This Model/WebApp predicts real estate price in Bangalore. Many times we have come across websites like “Magicbricks.com” where they sell and estimate the price of the property in any part of the country, so this model is also inspired by the concept of predicting property prices based on the area, bedrooms, bathrooms and location. Firstly I built the model using sklearn and machine learning algorithm using Bangalore home prices dataset from kaggle.com. The second step was to write a python flask server that uses the saved model to serve HTTP requests. The third component was the website built in HTML, CSS and javascript that allows user to enter home square ft area, bedrooms etc and it will call python flask server to retrieve the predicted price. During model building, I came across all data science concepts such as data load and cleaning, outlier detection and removal, feature engineering, dimensionality reduction, gridsearchcv for hyperparameter tuning, k fold cross validation etc.

Web App - https://bangalore-house-price-predict.herokuapp.com/

Visualizing dataset

Plotting Histogram for Bathrooms per Property

Plotting Property to Price Per Square feet

Data Cleaning

Finding and Removing Outliers

Plotting graph before removing anomalies in Rajaji Nagar location

Plotting graph after removing anomalies in Rajaji Nagar location

Plotting graph before removing anomalies in Hebbal location

Plotting graph after removing anomalies in Hebbal location

Link to GitHub Repository