The Fate of the Housing Loan

Inspiration

Our interest in Machine learning and data science inspired us to work on Financial dataset and get meaningful insights from it.

What it does

We have used Fannie Mae's open-source housing market data over a 15-year time period. The project analyzes and visualizes the dataset, in order to derive meaningful insights from it. Apart from data visualization, we have also used different classification methods such as Random Forest classifier, XGBoost and Logistic Regression to predict the status of the loan.

How we built it

Python was the primary language used in this project. We used various Python libraries such as Scikit-learn, Pandas, Numpy, Matplotlib, Seaborn etc.. for data analysis, classification and visualization.

Challenges we ran into

Understanding the housing loan concepts, Finding the relevant features for the classification model, dimensionality reduction and subsetting the dataset using Pandas.

Accomplishments that we're proud of

Data Visualization and successful implementation of different classification models to predict loan status.

What we learned

Basic terms used in housing Loans. Implementation of classification model to predict loan status.

What's next for The Fate of the Housing Loan

Implementation of Neural Networks to predict the status of the loan and more detailed graphs covering every important meaningful information that could be derived from the data.