Comment
Author: Admin | 2025-04-27
POD) , Term Loans (TL), Bank Guarantee (BG)) Page 1-12 © MANTECH PUBLICATIONS 2022. All Rights Reserved Journal of Research in Computer Science and Engineering Volume 7 Issue 1 Online ISSN- 2457-0818 Legal Status - Status of loan borrower (Individual, Partnership, Proprietorship, Private limited) Business Registration - Whether business is registered or not Business Age - Duration of business survival Business Sector - Retail, Wholesale business PPG Rating - Product Process Guideline Rate [ > 80 – 1, > 60 – 2, – 3] CRIB - Credit Information Bureau whether Regular or Irregular NDB Exposure All Bank Exposure FOIR / DSCR / Interest Cover - Fixed Obligation Income Ratio (FOIR) and Debt Service Coverage Ratio (DSCR) Class variable: Perform/Not Perform - Represent whether loan is approved or not 4. Model Creation In the model development step, suitable Machine Learning algorithms are selected according to the requirement and the models are developed using Data Mining tools (Nantasenamat, 2020). In this research study, the four Data Mining algorithms are used including Decision Tree, Naive Bayes, Random Forest and K-Nearest Neighbour to develop the prediction model. Rapid Miner Data Mining tool has been used to implement models. Data set was divided into two parts called training data set and testing data set and training dataset was used to train the Machine Learning model. 5. Model Testing Model evaluation is a core step of machine learning model development. Different evaluation metrics can be used to evaluate the model and the best model is selected according to the evaluation results. In this study, Cross validation, split validation and confusion matrix techniques were used to evaluate the model. Accuracy, recall, precision and F1-Score measures were used to measure the performance of the Machine Learning model. RESULTS
Add Comment