Real Estate Price Prediction

Project overview

Predictive Analytics in Machine learning uses regression models that help companies to forecast trends and predict outcomes. These models are usually trained on a tabular dataset consisting of categorical and numerical features which help to explore the relationship of different attributes with the outcome. The regression models are developed using statistics and are easy to understand. An essential application of the regression model is in the financial domain for commodity price prediction and forecasting using time-series data.

The score of our Multiple Linear Regression was around 69%, so this model had room for improvement. Then we changed our approach and used Keras Regression model. We got an accuracy of ~81% and also, noticed that RMSE (loss function) is lower for Keras Regression model which shows that our prediction is closer to actual rating price.

‍

What we did

• Analysis and Imputation of missing values.
• One-Hot Encoding of Categorical Features.
• Exploratory Data Analysis(EDA) & Outliers Detection.
• Keras-Regression Modelling along with hyper-parameter tuning.
• Training the Model along with EarlyStopping Callback.
• Prediction and Evaluation
• Create a software solution and integrate with existing client technology stack.