House price prediction Using hybrid

regression technique
Abhinav Thapliyal , Samarth Agrawal , Suraj Belwal
Department of Computer Science and Software Engineering

Sharda University, Greater Noida, INDIA

ABStract
House price index represent the summarized price changes of residential housing with some parameters
such as location, house type, size, local amenities and many other factors. House prices increases every year
that eventually forced the need of strategy that could predict house prices. This helps people in selecting a
house that is best fit for their living. A significant amount of expertise and market awareness is required for
making accurate price prediction of houses so that the user get into a profitable investment. The price of the
flats in the city is increasing and there is so much of risk to predict the price of the house to a good accuracy.
Property is one of our ecosystem’s lowest quantum transparent diligences. The major goal of this
investigation is to predict house prices using real time factors. In this research paper, we have used Machine
Learning technique i.e. Linear Regression. The motive of this paper is to help the buyer to estimate the cost
of a house perfectly. Our research paper will help the client to know the actual price of the house and it will
also help all the builders to know about the selling prices that will well fit their client’s needs. Compared
with other methods and projects, our work can obtain a better performance through experiments using
actual data of properties.

Keywords – Machine Learning, Regression, House price prediction, Feature Engineering, Linear Regression

Introduction
House Price Prediction refers to a concept of evaluating property prices by using various techniques. It is a
critical area of research in finance and economics. It serves as a first-hand assistant for people in purchase or
sale of their properties. Despite having a large number of increase property demands there is no appropriate
mechanism that could predict house prices in future. Machine Learning develops algorithms and builds models
from data, and uses them to predict on new data. However, machine learning algorithms have been shown to
reliably predict house prices and make predictions.

With the great advances in the use of Artificial Intelligence and Machine Learning algorithms, the worldwide
real estate market began to discover how to benefit from these techniques to analyse the vast data collected
from real estate transactions to predict housing prices. Real estate price plays a crucial role for buyers, sellers,
real estate agents and investors. Real estate price prediction can contribute to evaluating the economic and
social worth of real estate.[4] The main difference with traditional algorithm is that a model is built from inputs
data rather than just execute series of instructions.

Machine Learning has been used for image recognition, spam reorganization, medical diagnosis for more than
a decade. Machine Learning based predictions achieve better results when put in practice. Almost every
economic domain now benefits from machine learning prediction models.[6] In this research paper, House
Price Prediction has been performed using machine learning technique named “REGRESSION”. It is a method
for understanding the relationship between independent variables or features and a dependent variable or
outcome. Regression models will be trained to understand the relationship between different independent
variables and an outcome. The model can therefore understand the many different factors which may lead to a
desired outcome. The model will be trained on labelled data set to understand the relationship so that they can
predict the outcome of new and unseen data. Supervised machine learning models are generally used for this
purpose.[8] After examining data, we find that the data quality is a key factor to predict the house prices. Data
input feature density estimation is important for regression.

The performance of a machine learning model will be critical in providing users with the price range from
which they will benefit the most. As a result, those searching to buy or sell a home will face fewer challenges,
and the volatile market will remain stable [2]. Due to the present challenges being faced now, a home system
equipped with artificial intelligence and autonomous processing capabilities would help in developing a web
software, which allows both buyers and retailers to publish house details that are available for sale , purchasing
and even employing.

Literature

Methodology
In this project, we collected data from people of different living status. Using the data set, we perform training
using different machine learning algorithms and some set of data for testing.

A. Dataset Creation
The dataset in general means the collection of data, used for analytic and prediction purposes. Datasets can
hold any type of record that is stored in the system. For Machine Learning projects, a large amount of data is
required because without data AI models cannot be trained. An ideal dataset has either well labeled fields and
members or a data dictionary that can be used to relabel the data. A good dataset has completeness, they are
reliable and have great accuracy, correct relevance and timeliness. Dataset can also be referred to as a
container for storing data.

B. Data Preprocessing
Data preprocessing is a process of converting the source or atomic data into structured or understandable
data. It is a very predominant step in the Machine Learning process because only when the data is
understandable, the model can be trained. When the dataset is preprocessed, it makes it easier to interpret
the data and is simple to use. Preprocessing techniques are applied so that the data gives high quality results.

C. Training the model

Here the data is broken into 2 parts. That is training and testing. 80 percent of data is used for training the
model and the rest 20 percent is used for te0sting purposes. Training the model is mainly training the dataset
with Machine Learning algorithms.

D. Testing the model

Once the model is trained, they are tested with the dataset. The model provides the prediction accuracy or the
output for the processed data-set. It is a method to measure the results of the model that gives the accurate
score of the dataset. That is, validation/test is done for the model build. Test data sets are used to evaluate
machine learning programs that have been trained on an initial training data set.
In this proposed model, various machine learning algorithms are used. The model is trained on Linear
Regression. The following libraries are imported for working with Machine Learning. They are pandas, NumPy,
matplotlib.pyplot, and sklearn libraries.

Linear Regression
Linear regression is the most basic and most commonly used method in machine learning. It is very easy to
implement. It is evident from its name that Linear Regression represents a linear relationship between a input
variable and an output variable as can see in Fig.

References
[1] Shailendra Sharma, Gori Shankar, Deepti Arora, Priyanka Sharma, Vihaan Motwani
Student, Shiv Nadar School, Gurgaon, India, IEEE

[2] CH.Raga Madhuri, Anuradha G, M.Vani Pujitha, Assistant Professor, Associate

Professor, Department of CSE, VRSEC, Vijayawada, IEEE

[3] Rupam Dwivedi, Rishabh Gupta, Prashant Kumar Pal , School of Computing Science
and Engineering, Galgotias University, Greater Noida, India, IEEE

[4] Talal Alshammari Information and Computer Science Department, College of Computer Science
and Engineering University of Ha’il, Ha’il 81481, Saudi Arabia, IEEE

[5] Sifei Lu, Zengxiang Li, Zheng Qin, Xulei Yang, Rick Siow Mong Goh Institute of High Performance
Computing (IHPC), Agency for Science Technology and Research (A*STAR), Singapore, IEEE

[6] Maida Ahtesham, Narmeen Zakaria Bawany, Kiran Fatima Research Center for Computing,
Department of Computer Science and Software Engineering, Jinnah University for Women, Karachi,
Pakistan, IEEE
[7] Akhilendra Pratap Singh, Kartikey Rastogi, Shashank Rajpoot, Computer Science, Galgotias
University, Greater Noida, India, IEEE

[8] Amit Gupta, Shashi Kant Dargar, Abha Dargar, Department of E&C Engineering, Kalasalingam
Academy of Research and Education, Virudhunagar, Tamil Nadu, India, IEEE

[9] Yong Piao, Ansheng Chen- School of Software Dalian University of Technology Dalian, China,
Zhendong Shang Land Resources and Housing Information Centre ,Dalian, China, IEEE

[10] Chen Chee Kin, Zailan Arabee Bin Abdul Salam, Kadhar Batcha Nowshath, Asia Pacific University
of Technology & Innovation (APU), IEEE