A
PROJECT REPORT
ON
“House Price Prediction”
Submitted by
Sr. No. Name of Student Roll No.
01 Harshit Nandkumar Gorad 3108
02 Sarthak Balaso Patole 3119
03 Pradnya Adhikrao Gorad 3133
04 Shweta Ramesh Jadhav 3143
Under the guidance of
Mrs. N. A. Mulla
Academic
Year 2024-25
DEPARTMENT OF ARTIFICIAL INTELLIGENCE & MACHINE
LEARNING
Loknete Ma. Hanmantrao Patil Charitable Trust’s
ADARSH INSTITUTE OF TECHNOLOGY RESEARCH
CENTRE, VITA, DIST-SANGLI
Loknete Ma. Hanmantrao Patil Charitable Trust’s
Adarsh Institute of Technology and Research Centre, Vita
CERTIFICATE
This is to certify that the project report entitled
“House Price Prediction”
Submitted by
Sr. No. Name of Student Roll No.
01 Harshit Nandkumar Gorad 3108
02 Sarthak Balaso Patole 3119
03 Pradnya Adhikrao Gorad 3133
04 Shweta Ramesh Jadhav 3143
SUBMITTED IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE AWARD OF
DIPLOMA OF ENGINEERING
(ARTIFICIAL INTELLIGENCE & MACHINE LEARNING)
SUBMITTED TO
MAHARASHTRA STATE BOARD OF TECHNICAL EDUCATION
MUMBAI
ACADEMIC YEAR 2024-25
Guide H.O.D. Principal
Mrs.N. A. Mulla Prof. A. A. Vankudre Dr. P.S.Patil
ACKNOWLEDGEMENT
I would like to place on record my deep sense of gratitude to Prof. A. A. Vankudre HOD-Department of
Artificial intelligence & Machine Learning, for his generous guidance, help and useful suggestions.
I express my sincere gratitude to Mrs. N. A. Mulla, Department of Artificial intelligence & Machine Learning,
for his/her stimulating guidance, continuous encouragement and supervision throughout the course of present
work.
I am extremely thankful to Principal Dr. P. S. Patil for this motivation and providing me infrastructural facilities
to work in, without which this work would not have been possible.
I would like to express my gratitude to all my colleagues for their support, co-operation and fruitful discussions
on diverse seminar topics and technical help.
Name of Student Sign
1. Harshit Nandkumar Gorad
2. Sarthak Balaso Patole
3. Pradnya Adhikrao Gorad
4. Shweta Ramesh Jadhav
INDEX
1. Introduction ............................................................................................................... 1
1.1 Introduction ................................................................................................................................... 1
1.2 Objective........................................................................................................................................ 1
1.3 Scope ............................................................................................................................................. 2
2. Literature Review ..................................................................................................... 3
2.1 Literature Review ......................................................................................................................... 3
2.2 Need of Work ............................................................................................................................... 3
2.3 Problem Statement ........................................................................................................................ 3
3. System Development ................................................................................................. 5
3.1 Existing System............................................................................................................................ 5
3.2 Proposed System ........................................................................................................................... 5
3.3 System Architecture ...................................................................................................................... 5
4. Design Methodology..................................................................................................6
4.1 Data Flow Diagram ...................................................................................................................... 6
4.2 ER Diagram .................................................................................................................................. 7
4.3 UML Diagram ............................................................................................................................... 8
4.3.1 Class Diagram .......................................................................................................................9
4.3.2 Object Diagram................................................................................................................... 10
4.3.3 Use Case Diagram ............................................................................................................... 11
4.3.4 Sequence Diagram.............................................................................................................. 12
4.3.5 Activity Diagram ................................................................................................................. 13
4.3.6 State Diagram ...................................................................................................................... 14
4.3.7 Component Diagram .......................................................................................................... 15
4.3.8 Deployment Diagram ......................................................................................................... 16
5. Implementation Details...........................................................................................17
5.1 Functional Requirements............................................................................................................ 17
5.2 Non Functional Requirements .................................................................................................... 17
6. Conclusion ...............................................................................................................19
7. Future Scope ............................................................................................................ 19
8. References ................................................................................................................ 20
8.1 Books .......................................................................................................................................... 20
8.2 Research-Journal Papers .............................................................................................................20
8.3 Website ....................................................................................................................................... 20
1) Introduction
1.1 Introduction
The real estate market is a dynamic and complex environment influenced by various factors,
including economic conditions, demographic trends, and geographical characteristics. Accurately
predicting house prices is essential for buyers, sellers, andinvestors, as it directly impacts
financial decisions and market strategies. Traditional methods of valuation often rely on historical
sales data and subjective assessments, which may not capture the nuances of current market
conditions.
