House Price Prediction Using Machine Learning

SARTHAK DINESH PATIL SHIVSHANKAR WAYAL SHUBHANKAR LOKHANDE

COMPUTER ENGINEERING COMPUTER ENGINEERING COMPUTER ENGINEERING
AJEENKYA DY PATIL, AJEENKYA DY PATIL, AJEENKYA DY PATIL,
UNIVERSITY UNIVERSITY UNIVERSITY

NIRANJAN PAWAR ADITI PATIL MRUNAL GAIKWAD

COMPUTER ENGINEERING COMPUTER ENGINEERING COMPUTER ENGINEERING
AJEENKYA DY PATIL, AJEENKYA DY PATIL, AJEENKYA DY PATIL,
UNIVERSITY UNIVERSITY UNIVERSITY

Abstract —"In today's dynamic real estate market, there The target feature in this proposed model is the price of the
exists a growing need for an efficient house price prediction real estate property and the independent features are: no. of
system. The escalating annual surge in house prices has made it bedrooms, no.of bathrooms, carpet area, built-up area, the
increasingly challenging for individuals to accurately assess the floor, age of the property, zip code, latitude and longitude of
fair market value of a property. This issue is of paramount the property. Other than those of the mentioned features,
importance as it directly impacts the financial decisions of which are generally required for predicting the house prices,
potential homebuyers. For instance, a house that is priced at 30 we have included two other features - air quality and crime
lakhs for a 2 BHK today may become available at a significantly rate. These features provide a valuable contribution towards
reduced price of 24-25 lakhs in just a matter of weeks or months, predicting property prices since the higher values of these
resulting in individuals potentially overpaying for their dream features will lead to a reduction in house prices.
homes.The process of purchasing a house is inherently stressful,
exacerbated by the lack of awareness among buyers regarding Regression is a machine learning apparatus that encourages
the myriad factors that influence house prices. Furthermore, the you to make expectations by taking in – from the current
house-buying process is notoriously time-consuming. measurable information – the connections between your
Consequently, the need for predictive solutions becomes evident. target parameter and a lot of different independent
This paper aims to address this challenge by employing various parameters. As per this definition, a house's cost relies upon
data analytics, regression, and machine learning techniques. By parameters, for example, the number of rooms, living
applying these methodologies to relevant datasets, we intend to region, area, and so forth. On the off chance that we apply
provide prospective homebuyers with accessible tools and counterfeit figuring out how to these parameters, we can
insights that will enable them to make informed decisions and compute house valuations in a given land region
secure their ideal homes at the most favorable prices, all while
avoiding unnecessary brokerage fees
Every single organization in today’s real estate business is
Keywords—Data Analytics, Regression Analysis, Machine operating fruitfully to achieve a competitive edge over
Learning” alternative co mpetitors. There is a need to simplify the
process fo r a normal human being while providing the best
I. INTRODUCTION results. This paper proposes a system that predicts house
House price prediction serves as a valuable tool for prices using a regression machine learning algorithm. In
developers and potential homebuyers alike. It aids case you're going to sell a house, you have to recognize
developers in gauging property values and enables customers what sticker price to put on it. What's more, a PC calculation
to make well-timed decisions. Three key factors, namely can give you a precise gauge!. This regression model is built
physical condition, conceptual appeal, and location, heavily not only for
influence a property's worth. To achieve accurate predictions,
it is imperative to comprehend the processes involved in
handling datasets, encompassing inspection, cleansing,
II. LITERATURE SURVEY
transformation, and modelling. Data analytics techniques 1. House Price Prediction Using Machine Learning and
play a pivotal role in extracting meaningful insights from Neural Networks*: This study leverages machine learning
data, aiding businesses in strategic planning and decision- algorithms and Python programming, including Linear
making. Regression, Boosted Regression, Neural Networks, and
The importance of a user-friendly Graphical User Interface Forest Regression, to achieve accurate house price
(GUI) cannot be overstated, as not everyone possesses predictions. The paper emphasizes the importance of data
visualization for understanding results and hints at the
programming skills. Hence, the development of a web-based
potential for future improvements, such as augmented
GUI system becomes crucial to ensure easy comprehension reality integration.
of housing prices.

