Volume 9, Issue 10, October– 2024 International Journal of Innovative Science and Research Technology

ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24OCT1873

House Price Pridiction

Using Machine Learning
Dev Mulchandani1 Swati Shamkuwar 2
UG Student Professor
Department of Information Technology Department of Information Technology
G H Raisoni College of Engineering Nagpur G H Raisoni College of Engineering Nagpur

Abstract:- This project provides us an overview on how II. LITERATURE SURVEY

to predict house prices using various machine learning
models with the help of different python libraries. This Home prices reflect current market conditions and are
proposed model considers as the most accurate model a concern for buyers and sellers. Location also plays a role
used for calculating the house price and provides a most for many reasons. Manually estimating home prices is a
accurate prediction. This provides a brief introduction difficult task and is often inaccurate, so many machines
which will be needed to predict the house price. This have been developed to predict home prices. Sifei Lu,
project consists of what and how the house price model Zengxiang Li, Zheng Qing, Xulei Yang, Rick Siow Mong
works with the assistance of machine learning technique Goh proposed a high-level real estate estimate using
using scikit-learn and which datasets we will be using in horizontal lines. can give us a good estimate of home prices
our proposed model. Predicting the price of a house based on other variables. They used linear regression on
helps for determine the selling price of the house in a Ames dataset, so its accuracy is high. Project estimation
particular region and it help people to find the correct house price has two modules, admin and user. Admins can
time to buy a home. In this task on House Price add locations and view locations. Admins have the right to
Prediction using machine learning, our task is to use increase speed according to the area of the room. Users can
data to create a machine learning model to predict house search for locations and see estimated house prices for that
prices in the given region. We will implement a linear location. Home prices reflect current market conditions and
regression algorithm on our dataset. By using real world are a concern for buyers and sellers. There are many factors
data entities, we are going to predict the price of the that affect the price of a home, such as the number of
house in that area. For better results we require data bedrooms and bathrooms, and the price of a home also
pre-processing units to improve the efficiency of the varies depending on its location. Manually predicting home
model. for this project we are using supervised learning, prices is difficult and often not very good.
which is a part of machine learning. We have to go
through different attributes of the dataset Therefore, many systems have been developed to
estimate housing prices. In this research, these elements are
I. INTRODUCTION divided into three main categories: existing status, idea and
original. Our property is limited by the human dimensions
In recent years, the real estate market has witnessed of the house, such as the size of the house, the number of
unprecedented fluctuations, driving both excitement and rooms, the kitchen and parking space, the openness of the
apprehension among buyers, sellers, and investors alike. children's playground, the area of the land and buildings.
Amidst this dynamic landscape, the ability to accurately The age of the building and the idea are the ideas that
predict house prices has emerged as a pivotal tool for architects put forward to attract buyers, such as the
informed decision-making and strazegic planning within the possibility of a small house, sustainable and green products
housing sector. Recognizing the complexities inherent in and good conditions. The location of the house has a great
price determination, researchers and practitioners have turned impact on its value. This is because the park chooses
to advanced computational methods, particularly machine standard land prices. The district also selected important
learning, to unravel the intricate patterns underlying housing streets where businesses such as schools, parks, crisis
market dynamics. centers, and welfare centers are located, as well as family
businesses such as shopping malls, gourmet tours, or nicer
This research paper endeavors to contribute to the places. Accuracy of home price predictions. Fairfax County
burgeoning literature on house price prediction by offering a urban housing data was analyzed and the classification
comprehensive analysis of state-of-the-art machine learning accuracy of various algorithms was compared. Then, a
techniques in this domain. By leveraging rich datasets better prediction model was developed to help real estate
comprising diverse features such as location, property agents by supporting decision making based on home value
characteristics, economic indicators, and demographic assessment.
information, we aim to develop robust models capable of
forecasting house prices with a high degree of accuracy.

IJISRT24OCT1873 www.ijisrt.com 2192

Volume 9, Issue 10, October– 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24OCT1873

 Proposed System  Model Evaluation:

The performance of each model is assessed by
 The proposed approach involves a comprehensive evaluating appropriate parameters such as mean error
methodology, including: (MAE), mean square error (MSE), root mean square error
 Data collection and preprocessing for creating a clean (RMSE) and coefficient of determination (R-squared). Or
and standardized dataset. the process of cross-checking different models to determine
 Feature engineering to enhance the model's predictive the best way to predict house prices.
capabilities.
 Evaluation and selection of regression algorithms  Interpretability and Validation:
through rigorous testing. Interpret the results of training models using
 Incorporation of interpretability features for user trust techniques such as factor analysis, partial dependency plots,
and understanding. and nonlinear interpretation models such as SHAPley
 Development of a user-friendly interface for model Contribution Explanations to understand that it does not
integration. affect the price of the house. Non-standard data or real-
 Continuous monitoring and updating mechanisms for world testing to ensure it is reliable and usable in real-world
applications. Evaluation of results to promote innovation
model adaptation.
and transparency.
III. METHODOLOGY

 Data Collection:
Gather comprehensive information that includes a
variety of characteristics relevant to your home value
estimate, including property characteristics (For example
size , age , number of bedrooms/bathrooms) , location (For
example , neighborhood , proximity to amenities) ,
economic measures (e.g., interest rates, unemployment rate),
demographics (e.g., census rate, median income), and
historical sales data. complete and consistent.

