House-Price-Prediction-Website

Architecture of the DSS system

Process of developing the Project

• Build the ML Model using libraries like sklearn and store the model trained on the dataset as a pickle file to access it later.
• Make a Flask API by importing the previously made pickle file to communicate with the website backend (NodeJS).
• Design the website frontend using online tools like Figma and implement this in code using ReactJS, HTML, and CSS.
• Build the backend with the Routes and integrate it with the Frontend and the Flask app.
• Host the ML model (I used PythonAnywhere), host the NodeJS backend and ReactJS frontend (I used Render).

Results

Decision Tree has the best score of 0.9991662239204835

Tech stack

• Frontend- ReactJS, HTML, CSS, Bootstrap
• Backend- NodeJS, ExpressJS, Flask
• ML Model- Sklearn
• Visualization- Looker Studio
• Hosting- PythonAnywhere, Render