Banca de DEFESA: José Nilo Alves de Sousa Neto

Uma banca de DEFESA de MESTRADO foi cadastrada pelo programa.
STUDENT : José Nilo Alves de Sousa Neto
DATE: 18/04/2023
TIME: 14:30
LOCAL: LARA - Laboratório de Raciocínio Automatizado
TITLE:

Estimation of Union Property Values Administered by the Brazilian Army with Machine Learning Techniques and Space Components

KEY WORDS:

machine learning, real estate, spatial components

PAGES: 89
BIG AREA: Ciências Exatas e da Terra
AREA: Ciência da Computação
SUBÁREA: Metodologia e Técnicas da Computação
SUMMARY:

The valuation of an institution’s patrimony represents a necessary condition for an efficient management of its assets. The execution and analysis of real estate appraisal reports areessential to the achievement of some strategic objectives of the Brazilian Army, but theyare also quite costly in terms of time, labor and financial resources. Sometimes, greateffort is required for the aforementioned steps to take place and the market value finally obtained is inconsistent with what was initially imagined by the authorities, causing the technical study carried out to not be effectively used in negotiations by the organization. In this sense, this work proposes the development of multilevel predictive models capable of building estimates of urban and rural real estate values. The models have a reasonable level of assertiveness and national geographic coverage when generate estimated market values of Union real estate assets. Intrinsic and extrinsic variables to the properties were considered, including tests of aggregation of spatial components on some of them. As the interpretability of the proposed solution is an important requirement, in both linear and nonlinear approaches, the Shapley value was adopted as a tool to support the guarantee of explainability. Partial least squares structural equation modeling (PLS-SEM) method was applied in order to select features in a reasoned and visually accessible manner. These two considerations associated with real estate price modeling at a national level represent an innovation of this work in relation to the analyzed scientific literature.

BANKING MEMBERS:
Externo à Instituição - BERNARDO ALVES FURTADO - UFMG
Interno - 1114843 - ARI MELO MARIANO
Interno - 1072256 - EDISON ISHIKAWA
Presidente - 402520 - MARCELO LADEIRA