Colombo House Price Prediction System

The Colombo House Price Prediction System is an end-to-end machine learning–based web application designed to predict residential property prices in the Colombo District, Sri Lanka.

This project demonstrates the complete workflow of a real-world data science system, including data preprocessing, model training, model persistence, and deployment through a web-based user interface.

The system is intended for educational, analytical, and experimental purposes, especially for students and beginners learning applied machine learning.

---

User Interface Preview

Below is the web application interface used to input house details and generate price predictions:

---

Project Objectives

• Build a regression-based machine learning model to predict house prices
• Use real housing data from the Colombo district
• Save trained models for reuse
• Deploy the model using a simple Flask web application
• Allow users to predict house prices by entering property features

---

Dataset Description

The dataset contains residential property listings from the Colombo District.
It includes structured features such as:

• Property size
• Number of bedrooms
• Number of bathrooms
• Location-related attributes
• House price (target variable)

Two dataset versions are provided:

• Raw dataset: Colombo-House-Dataset.csv
• Processed dataset: cleaned_colombo_data.csv

All preprocessing steps are handled before model training.

---

Machine Learning Model

• Algorithm: Regression-based ML model
• Libraries: Scikit-learn, Pandas, NumPy
• Output: Predicted house price

Training Process

1. Load cleaned dataset
2. Perform feature selection and preprocessing
3. Train the regression model
4. Save the trained model and feature metadata

To retrain the model:

python train_model.py

Web Application

The web application is built using Flask and provides a simple, form-based interface that allows users to input house details and receive an estimated price prediction.

Features

• User-friendly input form
• Server-side loading of the trained machine learning model
• Real-time house price prediction
• Clean and minimal user interface

Run the Application

python app.py

After running the application, open your browser and visit: http://127.0.0.1:5000

Installation & Setup

1. Clone the Repository

git clone https://github.com/Pudamya/Colombo_House_Price_Prediction_System.git
cd Colombo_House_Price_Prediction_System

2. Create a Virtual Environment

python -m venv venv

Windows

venv\Scripts\activate

macOS/Linux

source venv/bin/activate

3. Install Dependencies

pip install -r requirements.txt

4. Run the Web Application

python app.py

Use Cases

• Academic coursework and final-year projects
• Learning end-to-end machine learning pipelines
• Demonstrating machine learning model deployment
• Real estate price analysis and experimentation

---

Author

Pudamya
GitHub: https://github.com/Pudamya