ADINA INSTITUTE OF SCIENCE & TECHNOLOGY SAGAR (M.P.
Department Of Compute Science And Engineering
SESSION : JAN TO JUNE 2025
A MAJOR PROJECT II REPORT
ON
HOUSE PRICE PREDICTION USING MACHINE LEARNING
Submitted in partial fulfillment for the requirement of Bachelor’s Degree in
Computer Science and Engineering
RAJIV GANDHI PRODYOGIKI VISHWAVIDHYALAYA,BHOPAL
(University of Technology in Madhya Pradesh)
Submitted by:-
HARSHRAJ SINGH DANGI (0612CS211024)
Miss.Sadhvi Biltharey Mr.Rajneesh Pachouri Dr. Abhishek Jain
(Project Guide) (H.O.D.) (Principal)
CSE deptt. CSE deptt. A.I.S.T. Sagar
ADINA INSTITUTE OF SCIENCE &TECHNOLOGY SAGAR (M.P.)
Department Of Compute Science And Engineering
SESSION : 2024-25
CERTIFICATE
This is hereby certified that Mr. Harshraj Singh Dangi of Computer Science
& Engg. Department of this college have submitted the project “HOUSE
PRICE PREDICTION USING MACHINE LEARNING” for the partial
fulfillment of his/her Bachelor Degree under the guidance of Miss Sadhvi
Biltharey
We wish all the best for their future.
(Internal Examiner) (External Examiner)
CSE deptt.
ADINA INSTITUTE OF SCIENCE &TECHNOLOGY SAGAR (M.P.)
Department Of Compute Science And Engineering
SESSION : 2024-25
ACKNOWLEDGEMENT
I express my deep sense of gratitude to Mr. Rajneesh Pachouri, Asst Prof. and
Head, Department of Computer Science and Engineering, Adina Institute of
Science and Technology Sagar (M.P), whose kindness valuable guidance and
timely help encouraged me to complete this work.
A special thank to my guide Miss Sadhvi Biltharey who helped me in completing
the minor project by exchanging her interesting ideas, thoughts which made this
work easy and accurate. I am indebted to him for the valuable time he has spared
for me during this work.
I express my thanks to Dr. Sunil Kumar Jain (DIRECTOR) for extending his
support. I am also grateful to Prof.Abhishek Jain (PRINCIPAL), who provided
all the official facilities and guidance to me. I also thank the authors whose works
have been consulted by me during the research.
I would also thank my institution and my faculty members without whom this
project would have been a distant reality.
I take this opportunity to express my regards and obligation to my father and other
family members whose support and encouragement I can never forget in my life.
At last but not the least I want to thank my best friend who appreciated me for my
work and motivated me and finally to god who made all the things possible.
HARSHRAJ SINGH DANGI (0612CS211024)
ADINA INSTITUTE OF SCIENCE &TECHNOLOGY SAGAR (M.P.)
Department Of Compute Science And Engineering
SESSION : 2024-25
DECLARATION
I/We, hereby declare that the work, which is being presented in the Major Project
II Report entitled “HOUSE PRICE PREDICTION USING MACHINE
LEARNING” is my/our own work, carried out under the noble guidance of
my/our guide Miss Sadhvi Biltharey, Department of Computer Science &
Engineering, Adina Institute of Science and Technology, Sagar (M.P.).
The matter embodied in this Project Report work has not been submitted in any
other university for the award of any degree.
HARSHRAJ SINGH DANGI(0612CS211024)
ABSTRACT
The ever-growing complexity and dynamism of the real estate industry make it
challenging to accurately predict property prices. Traditional valuation methods
depend heavily on the experience and intuition of real estate agents, which often
results in inconsistent and subjective assessments. To address this issue, this
project presents a data-driven, machine learning-based solution to accurately
predict house prices using historical property data and modern predictive
algorithms.
The project involves the collection and analysis of real estate data containing key
features such as location, total square footage, number of bedrooms and
bathrooms, year of construction, and additional amenities. The dataset undergoes
extensive preprocessing, including handling missing values, feature encoding,
normalization, and outlier detection to ensure model readiness.
Various regression algorithms—including Linear Regression, Decision Trees,
Random Forest Regressor, and XGBoost—are implemented and evaluated based
on metrics like Mean Absolute Error (MAE), Mean Squared Error (MSE), and R-
squared score (R²). The best-performing model is serialized using Python’s pickle
module and integrated into a web application using the Flask framework.
The Flask-based web interface allows users to enter property attributes through a
clean, responsive front end developed with HTML, CSS, and Bootstrap. Upon
submission, the backend processes the inputs, applies the trained model, and
displays the predicted house price to the user in real time.
This project not only demonstrates the practical use of machine learning for
regression problems but also highlights the synergy between backend data science
and frontend user interaction. The final application is scalable and can be further
enhanced with real-time data integration, map APIs, and database support, making
it a valuable tool for property buyers, investors, and real estate professionals.