 Data Preprocessing:
Cleanse data using techniques such as imputation,
outlier detection, and data validation to resolve missing
values, outliers, and inconsistencies. Input categorical
variables using methods such as single-bit encoding or label
encoding to convert them into numerical representations
suitable for modeling.

 Feature Engineering:
Conduct exploratory data analysis (EDA) to gain
insight into the distribution and relationship between
different features.

Create new features by combining, transforming, or

extracting data from existing variables to capture
relationships and patterns in the data.

Includes empirical information and expert opinions to

develop factors that are good predictors of home prices,
such as neighborhood characteristics, housing market
conditions, and employment.

 Model Development:
Experiment with various machine learning algorithms,
including transformation models (for example , linear
regression, ridge regression, lasso regression), tree methods
(for example , decision tree, random forest, gradient
boosting) , support vector machines (SVM), and neural
networks. To train and evaluate the performance of different
models, split the dataset into training set, validation set, and
test set as appropriate
Fig 1 Interpretability and Validation

IJISRT24OCT1873 www.ijisrt.com 2193

Volume 9, Issue 10, October– 2024 International Journal of Innovative Science and Research Technology
ISSN No:-2456-2165 https://doi.org/10.38124/ijisrt/IJISRT24OCT1873

IV. CONCLUSION [9]. Comprehensive Analysis of Housing Price Prediction

in Pune Using Multi-Featured Random Forest
Through empirical analysis and comparative studies, Approach, Rushab Sawant ; Yashwant Jangid ;
we have demonstrated the effectiveness of various Tushar Tiwari ; Saurabh Jain ; Ankita Gupta, 2018
algorithms in accurately forecasting house prices, Fourth International Conference on Computing
emphasizing the importance of robust feature selection, Communication Control and Automation
model optimization, and interpretability. Our findings (ICCUBEA)
underscore the interdisciplinary nature of house price [10]. Time-Aware Latent Hierarchical Model for
prediction, highlighting the need for collaboration between Predicting House Prices, Fei Tan ; Chaoran Cheng ;
data scientists, domain experts, policymakers, and industry Zhi Wei, 2017 IEEE International Conference on
practitioners to inform evidence-based decision-making and Data Mining (ICDM)
drive sustainable development in the housing sector.
Looking forward, future research directions may focus on
refining model interpretability techniques, addressing data
quality challenges, and integrating alternative data sources
to further advance our understanding and predictive
capabilities in the dynamic real estate market landscape.

REFERENCES

[1]. Housing Price Prediction Using Machine Learning

Algorithms: The Case of Melbourne City, Australia,
The Danh Phan, 2018 International Conference on
Machine Learning and Data Engineering (iCMLDE)
[2]. Predicting Sales Prices of the Houses Using
Regression Methods of Machine Learning, Parasich
Andrey Viktorovich ; Parasich Viktor
Aleksandrovich ; Kaftannikov Igor Leopoldovich ;
Parasich Irina Vasilevna, 2018 3rd Russian-Pacific
Conference on Computer Technology and
Applications (RPC)
[3]. Real Estate Value Prediction Using Linear
Regression, Nehal NGhosalkar ; Sudhir N Dhage,
2018 Fourth International Conference on Computing
Communication Control and Automation
(ICCUBEA)
[4]. Predicting Housing Market Trends Using Twitter
Data, Marlon Velthorst ; Cicek Güven, 2019 6th
Swiss Conference on Data Science (SDS)
[5]. House Price Prediction Using Machine Learning and
Neural Networks, Ayush Varma ; Abhijit Sarma ;
Sagar Doshi ; Rohini Nair, 2018 Second International
Conference on Inventive Communication and
Computational Technologies (ICICCT)
[6]. Forecasting house price index of China using
dendritic neuron model, Ying Yu ; Shuangbao Song ;
Tianle Zhou ; Hanaki Yachi ; Shangce Gao, 2016
International Conference on Progress in Informatics
and Computing (PIC) 41
[7]. Prediction of real estate price variation based on
economic parameters, Li Li ; Kai-Hsuan Chu, 2017
International Conference on Applied System
Innovation (ICASI)
[8]. Predicting house sale price using fuzzy logic,
Artificial Neural Network and K-Nearest Neighbor,
Muhammad Fahmi Mukhlishin ; Ragil Saputra ; Adi
Wibowo, 2017 1st International Conference on
Informatics and Computational Sciences (ICICoS)

IJISRT24OCT1873 www.ijisrt.com 2194