Table of Content

Abstract

Buying a home, especially in a city like Bengaluru, is a tricky choice. While the major factors are usually the same for all metros, there are others to be considered for the Silicon Valley of India. With its help millennial crowd, vibrant culture, great climate, and a slew of job opportunities, it is difficult to ascertain the price of a house in Bengaluru.

By cleaning and analyzing the Bangalore home dataset, we will be able to understand how house prices are affected by various factors, and then apply machine learning regression to establish an approximate price for the properties. In this work, I presented a study approach that utilizes a variety of methods (Logistic Regression, K-Folds, and DNN) to predict the houses price, and the deep learning model agreed on the others with an accuracy of 91.2 %.

Tools

• Python 3.
• Pandas Library.
• NumPy Library.
• Matplotlib Library.
• Sklearn Library.
• Keras APIs.
• Local Jupter Notebook.
• Microsoft Word and power point.

Prject Stages

Data Cleaning Processes

Conclusion

More Resources

• For more details see the project repository on github.

• Dispaly the project report from here

• Dispaly the project presentation from here

• Dispaly the project notebook from here