Banca de QUALIFICAÇÃO: Flávio Henrique Martins

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
STUDENT : Flávio Henrique Martins
DATE: 17/10/2023
TIME: 16:00
LOCAL: Teams
TITLE:

Prediction of unused and canceled airline tickets on leave from work through the Daily and Ticket Concession System of the Federal Government - SCDP

KEY WORDS:

machine learning, classification algorithms, decision making, daily allowances, airline tickets, absence from work, service cancellation

PAGES: 53
BIG AREA: Ciências Exatas e da Terra
AREA: Ciência da Computação
SUBÁREA: Metodologia e Técnicas da Computação
SPECIALTY: Banco de Dados
SUMMARY:

This work aims to carry out an analysis of the Proposal for Concession of Daily Allowances and Tickets (PCDP) for absence from work, which use the air modality for travel, carried out by public servants and occasional collaborators between the years 2014 to 2021, with the purpose of understanding the existence of behaviors or reasons that lead to non-use or cancellation of tickets, in order to support decision-making by managers in approving travel and improve the financial execution of the refund policy used by the Daily and Ticket Concession System of the Federal Government (SCDP). The approaches used take into account the most used machine learning techniques currently used to predict cancellations in hotel reservation, surgery scheduling and streaming subscription services, such as the eXtreme Gradient Boosting (XGBoost) classification algorithms, Support Vector Machine (SVM), Decision Trees and Random Forest (RF).

COMMITTEE MEMBERS:
Presidente - 1146571 - MARCIO DE CARVALHO VICTORINO
Interno - 1072256 - EDISON ISHIKAWA
Interno - 402520 - MARCELO LADEIRA
Externo à Instituição - ANDREI LIMA QUEIROZ - UnB