IEEE-CIS fraud detection: a case study for fraudulent transaction detection based on supervised learning models

ABSTRACT : This paper proposes a solution to the Kaggle competition: "IEE-Fraud Detection", whose objective is to detect fraudulent transactions in a customer and transactional dataset collected by an E-commerce site to construct a transaction confirmation system via text messaging of the payment services company Vesta Corporation. Exploratory analysis of the data and different modeling approaches are shown, selecting the most appropriate results for anomaly detection.

• Autores: González Benaissa, Aarón Al Rachid
• Tipo de recurso: Tesis
• Fecha de publicación: 2021
• Institución: Universidad de Antioquia
• Repositorio: Repositorio UdeA
• Idioma: eng
• OAI Identifier: oai:bibliotecadigital.udea.edu.co:10495/20175
• Acceso en línea: http://hdl.handle.net/10495/20175; https://github.com/AaronGonzalezB/monografia-especializacion-udea.git
• Palabra clave: Electronic commerce; Comercio electrónico; Artificial intelligence; Inteligencia artificial; Fraud; Fraude; Illegal practices; Practicas Ilegales; Classification systems; Sistemas de Clasificación; Linked open data; Datos abiertos vinculados; Fraud detection; binary classification; imbalanced data; dimensionality reduction; http://aims.fao.org/aos/agrovoc/c_8139c3d0; http://aims.fao.org/aos/agrovoc/c_15682; http://aims.fao.org/aos/agrovoc/c_9000017; http://aims.fao.org/aos/agrovoc/c_773acdb4; http://vocabularies.unesco.org/thesaurus/concept11036; http://vocabularies.unesco.org/thesaurus/concept3052
• Rights: openAccess
• License: http://creativecommons.org/licenses/by-nc-sa/2.5/co/