Building a credit scoring model to assign a reference score based on credit transaction and relevant profile data

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2019.

Detalles Bibliográficos
Autores principales:	Islam, Saqib Al, Aziz, Rifah Sama, Ahmed, Aritra, Abida, Fauzia
Otros Autores:	Majumdar, Mahbub Alam
Formato:	Tesis
Lenguaje:	English
Publicado:	Brac University 2020
Materias:	Credit score Credit risk Loan assessment Machine learning Artifcial intelligence Random forests Gradient boosting GBM Extreme gradient boosting Deep neural networks Interpret-ability Finance > Data processing.
Acceso en línea:	http://hdl.handle.net/10361/13644

id	10361-13644
record_format	dspace
spelling	10361-136442022-01-26T10:04:55Z Building a credit scoring model to assign a reference score based on credit transaction and relevant profile data Islam, Saqib Al Aziz, Rifah Sama Ahmed, Aritra Abida, Fauzia Majumdar, Mahbub Alam Department of Computer Science and Engineering, Brac University Credit score Credit risk Loan assessment Machine learning Artifcial intelligence Random forests Gradient boosting GBM Extreme gradient boosting Deep neural networks Interpret-ability Finance--Data processing. This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2019. Cataloged from PDF version of thesis. Includes bibliographical references (pages 49-52). A credit score is a numerical expression based on a level analysis of a person's credit files, to represent the creditworthiness of an individual. The credit score plays a major role in banks, financial institutions loaning money to individuals for their personal or business needs. This score is given based on factors such as personal information, assets, financial behavior and financial history. This system is not digitized or implemented yet in Bangladesh. So our aim is to build a reliable and robust credit scoring model which would help institutions like such to have an accurate reference score to rely on when validating a client. We were able to obtain an optimized model with an accuracy of( 93%). The model is based on CART(Classification and Regression Trees) using Gradient Boosting method(GBM). We also proposed a new hybrid model consisting of a two step architecture. The first one based on distributed Random Forests, the individual decision tree outputs of which was fed into a Deep Neural Network(DNN), and trained on to achieve marginally better results than using only Random Forest approach. Since, credit scoring an individual is a sensitive issue, it is not ethical to provide a score without proper justification. We conducted interpret-ability analysis on our model and generated visual representations of the criterion affecting the output of our model and provide necessary information to analyze the client efectively. Our results were conclusive and imitated the process of evaluating an individual precisely. The work- ow we proposed could be implemented in production to provide a concrete base for evaluation and prediction of defaulters. Simultaneously provide a detailed overview of the results obtained. This could help financial institutions immensely and help them save millions lost by default loans. Saqib Al Islam Rifah Sama Aziz Aritra Ahmed Fauzia Abida B. Computer Science 2020-01-20T07:29:13Z 2020-01-20T07:29:13Z 2019 2019-09 Thesis ID 16101084 ID 19141019 ID 16101216 ID 16101320 http://hdl.handle.net/10361/13644 en 52 pages application/pdf Brac University
institution	Brac University
collection	Institutional Repository
language	English
topic	Credit score Credit risk Loan assessment Machine learning Artifcial intelligence Random forests Gradient boosting GBM Extreme gradient boosting Deep neural networks Interpret-ability Finance--Data processing.
spellingShingle	Credit score Credit risk Loan assessment Machine learning Artifcial intelligence Random forests Gradient boosting GBM Extreme gradient boosting Deep neural networks Interpret-ability Finance--Data processing. Islam, Saqib Al Aziz, Rifah Sama Ahmed, Aritra Abida, Fauzia Building a credit scoring model to assign a reference score based on credit transaction and relevant profile data
description	This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2019.
author2	Majumdar, Mahbub Alam
author_facet	Majumdar, Mahbub Alam Islam, Saqib Al Aziz, Rifah Sama Ahmed, Aritra Abida, Fauzia
format	Thesis
author	Islam, Saqib Al Aziz, Rifah Sama Ahmed, Aritra Abida, Fauzia
author_sort	Islam, Saqib Al
title	Building a credit scoring model to assign a reference score based on credit transaction and relevant profile data
title_short	Building a credit scoring model to assign a reference score based on credit transaction and relevant profile data
title_full	Building a credit scoring model to assign a reference score based on credit transaction and relevant profile data
title_fullStr	Building a credit scoring model to assign a reference score based on credit transaction and relevant profile data
title_full_unstemmed	Building a credit scoring model to assign a reference score based on credit transaction and relevant profile data
title_sort	building a credit scoring model to assign a reference score based on credit transaction and relevant profile data
publisher	Brac University
publishDate	2020
url	http://hdl.handle.net/10361/13644
work_keys_str_mv	AT islamsaqibal buildingacreditscoringmodeltoassignareferencescorebasedoncredittransactionandrelevantprofiledata AT azizrifahsama buildingacreditscoringmodeltoassignareferencescorebasedoncredittransactionandrelevantprofiledata AT ahmedaritra buildingacreditscoringmodeltoassignareferencescorebasedoncredittransactionandrelevantprofiledata AT abidafauzia buildingacreditscoringmodeltoassignareferencescorebasedoncredittransactionandrelevantprofiledata
_version_	1814307058221056000

Building a credit scoring model to assign a reference score based on credit transaction and relevant profile data

Ejemplares similares