{"id":6649,"date":"2026-05-05T11:03:24","date_gmt":"2026-05-05T14:03:24","guid":{"rendered":"https:\/\/eic.cefet-rj.br\/ppcic\/?p=6649"},"modified":"2026-05-05T11:03:24","modified_gmt":"2026-05-05T14:03:24","slug":"dissertation-may-06-2026-jorge-nelson-de-souza-pavao","status":"publish","type":"post","link":"https:\/\/eic.cefet-rj.br\/ppcic\/en\/dissertation-may-06-2026-jorge-nelson-de-souza-pavao\/","title":{"rendered":"Dissertation (May 06, 2026): Jorge Nelson de Souza Pav\u00e3o"},"content":{"rendered":"<p><b>Student:<\/b>\u00a0Jorge Nelson de Souza Pav\u00e3o<\/p>\n<p><b>Title: <\/b>Large Language Models for Detecting Collusion in Bidding Processes<\/p>\n<p><b>Advisors: <\/b>Kele Teixeira Belloze (Advisor) and Diego Nunes Brand\u00e3o (Co-advisor)<\/p>\n<p><b>Committee: <\/b>Kele Teixeira Belloze (CEFET\/RJ), Diego Nunes Brand\u00e3o (CEFET\/RJ),\u00a0 Raissa dos Santos Barcellos (UERJ), Eduardo Bezerra da Silva (CEFET\/RJ)<\/p>\n<p><b>Day\/Hour:<\/b>\u00a0 May 06, 2026 \/\u00a0 4:30 p.m<\/p>\n<p><b>Room:<\/b>\u00a0Sala E-520 (Bloco E, 5\u00ba andar, Cefet\/Maracan\u00e3)<\/p>\n<p><b>Abstract: <\/b>The practice of collusion in public procurement, characterized by illicit agreements between competing firms, generates significant economic losses, reduces the efficiency of public contracting, and undermines trust in institutions. Several studies have employed machine learning algorithms and statistical variables to identify indications of this type of fraud; however, challenges such as the scarcity of labeled data, difficulties in generalization, and inconsistent performance across different datasets still persist. In this context, this dissertation investigates the potential of Large Language Models (LLMs) for detecting indications of collusion based on numerical data from procurement processes. Models from different providers were evaluated using two strategies: prompt engineering and supervised fine-tuning. The experiments were conducted on three real-world datasets \u2014 Brazil, the United States, and Switzerland \u2014 and the results were compared with those of traditional algorithms reported in the literature. The findings show that prompt engineering did not produce satisfactory performance. With fine-tuning, the LLMs outperformed traditional algorithms in only one of the three evaluated scenarios. Considering performance, cost, and implementation complexity jointly, it is concluded that, at the present time, traditional algorithms offer a better cost-benefit ratio for the evaluated task, while LLMs may serve as a complementary alternative in specific scenarios where classical methods fail to achieve satisfactory results or in situations involving textual data.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Student:\u00a0Jorge Nelson de Souza Pav\u00e3o Title: Large Language Models for Detecting Collusion in Bidding Processes Advisors: Kele Teixeira Belloze (Advisor) and Diego Nunes Brand\u00e3o (Co-advisor) Committee: Kele Teixeira Belloze (CEFET\/RJ), Diego Nunes Brand\u00e3o (CEFET\/RJ),\u00a0 Raissa dos Santos Barcellos (UERJ), Eduardo Bezerra da Silva (CEFET\/RJ) Day\/Hour:\u00a0 May 06, 2026 \/\u00a0 4:30 p.m Room:\u00a0Sala E-520 (Bloco E, [&hellip;]<\/p>\n","protected":false},"author":4,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"categories":[96,2],"tags":[],"class_list":["post-6649","post","type-post","status-publish","format-standard","hentry","category-defenses","category-noticias-en"],"_links":{"self":[{"href":"https:\/\/eic.cefet-rj.br\/ppcic\/wp-json\/wp\/v2\/posts\/6649","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/eic.cefet-rj.br\/ppcic\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/eic.cefet-rj.br\/ppcic\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/eic.cefet-rj.br\/ppcic\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/eic.cefet-rj.br\/ppcic\/wp-json\/wp\/v2\/comments?post=6649"}],"version-history":[{"count":1,"href":"https:\/\/eic.cefet-rj.br\/ppcic\/wp-json\/wp\/v2\/posts\/6649\/revisions"}],"predecessor-version":[{"id":6650,"href":"https:\/\/eic.cefet-rj.br\/ppcic\/wp-json\/wp\/v2\/posts\/6649\/revisions\/6650"}],"wp:attachment":[{"href":"https:\/\/eic.cefet-rj.br\/ppcic\/wp-json\/wp\/v2\/media?parent=6649"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/eic.cefet-rj.br\/ppcic\/wp-json\/wp\/v2\/categories?post=6649"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/eic.cefet-rj.br\/ppcic\/wp-json\/wp\/v2\/tags?post=6649"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}