Delhi House
Price Prediction
Project Overview
The "Delhi House Price Prediction" project focuses on predicting the prices of houses in various localities of Delhi. The primary objective is to develop a predictive model that can accurately estimate the prices of houses based on several key features present in the dataset. The dataset, obtained from Kaggle, contains information on factors such as house area, number of bedrooms, locality, and more. By analyzing these features, the project aims to provide valuable insights for potential buyers and sellers in the real estate market.
Data Dictionary
The project utilizes a dataset with 1259 rows and 11 columns, each representing different attributes related to houses in Delhi. Here is a brief overview of the columns:
Data Dictionary
| Column Name | Description |
|---|---|
| Area | Area of the house in square feet |
| BHK | Number of bedrooms |
| Bathroom | Number of bathrooms |
| Furnishing | Furnishing status |
| Locality | Locality of the house |
| Parking | Number of parking available |
| Price | Price of the house in INR |
| Status | property's status as in 'ready to move' or still under construction |
| Transaction | Its a new property or being re-sold |
| Type | Type of the property |
| Per_Sqft | Price per square feet |
Impact
The project's impact is twofold. Firstly, it addresses the need for accurate house price prediction in the dynamic real estate market of Delhi. Potential buyers can utilize the model's predictions to make informed decisions when purchasing a house. Sellers, on the other hand, can gain insights into fair pricing strategies for their properties.
Secondly, through exploratory data analysis (EDA), significant insights have been uncovered. The analysis revealed that house prices are influenced by factors such as the area, number of bedrooms, and locality. Localities like Punjabi Bagh, Lajpat Nagar, and Vasant Kunj stand out as high-end areas with elevated property prices. The preference for new builder floor properties indicates a demand for customization and independence among buyers.
In terms of machine learning, the project employed regression models such as Decision Tree Regressor and Random Forest Regressor. The Random Forest Regressor outperformed the Decision Tree Regressor, achieving an impressive accuracy of 84.98%.
In conclusion, the "Delhi House Price Prediction" project provides valuable insights into the dynamic real estate market of Delhi, offering both buyers and sellers a reliable tool for estimating house prices. The project's utilization of regression models underscores its commitment to accuracy and effectiveness in predicting house prices, contributing to informed decision-making in the real estate domain.
View Notebook Download Dataset