Machine Learning mini 6thsem. loan elegibity prediction.pptx

Loans are the core business of banks. The main profit comes directly from the loan’s interest. The loan companies grant a loan after an intensive process of verification and validation. However, they still don’t have assurance if the applicant can repay the loan with no difficulties. In our Final Year Project, we built a predictive model to predict if an applicant is eligible for the loan or not. We prepared a model to predict the target variable. And made a User Interface / web application

1. Department of CSE(AI&ML) Academic year: 2023-24 Mini Project (21AIMP67) – Review 1 Presentation GUIDE: Dr. KURSHEED B Lecturer Department of CSE(AI&ML) DBIT, Bengaluru PROJECT TEAM: 1. SIMRAN .S ( 1DB22CI412) 2. VIJAYALAKSHMI.J (1DB22CI414) 3.YESHWANTH.P(1DB22CI415) 4. THANYA.A.J ( 1DB22CI413) LOAN ELIGIBITY

2. 2 SL.NO. TITLE PAGE NO. 1 Introduction 03 2 Problem Statement 05 3 Objectives 06 4 Block diagram 07 5 Software and hardware Requirements 08 6 Planned Code Execution 09 7 Output Tool used for Development 10 8 Conclusion 12 9 Reference 13

3. INTRODUCTION Loans are the core business of banks. The main profit comes directly from the loan’s interest. The loan companies grant a loan after an intensive process of verification and validation. However, they still don’t have assurance if the applicant can repay the loan with no difficulties. In our Final Year Project, we built a predictive model to predict if an applicant is eligible for the loan or not. We prepared a model to predict the target variable. And made a User Interface / web application 3

4. PROBLEM STATEMENT The problem statement regarding loan eligibility typically revolves around determining the specific criteria and requirements that borrowers need to fulfill in order to qualify for a loan from a lender. This includes Intensive time Consumption process of verification and validation. Human errors can be introduced during the validation process. No cross referencing previous loan records Lot of human resource required . Our Machine learning model calculates all the parameters given and predicts if the applicant is eligible for loan or not in very less time Time required for verification, and validation reduces significantly 4

5. RISK MANAGEMENT: Lenders seek to minimize the risk of default by assessing the creditworthiness of borrowers . This involves evaluating factors such as credit history, income stability, debt levels, and employment status. By setting stringent eligibility criteria, lenders aim to approve loans to borrowers who are likely to repay them according to the agreed terms Enhance Detection Accuracy. Reduce False Positives. Adaptability to Evolving Tactics OBJECTIVES 5

6. BLOCK D IAGRAM 6

7. SOFTWARE & HARDWARE REQUIREMENTS

8. Planned Code Execution Data Preprocessing Objective: Prepare dataset for analysis Import data Clean: Remove duplicates, handle missing values Normalize text: Lowercase, feature scaling... Model Training Objective: LOAN ELIGIBITY Select algorithms: Naive Bayes, SVM Train models Tune hyperparameters Model Evaluation Objective: Evaluate model performance Metrics: Accuracy, precision, r2 -score Confusion matrix Deployment 8

9. OUTCOME Data Collection and Preprocessing Data Source: Collected from [specify sources, e.g., kaggle dataset] Preprocessing: Cleaned data by removing duplicates, handled missing values, and normalized text Feature Extraction Techniques Used: CountVectorizer Libraries: Scikit-learn Model Training Algorithms: Trained models using Naive Bayes, SVM, and a Neural Network Hyperparameter Tuning: Performed grid search for optimal parameters Deployment Tools: Deployed model using Flask Platform:Hosted on a local web page using Chrome for free 9

10. TOOL USED FOR DEVELOPMENT 10

11. CONCLUSION & FUTURE SCOPE In conclusion , The system approved or rejects the loan applications. Recovery of loans is a major contributing parameter in the financial statements of a bank. It is very difficult to predict the possibility of payment of loan by the customer. Machine Learning (ML) techniques are very useful in predicting outcomes for large amount of data. In our project, three machine learning algorithms, Logistic Regression (LR), Decision Tree (DT) and Random Forest (RF) are applied to predict the loan approval of customers. The experimental results conclude that the accuracy of Random Forest machine algorithm is better than compared to Logistic Regression and decision tree machine learning approaches 11

12. References / Bibliography [ 1 Al Mamun , M., Farjana , A., & Mamun , M. (2022): Predicting Bank Loan Eligibility Using Machine Learning Models and Comparison Analysis. 7th North American International Conference on Industrial Engineering and Operations Management, Orlando, Florida, USA, June 12-14 . Awodele , O., Alimi , S., Ogunyolu , O., Solanke , O., Iyawe , S., & Adegbie , F. (2022, November). Cascade of Deep Neural Network And Support Vector Machine for Credit Risk Prediction. In 2022 5th Information Technology for Education and Development (ITED) (pp. 1-8). IEEE. Bansal , M., Goyal , A., & Choudhary , A. (2022). A comparative analysis of K-nearest neighbor , genetic, support vector machine, decision tree, and long short term memory algorithms in machine learning. Decision Analytics Journal, 3, 100071 . Gupta, A., Pant, V., Kumar, S., & Bansal, P. K. (2020, December). Bank Loan Prediction System using Machine Learning. In 2020 9th International Conference System Modeling and Advancement in Research Trends (SMART) (pp. 423-426). IEEE. https://jupyter.org/ [Last accessed on 15-06-2023] https://docs.anaconda.com/free/navigator/index.html [Last accessed on 10-05-2023] https://www.kaggle.com/code/vinodkumargr/loan-prediction [Last accessed on 01-05-2023 ] 12