http://ir.haramaya.edu.et//hru/handle/123456789/46 Mon, 20 Apr 2026 12:31:22 GMT 2026-04-20T12:31:22Z http://ir.haramaya.edu.et//hru/handle/123456789/8129 CONSTRUCTING A PREDICTIVE MODEL FOR CREDIT RISK ASSESSMENT IN THE BANKING SECTOR USING MACHINE LEARNING TECHNIQUES GELETA BEGNA; Million Meshesha (PhD) A commercial bank is a type of financial intermediary that takes deposits and uses them to fund lending operations. Credit risk occurs when a debtor fails to make a loan or other credit-related payments. Banks often regulate and manage risk through the discipline known as risk management. Creating and implementing a technology that can effectively support risk management is crucial. This study used Awash Bank Share Company as a case study to examine how machine-learning techniques support loan risk assessment. Following the acquisition of credit data from Awash Bank, appropriate features were selected and data preparation procedures, including data preprocessing, were accomplished. Recursive Feature Elimination (RFE) was utilized for attribute selection during data preprocessing, and efforts were made to clean the data by handling missing values and correcting errors. The important attributes that were identified are Loan Type, Amount Granted, Mode of Repayment, Principal, Interest Rate, Days Overdue, Net worth, Current ratio, Quick Ratio, Debt to Asset ratio, Debt to Equity Ratio, Net profit margin, Liabilities, Total Capital, Total Asset, and target class Status. To address data imbalance and control model overfitting, SMOTE and L2 regularization were applied. This study employs two data splitting techniques (Percentage split and 10-fold cross-validation). For constructing a prediction model machine learning algorithms, such as MLP (Multi-Layer Perceptron), SVM (Support Vector Machine), and LR (Logistic Regression) are employed to identify and classify credit Status into Pass or Loss categories. According to the experimental results, the MLP classifier achieves a higher classification accuracy of 99.35% because MLP's ability to learn complicated patterns as well as its independence from data sequence dependencies led to its excellent performance in this context and hence we suggest MLP for constructing an applicable system for credit risk assessment. So, this study successfully constructs a predictive model with higher accuracy for Credit Risk Assessment in the Banking Sector to identify customers' credit repayment ability by using Machine Learning Techniques. However, the study constructs a predictive model based on the data obtained from one bank, Awash Bank. It is therefore our recommendation to collect data from different banks so as to construct a generic model. 93 Sat, 01 Jun 2024 00:00:00 GMT http://ir.haramaya.edu.et//hru/handle/123456789/8129 2024-06-01T00:00:00Z http://ir.haramaya.edu.et//hru/handle/123456789/8115 DEVELOPING ISLAMIC LEGAL KNOWLEDGE-BASED SYSTEM USING RULE BASED REASONING Abubeker Ali Adem; Dr.Million M. (Ph.D.); Tilahun S. (Assistant Professor) The objective of this research primarily focused to capture tacit and explicit knowledge from domain experts and existed documents in order to support the decision making processe of the domain experts and to provide a solution for existing problems, such as problem related to a societies social (i.e. racism, inappropriet marriage and divorce), economical (support the process of financing), and political (i.e. islamic penal laws for crime and punishment) issues. Based on extracted knowledges rules were formulated to develop knowledge-based system for islamic legal system inorder to address the difficulty of getting informations and knowledges for the problem stated above. After developing the knowledge based system, the system were demonstrated and evaluated to test the performance and user acceptance of the proposed knowledge-based system. The study followed Design Science Research Methodology. And also, in order to evaluate the proposed knowledge based system questionary were used. The knowledge’s collected from experts and codified sources were represented in the form of rules and facts. The inference engine is used for reasoning by comparing the rules and facts stored in rule base with user specific problem or facts which are stored in working memory, so the inference engine provides solution for problem related to marriage, divorce, commercial dealing and islamic banking service, racism, islamic penal laws, and islamic rules and regulations in order to advice, recommend, direct, and support decision making of an experts and users. And also the result obtained suggested that the proposed knowledge-based system can play an important role to the process of building family, maintain peace and fight crime and racism, and support economy of country. One of the major limitation was unable to follow a proper approaches such as questionary along with interview before developing the knowledge-based system in order to identify and understand existing problem and applicability of knowledge-based system. Furthermore, the proposed rule-based knowledge-based system is limited on reasoning and unable to learn from its experience so if it intgrete with case based reasoning more complex problems can be handled 127 Thu, 01 Aug 2024 00:00:00 GMT http://ir.haramaya.edu.et//hru/handle/123456789/8115 2024-08-01T00:00:00Z http://ir.haramaya.edu.et//hru/handle/123456789/8014 PREDICTING HIGHER EDUCATION STUDENTS’ ACADEMIC PERFORMANCE USING MACHINE LEARNING DESTA TADESSE The primary goal of every educational institution is to deliver the best educational experience and knowledge to students. Achieving this goal involves recognizing students in need of extra support and implementing measures to enhance their academic performance. This study investigates five machine learning algorithms to construct a classification model that is capable of predicting students’ academic performance. The machine learning algorithms utilized in this study include Naïve Bayes, Decision Tree, Logistic Regression, Random Forest, and Linear Regression. The model is constructed using three distinct machine-learning platforms: WEKA, RapidMiner Studio, and Python. The dataset for constructing the models are gathered directly from students via the questionnaire data collection method. Initially, data was collected from 3,620 students. After preprocessing, the dataset was reduced to 3,001 participants, comprising 916 females and 2,085 males. The key stages of data preprocessing applied in this study include data cleaning, data reduction, and data transformation. Subsequently, the dataset was divided, allocating 80% for training purposes and 20% for testing. The study adopts an experimental research methodology, constructing a model with chosen machine-learning algorithms and tools. It is developed on a specific training dataset and evaluated based on precision, recall, and accuracy metrics. The experimental results indicate that the random forest algorithm, implemented using Python programming tools, achieved promising outcomes with an accuracy of 95.00%, precision of 95.03%, and recall of 95.01%. The findings of this study are promising and could potentially act as a springboard for additional investigation within this area of research. The study identified a clear link between academic ranking and various factors such as socio-demographic characteristics, economic background, and educational practices. These factors encompass the student's place of origin (be it urban, rural, or emerging regions), family background (including parents' education and economic standing), previous academic performance, time allocated for studying, materials used for examination preparation, and hours spent with peers. This research utilized exclusively student data gathered from Haramaya University. Therefore, it is recommended that future researchers strive to develop a generic model by collecting data from a diverse range of Ethiopian universities. 110 Mon, 01 Apr 2024 00:00:00 GMT http://ir.haramaya.edu.et//hru/handle/123456789/8014 2024-04-01T00:00:00Z http://ir.haramaya.edu.et//hru/handle/123456789/7931 USE OF CLASSIFICATION MODEL WITH ONTOLOGY TO DEVELOP MEDICAL KNOWLEDGE BASED SYSTEM FOR BREAST CANCER DIAGNOSIS AND TREATMENT RECOMMENDATION Wabi Jifara Gebisa; Dr. Million Meshesha; Mr.Tariku Mohammed Among the various types of cancer diseases, breast cancer is the first-ranked cause of death in Ethiopia. Considering this, the researcher attempts to use a classification model with ontology to develop a medical knowledge-based system for breast cancer diagnosis and treatment recommendation. To conduct this study, the researcher used an ontology-based design science research methodology. Ontology was developed to share and re-use the knowledge of domain experts. The use of ontologies in the medical domain has gained wider acceptance in recent years and has been accompanied by great success, which motivated this study to create ontologies for the diagnosis of breast cancer that serve as a knowledge base. In this study, the researcher used classification algorithms such as the J48 decision tree, decision tables, and JRIP to extract rules from the breast cancer dataset and selected J48, which performed well, and transformed the extracted rules to SWRL that infer new knowledge from domain ontology for representing the knowledge needed to diagnose breast cancer to its stages. Ontology uses DT rules, SWRL rules, and the Drool inference engine to classify breast cancer stages. The Protégé tool that supports OWL representation is used to build concepts and relationships in an ontology for knowledge representation. The constructed ontology is used for knowledge structuring and representation in the form of hierarchy, and a top-down approach is used to express domain knowledge. Similarly, the medical knowledge-based system is developed based on the rules extracted from the breast cancer dataset using a classification algorithm and later mapped to SWRLs to construct an ontology model. The proposed prototype analyzes the symptoms of the patients and gives the exact stages of breast cancer and the appropriate recommended treatments. Finally, the system performance testing is done by using test queries, which achieved an accuracy of 98.67%, precision of 96%, recall of 100%, specificity of 98.94% and F-measure score of 98%. Likewise, user acceptance testing also takes place and achieves 93.8% user acceptance. This indicates that the developed prototype is promising to come up with an applicable system. To enhance the performance of the prototype, there is a need to use an image-based breast cancer dataset and apply deep learning algorithms, machine learning, and hybrid techniques to increase the accuracy of the model. 112p. Sat, 01 Jun 2024 00:00:00 GMT http://ir.haramaya.edu.et//hru/handle/123456789/7931 2024-06-01T00:00:00Z