- Projects 2
- Followers 2
Siddharth KM
Karnataka
Bengaluru House Price Prediction
Bengaluru House Prediction is an ML model with a user-friendly Flask interface built using Intel One API. It predicts home prices using pandas, scikit-learn, and matplotlib. The project benefits homebuyers, agents, and developers, demonstrating data science's power. ...learn more
Project status: Under Development
oneAPI, Artificial Intelligence, Cloud
Intel Technologies
DevCloud,
oneAPI,
Intel Opt ML/DL Framework,
Intel Python,
Intel CPU
Overview / Usage
The Bengaluru House Prediction project is a machine learning-based solution designed to help potential homebuyers in Bangalore predict home prices accurately. It addresses a common problem faced by homebuyers who struggle to make informed decisions due to the complexity of factors that influence property prices.
The project follows a robust data science process to develop a highly accurate and efficient machine learning model that can handle large datasets and deliver precise predictions. The user interface is sleek and intuitive, allowing users to input the necessary features and receive an instant price prediction.
The project can be used in production by potential homebuyers, real estate agents, and property developers to estimate property prices, negotiate better deals, and make informed decisions. The project also demonstrates the power of data science in solving real-world problems and provides a robust framework for developing similar machine-learning applications.
Overall, the Bengaluru House Prediction project is a valuable tool that empowers users with the right information to make informed decisions and demonstrates the potential of machine learning in the real estate industry.
Methodology / Approach
Our methodology for solving the problem of predicting home prices accurately in Bangalore involves leveraging the power of data and advanced machine learning techniques. The project follows a robust data science process, including data loading and cleaning, outlier detection and removal, feature engineering, dimensionality reduction, and hyperparameter tuning using GridSearchCV and k-fold cross-validation.
We have used Python as the primary programming language for developing the machine learning models, along with Intel One Api and Intel oneDAL libraries for optimized performance. The models built and trained were Linear Regression, Lasso, Decision Tree with the highest accuracy being the Linear Regression model. Therefore, the linear regression model has been selected as the final model for prediction.
Additionally, we have used several other standard libraries such as pandas, numpy, flask, request, and matplotlib.
To make the project more user-friendly, we have developed a sleek and intuitive user interface using HTML, CSS, and JavaScript. The user interface allows users to input the necessary features and receive an instant price prediction.
Furthermore, we have used a Flask server to consume the trained machine learning model and expose HTTP endpoints for various requests, enabling seamless integration with other applications and systems. We have also used a pickle file to store the trained model, making it easy to deploy and use in various environments.
Overall, our methodology involves using advanced machine learning techniques, optimized libraries, and a user-friendly interface to develop a robust and efficient solution for predicting home prices accurately in Bangalore. Our approach demonstrates the power of data science in solving real-world problems and provides a framework for developing similar machine-learning applications.
Technologies Used
Technologies, libraries, tools, and Intel technologies used in the development of Bengaluru House Prediction project are as follows:
- Python - Primary programming language used for developing the machine learning model.
- Intel One API - Used for optimized performance of the model.
- Intel oneDAL - Used for optimized data analysis and machine learning.
- Scikit-learn - Used for training and building the models.
- Pandas - Used for data manipulation and analysis.
- Numpy - Used for scientific computing.
- Flask - Used for building web applications and API.
- Matplotlib - Used for data visualization.
- HTML, CSS, and JavaScript - Used for developing the user interface.
- GridSearchCV - Used for hyperparameter tuning.
- K-fold cross-validation - Used for model validation.
- Pickle - Used for storing the trained machine learning model.
Documents and Presentations
Repository
https://github.com/aaronDev28/Bangalore_House_Price_Prediction_oneAPI