With the advent of big data and machine learning technologies, there is an opportunity to
enhance the precision of house price predictions. Machine learning algorithms can analyze
vast datasets, identifying patterns and relationships that traditional methods may overlook.
Features such as location, square footage, the number of bedrooms andbathrooms, and
property age can significantly influence property values, making it crucial to incorporate these
variables into predictive models.
This study aims to harness the power of machine learning to develop robust predictive models
for house prices. By exploring a range of algorithms —including Linear Regression, Decision
Trees, Random Forests, and Gradient Boosting Machines—we seek to identify the most
effective methods for forecasting housing prices. Additionally, the integration of OAuth 2.0 for
secure data access and real-time encryption for data protection ensures that sensitive housing
information is safeguarded while allowing for comprehensive analysis.
1.2 Objective
• Develop Predictive Models: Utilize machine learning techniques to create robust models for
accurately forecasting house prices.
• Analyze Key Features: Identify and incorporate critical factors like location, square footage,
number of bedrooms/bathrooms, and property age into the models.
• Explore Algorithms: Evaluate multiple machine learning algorithms, including Linear
Regression, Decision Trees, Random Forests, and Gradient Boosting Machines, to determine the
most effective approach.
• Enhance Prediction Precision: Leverage big data and machine learning to identify patterns and
relationships that traditional methods may miss.
• Ensure Data Security: Integrate OAuth 2.0 for secure data access and implement real-time
encryption to protect sensitive housing information.
• Support Stakeholders: Provide accurate and reliable insights for buyers, sellers, and investors to
make informed financial decisions.
• Improve Market Strategies: Address the nuances of current market conditions to enhance
decision-making and market strategies.
1.3 Scope
• Advanced Predictive Analysis: Develop machine learning models to accurately predict house
prices, addressing the limitations of traditional valuation methods.
• Comprehensive Data Integration: Utilize diverse datasets, including property features
(location, size, age, etc.), to enhance the accuracy and reliability of predictions.
• Algorithm Exploration: Compare and optimize multiple algorithms, such as Linear Regression,
• Decision Trees, Random Forests, and Gradient Boosting Machines, for effective performance.
• Technology Adoption: Leverage big data and machine learning to uncover hidden patterns in
• housing market trends that traditional methods may overlook.
• Secure Data Handling: Ensure the confidentiality and integrity of data through OAuth 2.0 and
real-time encryption mechanisms.
Page 7
• Stakeholder Benefits: Cater to the needs of buyers, sellers, and investors by providing
actionable insights for informed decision-making.
• Scalability: Offer a system that can adapt to evolving real estate markets and handle a variety of
property types and regions.
• Practical Applications: Facilitate strategic market planning, financial forecasting, and
investment decision-making for diverse real estate stakeholders.
• Market Impact: Contribute to a deeper understanding of real estate dynamics, enabling
stakeholders to navigate complex market conditions effectively.
• Future Expansion: Set the foundation for integrating additional features, such as rental price
predictions, real-time market analysis, and property recommendation systems.
Page 8
2) Literature Review
2.1 Literature Review
The field of real estate price prediction has evolved significantly from traditional methods, such
as Hedonic Pricing Models and Multiple Linear Regression, which rely heavily on historical sales
data and subjective appraisals but often fail to capture the complexities of dynamic market
conditions. Recent advancements in machine learning have enabled more accurate and robust
predictions by analyzing non-linear relationships and vast datasets, incorporating features such
as location, propertysize, and economic indicators. Algorithms like Decision Trees, Random
Forests, Gradient Boosting Machines, and Neural Networks have shown promising results in
identifying patterns and trends that traditional approaches overlook. Geographic Information
Systems (GIS) and big data integration further enhance prediction accuracy by including
spatial and real-time market influences. However, challenges such as data quality, computational
efficiency, and the secure handling of sensitive information remain. Studies emphasize the
importance of frameworks like OAuth 2.0 and encryption to address privacy concerns while
ensuring reliable and scalable models for real estate forecasting. This literature provides a
foundation for developing a comprehensive, machine learning-based solution to predict house
prices effectively.
