https://github.com/keshav434/loan-application-data-analysis

Data Analysis and visualization project involing bias detection and building predictive models using Python.
https://github.com/keshav434/loan-application-data-analysis

data-analytics data-visualization python

Last synced: 3 days ago
JSON representation

Data Analysis and visualization project involing bias detection and building predictive models using Python.

• Host: GitHub
• URL: https://github.com/keshav434/loan-application-data-analysis
• Owner: keshav434
• Created: 2024-07-19T10:29:08.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2024-08-18T18:41:15.000Z (3 months ago)
• Last Synced: 2024-08-18T19:53:56.635Z (3 months ago)
• Topics: data-analytics, data-visualization, python
• Language: Jupyter Notebook
• Homepage:
• Size: 864 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
Project Info:

Rahuri Finance requires building an AI model to predict the "Loan Payment Failure" tendency (a binary classification problem) for a given loan application. Additionally, we need to identify any bias towards specific attributes.

Project Steps:

(a) Preprocessing:

Detail the preprocessing steps, including handling missing values, plotting graphs, data discretization, normalization, and data encoding.

(b) Initial Data Exploration:

Utilize techniques like association rule mining and clustering for initial data exploration to identify potential biases. Report any findings.

(c) Building the Classification Model:

Explore various classification techniques (e.g., Decision Trees, Neural Networks, Naïve Bayes, SVM, and Ensemble methods).

Evaluate training and validation errors to determine model suitability.

Use cross-validation for model assessment and perform hyperparameter tuning with tools like GridSearchCV.

Report the final cross-validated accuracies and optimal hyperparameters for each classification model.

Tools and Libraries:

Python Libraries: Pandas, NumPy, Matplotlib, and Scikit-learn.