Beatriz Albiero, Estevo Uyrá, Ramon Vilarino, J. Silva, T. Souza, Ricardo Caneloi dos Santos, Sami Yamouni, Renato Vicente
{"title":"EMPLOYING GRADIENT BOOSTING AND ANOMALY DETECTION FOR PREDICTION OF FRAUDS IN ENERGY CONSUMPTION","authors":"Beatriz Albiero, Estevo Uyrá, Ramon Vilarino, J. Silva, T. Souza, Ricardo Caneloi dos Santos, Sami Yamouni, Renato Vicente","doi":"10.5753/ENIAC.2019.9345","DOIUrl":"https://doi.org/10.5753/ENIAC.2019.9345","url":null,"abstract":"Energy fraud is a critical economical burden for electric power orga-nizations in Brazil. In this paper we present the application of novel MachineLearning algorithms to boost efficiency in detection of energy frauds. More-over, we also propose a generalized and unsupervised model for fraud detectionbased on consumption anomalies.","PeriodicalId":289788,"journal":{"name":"Tecnologias, Métodos e Teorias na Engenharia de Computação","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125236863","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"BRAZILIAN GOVERNMENT PROCUREMENTS: AN APPROACH TO FIND FRAUD TRACES IN COMPANIES RELATIONSHIPS","authors":"R. A. Baldomir, G. V. Erven, C. Ralha","doi":"10.5753/ENIAC.2018.4464","DOIUrl":"https://doi.org/10.5753/ENIAC.2018.4464","url":null,"abstract":"Data mining has been an area of high visibility in recent years and many researches have shown good efficiency in this area to find information in large databases. This paper presents an approach to find fraud traces applying data mining techniques to public databases of the Brazilian Federal Government bidings. The aim is to find evidence of fraud, such as stunts and cartels. The task of finding fraud evidences in large amount of data is complex for auditors since they have correlate data. The proposed approach was used to develop a prototype which has been used by auditors in the Ministry of Transparency and General Comptroller of the Union (CGU).","PeriodicalId":289788,"journal":{"name":"Tecnologias, Métodos e Teorias na Engenharia de Computação","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124301386","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}