2.2 Need of Work
Accurately predicting house prices is critical for buyers, sellers, and investors as it directly
impacts financial decisions, market strategies, and economic planning. Traditional valuation
methods, while widely used, often fail to capture the complexities of modern real estate markets,
which are influenced by a wide range of factors, including location, property features, and
macroeconomic conditions. With the advent of big data and machine learning technologies, there
is a growing need to leverage these tools to enhance the precision and reliability of house price
predictions. Machine learning models can uncover hidden patterns and relationships in large
datasets that traditional approaches overlook, providing stakeholders with deeper insights.
Furthermore, the real estate industry requires secure and scalable solutions to address concerns
regarding data privacy and accuracy, particularly with the increasing reliance on digital platforms
and big data analytics. This work seeks to fill these gaps by developing a robust predictive
framework that incorporates advanced machine learning techniques, ensures secure data
handling, and delivers actionable insights to support informed decision-making in the dynamic
and complex real estate market.
2.3 Problem Statement
The real estate market is inherently complex, influenced by numerous dynamic factors such as
economic conditions, geographic characteristics, and property-specific attributes. Traditional
methods of house price prediction, primarily based on historical sales data and subjective
appraisals, often fail to accurately reflect the intricacies of modern market dynamics. As a result,
these methods can lead to suboptimal decision-making for buyers, sellers, and investors. With the
rise of big data and machine learning technologies, there is a significant opportunity to enhance
prediction accuracy by analyzing vast datasets and uncovering patterns that traditional techniques
overlook. However, challenges persist in integrating diverse data sources, handling large volumes
Page 9
of real-time data, and ensuring the security of sensitive information. This study aims to develop a
machine learning-based predictive model that accurately forecasts house prices by leveraging key
property attributes and external factors, while addressing issues related to data security and
computational efficiency. The goal is to provide a reliable and scalable solution that supports
informed decision-making in the real estate market.Agri Connect seeks to bridge these gaps by
creating a digital platform that provides real-time solutions for crop management, helping
farmers make informed, data-driven decisions. This platform will also facilitate access to
affordable and quality farming inputs, enabling farmers to reduce costs and improve profitability.
Through these solutions, Agri Connect aims to empower farmers, enhance productivity, and
promote sustainable agricultural practices.
Page 10
3) System Development
3.1 Existing System
Currently, house price prediction mainly relies on older methods like Hedonic Pricing Models
(HPM), Multiple Linear Regression (MLR), and Automated Valuation Models (AVMs). These
methods look at historical data and property details like size, location, and condition to estimate
prices. While these systems are commonly used, they don’t do well at handling the complex and
ever-changing nature of the real estate market. Manual appraisals, where experts give their
opinion on a property's value, can also lead to inconsistent results. Moreover, these systems often
struggle to work with real-time data and newer factors like digital trends and economic changes,
which can affect house prices. As a result, there is a need for better, more modern approaches,
such as machine learning, which can handle large amounts of data, find patterns, and provide
more accurate, real-time predictions. However, challenges like combining different data sources,
scalability, and security still need to be addressed, which this study aims to tackle with a machine
learning-based solution.
3.1 Proposed System
• Use of Machine Learning: The system will use machine learning to predict house prices
more accurately.
• More Data: It will consider more information, like property details, market trends, and real-
time updates.
• Finding Patterns: Machine learning will help find patterns in the data that traditional
methods miss, like location, size, and age of the property.
• Real-Time Updates: The system will keep predictions updated with the latest market
information.
• Data Protection: It will use security measures like encryption to protect sensitive data.
• Better Decisions: The system will help buyers, sellers, and investors make smarter decisions
with faster and more accurate predictions.
3.2 System Architecture
The System Architecture of House Price Prediction consists of three main layers:
• User Interface Layer: Provides users with an easy-to-use platform (web and mobile) to
input property details, view predictions, and access market insights.
• Application Layer: Contains the machine learning model for price predictions, data
analytics for market trends, and real-time updates for accurate pricing forecasts.
• Data Layer: Manages a centralized database for property data, integrates external data
sources like economic indicators and market trends, and ensures data security and
backups.
Page 11
4) Design Methodology
4.1 Data Flow Diagram
Registration
Login using user type
1)Farmer. 2)Admin. 3)Worker.
