1. Abstract

Housing price prediction has become an important application of machine learning in the real estate industry. The price of a house depends on several factors such as location, size of the property, number of rooms, nearby facilities, and infrastructure development. Predicting the correct price of a property helps both buyers and sellers make better decisions.

This project focuses on predicting housing prices in Bangalore city using machine learning techniques and automated machine learning. The dataset used in this project contains information about houses in different localities of Bangalore along with their prices and other relevant attributes.

The system analyzes historical housing data and identifies patterns that influence property prices. Machine learning algorithms are used to build regression models capable of estimating house prices based on various features such as location, area, number of bedrooms, and other housing parameters.

In addition to traditional machine learning models, the project also uses AutoSklearn, an automated machine learning library that automatically selects the best algorithm and optimizes hyperparameters for improved prediction performance.

The project includes several stages such as data analysis, data preprocessing, feature engineering, model building, and automated machine learning implementation.

This project demonstrates how machine learning and AutoML techniques can be applied in the real estate domain to develop intelligent systems capable of predicting property prices accurately.

2. Objectives

The main objectives of this project are:

1. To understand the concept of house price prediction using machine learning.
2. To analyze housing data of Bangalore city and identify important features affecting property prices.
3. To perform data preprocessing and feature engineering on the housing dataset.
4. To build predictive models using machine learning regression algorithms.
5. To apply different regression techniques for housing price prediction.
6. To implement Automated Machine Learning using AutoSklearn.
7. To compare traditional machine learning models with AutoML models.
8. To develop a system capable of predicting housing prices based on property features.

3. Existing System

In traditional systems, property prices are estimated using manual evaluation or simple statistical methods by real estate agents.

However, these systems have several limitations:

1. Manual price estimation may not be accurate.
2. Traditional methods cannot analyze large housing datasets efficiently.
3. Price prediction depends heavily on human judgment.
4. It is difficult to identify hidden patterns in housing data manually.
5. Buyers and sellers may not get accurate property price estimates.

Therefore, machine learning based prediction systems are required to provide more reliable and data-driven housing price estimates.

4. Proposed System

The proposed system uses Machine Learning and Automated Machine Learning techniques to predict housing prices in Bangalore.

In this system:

1. A housing dataset containing different property attributes is used.
2. Data preprocessing techniques are applied to clean and prepare the dataset.
3. Machine learning regression algorithms are trained to predict house prices.
4. AutoSklearn AutoML is used to automatically select the best model and perform hyperparameter tuning.
5. The final model predicts housing prices based on given input parameters such as location, size, and other features.

This system provides a data-driven approach for estimating property prices and can help buyers, sellers, and real estate companies make better decisions.

5. Implementation Procedure

The implementation of this project is carried out in the following steps:

Step 1: Data Collection

1. Collect the Bangalore housing dataset.
2. The dataset contains information about houses located in different areas of Bangalore.
3. It includes attributes such as location, area, number of rooms, and price.

Step 2: Data Analysis

1. Analyze the dataset to understand the relationship between different features and housing prices.
2. Visualize the data using graphs and charts.

Step 3: Data Preprocessing

1. Handle missing values in the dataset.
2. Remove incorrect or inconsistent data entries.
3. Convert categorical data into numerical form using encoding techniques.

Step 4: Feature Engineering

1. Select important features that influence housing prices.
2. Apply techniques such as one-hot encoding and feature scaling.

Step 5: Model Building

1. Train machine learning regression models such as:
2. Linear Regression
3. Decision Tree Regression
4. Random Forest Regression

Step 6: Automated Machine Learning

1. Apply AutoSklearn AutoML to automatically train multiple models.
2. AutoSklearn performs algorithm selection and hyperparameter tuning automatically.

Step 7: Model Evaluation

1. Evaluate the models using metrics such as:
2. Mean Squared Error (MSE)
3. Root Mean Squared Error (RMSE)
4. R² Score

Step 8: Model Comparison

1. Compare traditional machine learning models with AutoML generated models.
2. Select the best performing model for housing price prediction.

6. Software Requirements

The software used in this project includes:

Operating System

1. Windows / Linux / macOS

Programming Language

1. Python 3.x

Development Environment

1. Jupyter Notebook
2. Google Colab
3. VS Code

Libraries and Frameworks

1. AutoSklearn
2. Scikit-learn
3. NumPy
4. Pandas
5. Matplotlib
6. Seaborn

Web Browser

1. Chrome / Firefox

7. Hardware Requirements

The hardware required for this project includes:

1. Processor: Intel i3 / i5 or higher
2. RAM: Minimum 4 GB (8 GB recommended)
3. Storage: Minimum 128 GB free space
4. System: Laptop / Desktop Computer
5. Internet Connection

8. Advantages of the Project

1. Helps predict housing prices accurately using machine learning.
2. Supports better decision making for home buyers and sellers.
3. Uses data-driven analysis instead of manual estimation.
4. Automates model development using AutoSklearn AutoML.
5. Handles large housing datasets efficiently.
6. Helps real estate companies analyze property price trends.
7. Reduces human errors in price estimation.
8. Can be extended into a real estate price prediction web application.