Real-time collaboration for Jupyter Notebooks, Linux Terminals, LaTeX, VS Code, R IDE, and more,
all in one place. Commercial Alternative to JupyterHub.

Machine Learning with Python - The Best Classifier

📄 Summary

This project involved completing a notebook to build a classifier that predicts whether a loan case will be paid off or not.

📝Method

A historical dataset from previous loan applications is loaded, the data is cleaned, and then split into a testing dataset and a training dataset. Tthe following classification algorithms are trained using the training data, and the corresponding ski-kit learn libraries:

• k-Nearest Neighbour

• Decision Tree

• Support Vector Machine

• Logistic Regression

The results are reported as the accuracy of each classifier, using the following metrics:

• Jaccard index

• F1-score

• LogLoss (for logistic regression)