Applying a supervised learning model to support biometric authentication score

• Larissa Mukuno unico
• Erick Takeshi Moraes unico
• Rafael Mansur Haddad unico
• Eduardo C. Almeida UFPR

DOI: https://doi.org/10.5753/semish.2021.15823

Abstract

Facial recognition is already a part of our lives. Most smartphones can be unlocked using the face, as a way to identify the owner and provide access to data. However, it has also been gaining ground for other goals, especially in corporate solutions such as access control, document validation and online shopping. In order to increase the accuracy of our biometric score, a risk calculation model was developed that takes into account consumer behavior, based on their transaction history, aiming at reducing fraud.

Keywords: fraud, score, algorithm, biometry, facial recognition, supervised learning

References

Beraldi, F. Atualização dinâmica de modelo de regressão logística binária para detecção de fraudes em transações eletrônicas com cartão de crédito. Dissertação de Mestrado, USP, 2014.

Hair, J. F. Jr., Anderson, R. E., Tatham, R. L. & Black, W. C. (1995). Multivariate Data Analysis (3rd ed). New York: Macmillan.

Siddiqi, Naeem (2006). Credit Risk Scorecards: Developing and Implementing Intelligent Credit Scoring. SAS Institute, pp 79-83.

Zanlorensi, L., Rayson Laroca, Eduardo Luz, Alceu S. Britto Jr., Luiz S. Oliveira, David Menotti. Ocular Recognition Databases and Competitions: A Survey (2011). Wireless Sensor Networks to Control Radiation Levels. https://arxiv.org/abs/1911.09646, 2021.