scholar
  44. Tóth B, Fazekas M, Czibik Á, Tóth JI (2015) Toolkit for detecting collusive bidding in public procurement. With examples from Hungary. Working Paper series: CRC-WP/2014:02, Version 2.0—Corruption Research Center, BudapestGoogle Scholar
  45. Vojtěch S, Mynarz J, Węcel K, Klímek J, Knap T, Nečaský M (2014) Linked open data for public procurement. In: Auer S, Bryl V, Tramp S (eds) Linked open data. Creating knowledge out of interlinked data. Lecture Notes in Computer Science 8661. Springer, Heidelberg, pp. 196–213Google Scholar
  46. Wang H, Wang N, Yeung DY (2015) Collaborative deep learning for recommender systems. In: Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining. ACMGoogle Scholar
  47. Wensinck W, De Vet JM et al (2013) Identifying and reducing corruption in public procurement in the EU. PricewaterhouseCoopers, Ecorys, BrusselsGoogle Scholar
  48. Werden GJ, Hammond SD, Barnett BA (2011) Deterrence and detection of cartels: using all the tools and sanctions. Antitrust Bull 56(2):207–234Google Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Pál Vadász
    • 1
    Email author
  • András Benczúr
    • 2
  • Géza Füzesi
    • 3
  • Sándor Munk
    • 1
  1. 1.National University of Public ServiceBudapestHungary
  2. 2.Institute for Computer Science and Control of the Hungarian Academy of Sciences (MTA SZTAKI)BudapestHungary
  3. 3.Hungarian Competition AuthorityBudapestHungary

Personalised recommendations