Banca de QUALIFICAÇÃO: Daniel Ferreira Schulz

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
STUDENT : Daniel Ferreira Schulz
DATE: 17/03/2023
TIME: 14:00
LOCAL: https://teams.microsoft.com/l/meetup-join/19%3ameeting_NGU3NzA5MDAtZTM3Ni00NGVlLWJkMTgtY2ZjNDU2ODk4N
TITLE:

Detecção de Falhas em um Aplicativo Móvel Bancário

KEY WORDS:

Failure Detection, Mobile Banking, Web Analytics, CRISP-DM, Machine Learning

PAGES: 59
BIG AREA: Ciências Exatas e da Terra
AREA: Ciência da Computação
SUMMARY:

High availability is an increasingly important requirement in IT systems. One of the strategies implemented to achieve a stable environment is the continuous monitoring of services, as described by ITIL. Given the above, this work proposes a failure detection approach through data mining techniques. The approach was modeled using the CRISPDM reference model. The trained models used data extracted from a Web Analytics tool that stores user interactions with a mobile banking application. The effects of different attribute engineering techniques, such as variable filtering, data standardization and generation of synthetic samples, were also evaluated. Finally, the results were compared between seven algorithms, and the support vector machine was the one that obtained the best result, with an F1-Score of 0.954 and a ROC-AUC of 0.989

BANKING MEMBERS:
Externo à Instituição - ALAN DEMÉTRIUS BARIA VALEJO
Presidente - 1706731 - ALETEIA PATRICIA FAVACHO DE ARAUJO VON PAUMGARTTEN
Interno - 3085005 - GERALDO PEREIRA ROCHA FILHO
Interno - 2518570 - MARCOS FAGUNDES CAETANO