AUTOMATED MODEL SELECTION FOR CORPORATION CREDIT RISK ASSESSMENT USING MACHINE LEARNING - PhD Thesis Abstract

Aug 3, 2026

Upload by Liam

Credit risk assessment determines whether a borrower is likely to default, protecting lenders and investors from harmful decisions. Corporation Credit Risk Assessment (CCRA) relies on financial indicators describing company conditions at specific times, and machine learning has become increasingly dominant in this financial research area. This study addresses the difficulty of selecting optimal learning models by automating pipeline selection while managing timeout and memory leak issues through CSV-based result storage.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages5

Reading Time13 min

AccessFree to download

Chapter One Introduction

Research Background

Preliminary Study

Research Motivation

Problem Statement

Research Questions

Research Objectives

Research Scope and Limitations

Research Significance and Contribution

Thesis Outline

Summary

Chapter Two Literature Review

Introduction

UNIVERSITI TEKNOLOGI MARA AUTOMATED MODEL SELECTION FOR CORPORATION CREDIT RISK ASSESSMENT USING MACHINE LEARNING ZULKIFLI BIN HALIM Thesis submitted in fulfillment of the requirements for the degree of Philosophy of Doctorate (Computer Science) Faculty of Computer and Mathematical Sciences May 2023 ABSTRACT Credit risk assessment is the procedure by the investors or lenders to predict the chances of loan default to measuring the risk. A wrong decision places the institution at risk. Corporation Credit Risk Assessment (CCRA) depends on the financial indicators representing the companies' status at a given time. Nowadays, machine learning is a significant field used in various applications, including the financial domain. The global trend in the CCRA study shows that implementing machine learning and deep learning techniques is expanding rapidly. These techniques have demonstrated their superiority over traditional approaches in many CCRA studies. Machine learning model selection is an iterative process of exploring, evaluating, and improving algorithms. Selecting an optimal model for a particular domain is rigid, challenging, and complicated. No free lunch theorem implies that no particular algorithm or combination of features will always produce considerably superior outcomes to others. Hence, the question arises about selecting the optimal model: the characteristic data for CCRA and the best practice machine learning pipelines. The characteristic data for CCRA includes the features used and data dimension. This study used thirteen features, including ten financial ratios, two macroeconomic variables, and the company's age. The features are selected based on the extensive literature on CCRA studies worldwide. This study also investigates the significance of data dimension in CCRA: single or multi-dimensional, and the correlation of the features. For the best practice machine learning pipelines, various machine learning models are used to discover the best model for CCRA study. This study has proposed an automated model selection based on the exhaustive search algorithm—that caused the timeout and memory leak issues. The proposed automated model selection has solved the timeout and memory leak issue by automatically writing all results in CSV files to reduce memory consumption. The samples ofthe study are the PN17 status companies. Through the automated model selection, 176 models are created across the experiment settings. The models are based on the four machine learning algorithms: logistic regression, support vector machine, decision tree, and neural network; two ensemble techniques: adaptive boost and bootstrap aggregation ; three deep learning algorithms: recurrent neural network, long short-term memory (LSTM), and gated recurrent unit (GRU) . Besides that, this study proposed two hybrid LSTM-GRU based models. The hybrid models were LSTM-GRU Double Stack (LGDS) and LSTM-GRU Alternate Double Stack (LGADS) . As a result, the proposed automated model selection has found that the LGADS model on multi-dimensional data of FR-only features and without a features correlation setup has outperformed the other models with the highest accuracy and Fl score. The LGADS model achieved 84.2% for both measurements. This study contributed to the body of knowledge by proposing an automated machine learning model selection for the CCRA study. This study might be expanded with extensive scope. The scope can be extended by adding more financial ratios since the FR features are significant for the CCRA study and adding more samples to produce better results. ACKNOWLEDGEMENT Alhamdulillah, I express my heartfelt gratitude to ALLAH SWT for granting me the opportunity to pursue and successfully complete my Ph.D. journey. I would like to extend my sincere appreciation and thanks to my supervisor, Dr. Shuhaida Mohamed Shuhidan, for her unwavering guidance and support throughout this challenging undertaking. I am also grateful

FAQs

What problem does the study target in corporation credit risk assessment?

It targets the challenge of selecting optimal machine learning models and best-practice pipelines for CCRA, where no single approach consistently performs best across settings.

How does the proposed automated model selection handle computational issues?

It uses exhaustive search while resolving timeout and memory leak problems by automatically writing all results into CSV files to reduce memory consumption.

Which models and algorithms are evaluated in the experiments?

The experiments build 176 models using four machine learning algorithms (logistic regression, support vector machine, decision tree, neural network), two ensemble methods (AdaBoost, bagging), three deep learning methods (RNN, LSTM, GRU), and two hybrid LSTM-GRU models (LGDS and LGADS).

Aug 3, 2026

Upload by Liam