International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 02 | Feb 2024
p-ISSN: 2395-0072
www.irjet.net
Predicting Pune House Prices: A Machine Learning Approach Levansh Bhan1, Vedant Vispute2 1-2 Mrs Prachi Karale, Department of Computer Engineering, Savitribai Phule Pune University, Pune, MH, India
---------------------------------------------------------------------***--------------------------------------------------------------------process, ensuring a deep understanding of its intricacies. Abstract - We propose the implementation of a machine
To accomplish this, we deliberately selected the Pune Real Estate Prediction task, commonly referred to as a "toy problem." Although not directly aligned with pressing scientific concerns, such problems serve as valuable tools for demonstration and practical application. Our primary objective revolved around developing a robust forecasting model for the price of a specific apartment, incorporating an array of pertinent "features" that would be elucidated in subsequent sections of our research.
learning model for predicting house prices in Pune, India. This model integrates data science and web development techniques, and we have deployed it on Elastic Beanstalk. Our project aims to address the issue of fluctuating and potentially exaggerated housing prices by focusing on genuine factors. We aim to evaluate the pricing based on essential criteria commonly considered in establishing house prices. The primary objective of this project is to gain hands-on experience in Python, data analytics, machine learning, and artificial intelligence, contributing to the advancement of predictive analytics in the real estate domain.
2. Literature Survey Real estate property holds immense significance as it represents not only a person's primary desire but also their wealth and social standing in contemporary society. Investing in real estate is often seen as a lucrative option due to the generally stable nature of property values. Fluctuations in real estate prices impact a wide range of stakeholders, including home investors, bankers, policymakers, and others. Anticipating real estate prices is crucial for economic indicators, considering that the Asian country ranks second globally in terms of the number of households. However, past economic downturns have revealed the unpredictability of real estate costs, which are closely tied to the overall economic conditions of a region. Unfortunately, standardised approaches to accurately forecast real estate property values are lacking.
Key Words: Pune House Price Prediction (PHPP), Pandas, NumPy, Matplotlib, Exploratory Data Analysis (EDA), Data Cleaning, Feature Engineering, Dimensionality Reduction, Data Visualisation, PythonAnywhere, Anaconda, Flask, Scikit-learn.
1. INTRODUCTION 1.1 Context This research project was undertaken with the aim of satisfying our curiosity and gaining practical experience in the field of machine learning. By immersing ourselves in this project, we sought to enhance our knowledge and skills in developing machine-learning models firsthand.
In our research, we conducted an extensive review of articles and discussions on machine learning applications for housing price prediction. One notable publication focuses on house price prediction utilising machine learning and neural networks, aiming for minimal error and maximum accuracy. Another study titled "Hedonic models based on price data from Belfast" explores the identification of submarkets and residential valuation, shedding light on the evaluation process involving the selection of comparable evidence and the quality of variables that influence property values. The article delves into understanding current trends in house prices and homeownership, emphasising the role of feedback mechanisms and social influences in shaping perceptions of real estate as a crucial market investment.
1.2 Motivation Our profound interest in the realm of machine learning has led us to embark on this research project, providing us with a valuable opportunity to delve deeper into this subject and rekindle our passion for it. The immense potential of machine learning in generating predictions, and forecasts, and enabling autonomous learning capabilities is awe-inspiring, offering limitless possibilities across various domains. With its wide-ranging applicability in fields such as finance, medicine, and countless others, we deliberately chose to centre our research idea around the fascinating world of machine learning. 1.3 Objective In our inaugural research endeavour, we aimed to design a project that would provide comprehensive instruction by thoroughly exploring each stage of the machine learning
© 2024, IRJET
|
Impact Factor value: 8.226
|
ISO 9001:2008 Certified Journal
|
Page 277