© 2022 JETIR April 2022, Volume 9, Issue 4 www.jetir.

org (ISSN-2349-5162)

House Price Prediction

Ammar Anwar, Arbaz Ansari, Siddhesh Ghadigaonkar, Dr. Varsha Shah, Prof. Shiburaj Pappu

Student, Student, Student, Principal, Head of Department

Department of Computer Engineering,

Rizvi College of Engineering, Mumbai, India.

Abstract: Data mining is now commonly used in the real estate market. Real Estate is a clear industry in
our ecosystem. The ability to extract data to extract relevant information from raw data makes it very useful to
predict house prices, important housing features, and much more. Housing prices continue to change from day to
day and are sometimes raised rather than based on calculations. Research has shown that fluctuations in housing
prices often affect homeowners and the housing market. Literature research is done to analyze the relevant factors
and the most effective models for predicting housing prices. The findings of this analysis confirmed the use of
Artificial Neural Network, Support Vector Regression, and Linear Regression as the most efficient models
compared to others. In addition, our findings also suggest that spatial and real estate agents are key factors in
predicting house prices. This study will be of great benefit, especially to housing developers and researchers, to
find the most important criteria for determining housing prices and identify the best machine learning model used
to conduct research in this field.

Keywords: House price prediction, Machine Learning, Linear regression.

1. INTRODUCTION:
In this report, we propose our system “House price prediction”. House is one of human life's most essential
needs, along with other fundamental needs such as food, water, and much more. Demand for houses grew
rapidly over the years as people's living standards improved. House price prediction can be done using
multiple prediction models (Machine Learning Model) such as support vector regression, artificial neural
network, etc. There are many benefits that home buyers, property investors, and housebuilders can reap
from the house-price model. This model will provide a lot of information and knowledge to home buyers,
property investors, and housebuilders, such as the valuation of house prices in the present market, which
will help them determine house prices. The target feature in this proposed model is the price of the real
estate property and the independent features are: no. of bedrooms, carpet area, the floor, car parking, and
lift availability. The whole implementation is done using the python programming language.

JETIR2204579 Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir.org f615
© 2022 JETIR April 2022, Volume 9, Issue 4 www.jetir.org (ISSN-2349-5162)

2. PROBLEM STATEMENT:
The general and standardized real estate characteristics are often listed separately from the asking price
and general description. Because these characteristics are separately listed in a structured way, they can
be easily compared across the whole range of potential houses. Because every house also has its unique
characteristics, such as a particular view or type of sink, house sellers can provide a summary of all the
important features of the house in the description. All given real estate features can be considered by the
potential buyers, but it is nearly impossible to provide an automated comparison of all variables due to
the large diversity. This is also true in the other direction: house sellers have to estimate the value based
on its features in comparison to the current market price of similar houses. The diversity of features
makes it challenging to estimate an adequate market price. Apart from providing a summary of the
important features of the house, the house description is also a means of raising curiosity in the reader,
or in other words persuading the person. Housing prices are an important reflection of the economy, and
housing price ranges are of great interest to both buyers and sellers. In this project, house prices will be predicted
given explanatory variables that cover many aspects of residential houses. The goal of this project is to create a
regression model that can accurately estimate the price of the house given the features.

3. LITERATURE REVIEW:
i. Survey Existing System:
Trends in housing prices indicate the current economic situation and also are a concern to the buyers and
sellers. Many factors have an impact on house prices, such as the number of bedrooms and bathrooms.
House price depends upon its location as well. A house with great accessibility to highways, schools,
malls, and employment opportunities, would have a greater price as compared to a house with no such
accessibility. Predicting house prices manually is a difficult task and generally not very accurate, hence
there are many systems developed for house price prediction. Sifei Lu, Zengxiang Li, Zheng Qin, Xulei
Yang, and Rick Siow Mong Goh had proposed an advanced house prediction system using linear
regression. This system aimed to make a model that can give us a good house price prediction based on
other variables. They used the Linear Regression for Ames dataset and hence it gave good accuracy.

ii. Limitation Existing system or research gap:

In the existing literature, a limited amount of work has been focused on the housing price prediction
model, particularly, to solve the problem using machine learning approaches. A few identified papers
were reported above. In addition, most of the past research considered the housing market problem as a
classification problem to develop a classification model instead of a regression model. Therefore, the
objective of the study is to predict the housing price valuation using machine learning techniques and
considering competitive regression models. An improved ML-based algorithm is proposed, which
includes the predicted target price binning variable as features in the model and improves the model
accuracy significantly. More precisely, the model accuracy is increased by 10 percent compared to other
contemporary machine learning techniques.

