Loan-Status-Prediction-and-Deployment:

Predicting loan status with a powerful machine learning model and creating an intuitive user interface for informed decision-making

Web Applicaton Link

Overview:

This project centers on the development of an advanced machine learning model for loan status prediction, utilizing 11 key features such as Loan Amount, Applicant Income, and Credit History to enhance prediction accuracy and reliability. Furthermore, we have deployed an intuitive web application to provide users with an accessible and user-friendly interface for accessing loan status predictions.

Tool Used:

• Python (Jupyter Environmnet)

Key Highlights:

Model Development:

• Developed a machine learning model for predicting loan status, addressing a critical business need.

• Comprehensive data cleaning and feature scaling were performed to ensure data quality and model effectiveness.

• Conducted a thorough assessment of three key machine learning algorithms: Logistic regression, Random Forest, and Decision Tree, to determine the most effective model for loan status prediction.

• After a comprehensive evaluation, Logistic regression emerged as the top-performing algorithm with a Accuracy Score of 0.83 and an F1-score of 0.89, solidifying its position as the best choice for this critical business task when compared to Random Forest and Decision Tree.

• Utilized a column transformer to combine all feature engineering steps and create a pipeline for model development.

Model Deployment:

• Deployed the project using Streamlit, providing an interactive and user-friendly interface for users to assess loan status predictions.

Model Evaluation

The model was evaluated using Accuracy Score and F1-score.

• Accuracy Score: 0.83
• F1-score: 0.88

Dataset:

Dataset Link