XXX-X-XXXX-XXXX-X/XX/$XX.00 ©20XX IEEE

2. House Price Prediction Using Machine Learning*: This large number of missing attributes we drop persons
research employs various algorithms, such as regression and characteristics else substitute them with the typical worth.
gradient boosting, to predict housing prices. Data
visualization aids in conveying results effectively, with the Stage 3: The model's education
mention of XG support for enhancing prediction accuracy.
We should train the model first since the data is separated
3. Modeling House Price Prediction using Regression
into two modules: a Training set and a Test set. The
Analysis and Particle Swarm Optimization*: Linear
objective variable is joined by the readiness set. The layout
regression and particle swarm optimization are applied in
of educational assortment is computed using a decision tree
this study to predict house prices. The paper highlights the
regressor. A backslide model is collected as a tree structure
advantages of these methods and hints at potential future
by the Decision tree.
research avenues to further enhance prediction accuracy.
4. House Price Forecasting using Data Mining*: This Stage 4: Testing and Integrating
research combines linear regression and data mining
techniques for house price prediction. The benefits of data The test dataset is fed into the pre-programmed model, and
cleaning for faster predictions are discussed, with a focus on home expenses are predicted.
optimizing estate choice accuracy.
5. House Price Prediction Using Regression Techniques*:
The study utilizes a neural network and various regression IV. FINAL OUTPUT
techniques, including Gradient Boosting Regression, for
The application's final output includes the prediction of
house price prediction. It acknowledges the time-consuming
nature of the process and suggests continued model updates house prices based on input variables such as area, location,
for improved accuracy. number of bedrooms (BHK), square footage (sqft), and
more. Multiple linear regression is employed to make
6. House Price Prediction Using Diverse Machine Learning predictions, and results are displayed through data
Techniques*: This project explores diverse machine learning visualization, enhancing user understanding.
algorithms, including Extra Tree, Support Vector Machine,
and Naive Bayes, combined using stacking techniques, to
predict house prices.
V. FUTURE SCOPE
III. PROJECT DETAILS House price prediction remains crucial for cost-effective
The project aims to create a web-based application using R decision-making and reduced travel time. The application
and machine learning for predicting house prices based on can be valuable in real estate for booking houses at optimal
historical data. Users can input data from various sources, prices.
and the application will provide price predictions. Data
visualization facilitates easy comprehension of price trends, VI. CONCLUSION
helping users make informed decisions. The web-based application successfully predicts house
prices, providing users with a user-friendly interface and
The project involves loading a dataset from Kaggle,
valuable insights into price fluctuations. The use of GUI
cleaning it, building predictive models using machine
enhances accessibility and usability. FINAL OUTPUT
learning, and using regression techniques for prediction. A
GUI-based system is chosen for its user-friendliness and
broad accessibility
Stage 1: Collection of data REFERENCS
[1] Lakshmi, B.N., and G.H. Raghunandhan."An abstract
Information handling strategies and cycles are various. We overview of data mining."2011 National Conference on
gathered the information for Mumbai's land properties from Inventions in Emerging Technology. IEEE, 2011.
different land sites. The information would have traits, for [2] Manjula, R., etal." Real estate value vaticination using
example, Location, cover region, developed region, age of multivariate retrogression models." Accoutrements Science
the property, postal district, and so forth We should gather and Engineering Conference Series.Vol. 263. No. 4. 2017.
the quantitative information which is organized and ordered. [3] A. Varma etal., “ House Price Prediction Using Machine
Information assortment is required before any sort of AI Learning And Neural Networks,” 2018 Second International
research is completed. Dataset legitimacy is an Conference on Inventive Communication and
unquestionable requirement in any case it is a waste of time Computational Technologies, pp. 1936 – 1939, 1936.
to break down the information. [4] Arietta, SeanM., etal."City forensics Using visual
rudiments to prognosticatenon-visual megacity
Stage 2: Information Preprocessing attributes."IEEE deals on visualization and computer
plates20.12 (2014) 2624-2633.
Data preprocessing is the most well-known approach to [5] Yu, H., andJ. Wu." Real estate price vaticination with
cleaning our instructive file. There might be missing retrogression and bracket CS 229 Afterlife 2016 Project
characteristics or irregularities in the dataset. Data cleansing Final Report 1 – 5." (2016).
can help with these issues. Expecting a variable to have a [6] Li, Li, and Kai-Hsuan Chu." Vaticination of real estate
price variation grounded on profitable parameters."2017
International Conference on Applied System
Identify applicable funding agency here. If none, delete this text box.
Innovation (ICASI). IEEE, 2017.
[7] Nihar Bhagat, Ankit Mohokar, Shreyash Mane" House
Price Soothsaying using Data Mining"International Journal
of Computer Applications,
[8] N.N. Ghosalkar andS.N. Dhage, "Real Estate Value
Prediction Using Linear Retrogression, "2018 Fourth
International Conference on Computing
Communication Control and Robotization (ICCUBEA),
Pune, India, 2018, pp. 1-5.
[9] Pow, Nissan, Emil Janulewicz, and Liu Dave
Liu."Applied Machine Learning Project 4 Vaticination of
real estate property prices in Montréal." Course design,
Presentation-598, Fall/ 2014, McGill University (2014).
[10]
Sampathkumar,V.,Santhi,M.H.,&Vanjinathan,J(2015).Vatici
natingthelandpriceusingstatisticalandneuralnetworksoftware.
ProcediaComputerScience, 57, 112-121.