4. METHODOLOGY:
The proposed system face recognition-based attendance system can be divided into three main modules.
The modules and their functions are defined as follows.

JETIR2204579 Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir.org f616
© 2022 JETIR April 2022, Volume 9, Issue 4 www.jetir.org (ISSN-2349-5162)

a. Data Collection:
For doing machine learning projects we need a vast amount of data which we have taken
through the Kaggle website. The data consists of several factors in a house of a given
locality such as the number of bedrooms, carpet area, location, etc. The dataset that we
will be using will be batch i.e., static data and not dynamic
b. Train the Dataset and Feature Extraction:
The dataset will further be trained and processed using Linear Regression Algorithm
which will predict the house price accurately. The algorithm used will be a regression
since regression helps to get a value by analyzing a dataset, in this condition the value is
the price of the house.
c. Displaying the output:
The project uses a web application to work with the users and give them accurate price
predictions. The user will input features accordingly which they want on the frontend and
the data will be processed on the backend using Linear Regression and the predicted
output will be shown to the respective user

5. ALGORITHM:
1) Importing the required packages into our python environment
2) Importing the house price data
3) Data Visualization of the house price data
4) Modelling the data using the algorithms
5) Create a responsive website
6) Take inputs from the user and display the analyzed result

6. RESULT AND OUTPUT:

The result of our project has an accuracy of 86.45%, where the user has to enter the location, no. of
bedrooms, lift availability, and car park to get the desired output.

JETIR2204579 Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir.org f617
© 2022 JETIR April 2022, Volume 9, Issue 4 www.jetir.org (ISSN-2349-5162)

Fig 1. Result of a sample location

Tools required: -
1. Python
2. Jyupter Notebook
3. Scikit Learn.
4. NumPy

Conclusion:
This paper examined and analyzed the current research on the significant attributes of house prices and analyzed
the data mining techniques used to predict house prices. The accurate prediction model would allow investors or
house buyers to determine the realistic price of a house as well as the house developers to decide the affordable
house price. This paper discusses an overview of the concept of machine learning and its various applications.
Taking the sample dataset for houses, and considering its various attributes, the prices for houses have been
predicted by employing machine learning methods of regression for predicting the price of the estate using prior
data.

References:
[1] Theobald, O. (2017). Machine learning for absolute beginners
[2] Mueller, J. P., & Massaron, L. (2016). Machine learning for dummies. John Wiley & sons
[3] G. Gao et al., “Location-Centered House Price Prediction: A Multi-Task Learning Approach,”
pp. 1–14, 2019, [Online]. Available: http://arxiv.org/abs/1901.01774.
JETIR2204579 Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir.org f618
© 2022 JETIR April 2022, Volume 9, Issue 4 www.jetir.org (ISSN-2349-5162)

[4] T. D. Phan, “Housing price prediction using machine learning algorithms: The case of Melbourne
city, Australia,” Proc. - Int. Conf. Mach. Learn. Data Eng. made 2018, pp. 8–13, 2019, DOI:
10.1109/iCMLDE.2018.00017.
[5] Park, B., & Bae, J. K. (2015). Using machine learning algorithms for housing price
prediction: The case of Fairfax County, Virginia housing data. Expert Systems with
Applications.
[6] Y. Zhou, “Housing Sale Price Prediction Using Machine Learning Algorithms,” 2020.
[7] T. Mohd, S. Masrom, and N. Johari, “Machine learning housing price prediction in petaling
Jaya, Selangor, Malaysia,” Int. J. Recent Technol. Eng., vol. 8, no. 2 Special Issue 11, pp. 542–
546, 2019, Doi: 10.35940/ijrte. B1084.0982S1119.
[8] A. Varma, A. Sarma, S. Doshi, and R. Nair, “House Price Prediction Using Machine Learning
and Neural Networks,” Proc. Int. Conf. Inven. Commun. Comput. Technol. ICICCT 2018, pp.
1936–1939, 2018, Doi: 10.1109/ICICCT.2018.8473231.
[9] H. Wu et al., “Influence factors and regression model of urban housing prices based on internet
open access data,” Sustain., vol. 10, no. 5, pp. 1–17, 2018, Doi: 10.3390/su10051676.

JETIR2204579 Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir.org f619