Farmer Admin Worker
Sell Rent Machinery
Product Add Product Work Requests Work
Worker Profile
Available
Machinery Add Product
Buy Page Request Page Work History
for Rent Worker Profile Page with Attributes
Payment
Cart Payment
Profile Farmer Revenue/History Add Machinery
To Rent
Info about Farmer Profile Page Revenue page Rent Machinery
Agri-connect
Fig:4.1 Data Flow Diagram
Page 12
4.2 ER Diagram
Fig:4.2 ER Diagram
Page 13
4.3 UML Diagram
Fig:4.3 UML Diagram
Page 14
4.3.1 Class Diagram
Fig:4.3.1 Class Diagram
Page 15
4.3.2 Object Diagram
Fig:4.3.2 Object Diagram
Page 16
4.3.3 Use Case Diagram
Fig:4.3.3 Object Diagram
Page 17
4.3.4 Sequence Diagram
Fig:4.3.4 Sequence Diagram
Page 18
4.4.5 Activity Diagram
Fig:4.3.5 Activity Diagram
Page 19
1.3.6 State Diagram
Fig:4.3.6 State Diagram
Page 20
1.3.7 Component Diagram
Fig:4.3.7 Component Diagram
Page 21
1.3.8 Deployment Diagram
Fig:4.3.8 Deployment Diagram
Page 22
5) Implementation Details
5.1 Functional Requirements
• Processor : Intel core i5
• Speed : 2.6Ghz-4.6Ghz
• RAM : 16 GB
• SSD : 512 GB
• Monitor : N/A
5.2 Non Functional Requirements
• Performance
1) The system shall handle up to 500 concurrent users without performance degradation.
2) Response time for any action shall not exceed 2 seconds under normal load.
• Scalability
1) The system shall be scalable to support future growth in user base and additional
functionalities.
2) The database shall accommodate up to 1 million records efficiently.
• Availability
1) The system shall ensure 99.9% uptime, with planned maintenance downtime notified to
users in advance.
• Security
1) All user data, including passwords, shall be securely stored using encryption (e.g., AES-
256).
2) The system shall implement SSL/TLS for secure data transmission.
3) User sessions shall time out after 30 minutes of inactivity.
• Usability
1) The system shall have an intuitive and user-friendly interface suitable for both tech-savvy
and non-tech-savvy users.
2) All forms shall include tooltips and validations to guide users.
Page 23
• Maintainability
1) The system shall be designed for easy maintenance, with clear documentation provided for
code, database schemas, and APIs.
2) Regular updates shall be deployed without disrupting user activity.
• Compatibility
1) The system shall be compatible with major browsers, including Chrome, Firefox, Edge, and
Safari.
2) Mobile-friendly design shall be implemented using responsive web design techniques.
• Logging and Monitoring
1) The system shall maintain detailed logs of all user activities for troubleshooting and auditing
purposes.
2) The system shall include monitoring tools to track server performance and errors in real time.
• Data Backup and Recovery
1) The system shall perform automated daily backups of all critical data.
2) Recovery from a backup shall not exceed 1 hour in case of data loss or corruption.
Page 24
6) Conclusion
In conclusion, the Agri Connect project successfully delivers a comprehensive web application
that addresses the key challenges faced by farmers. This platform not only provides access to
essential resources like machinery and skilled labor but also offers real-time solutions to crop-
related issues, improving overall farming efficiency and productivity. By enabling data-driven
decision-making, connecting farmers to markets, and promoting sustainable practices, Agri Connect
empowers farmers to increase their yields, reduce costs, and improve their livelihood. Ultimately,
this application is a valuable tool in driving agricultural advancement and ensuring a resilient,
sustainable future for farmers.
7) Future Scope
The Future Scope of Agri Connect includes:
• IoT and Smart Devices: Integrate with sensors and devices that track soil health, weather,
and crop growth, providing farmers with accurate, real-time data.
• Predictive Analysis: Use advanced AI to predict crop yields, pest outbreaks, and weather
effects, helping farmers plan ahead.
• Expanded Market Access: Grow the platform’s e-commerce features so farmers can sell
directly to consumers or retailers, reducing reliance on middlemen.
• Financial Services: Offer micro-loans, crop insurance, and savings options to support
farmers financially and help them invest in better resources.
Page 25
8) References
8.1 Books
• Sommerville, I. (2011). Software Engineering (9th ed.) - A comprehensive guide to
software engineering practices.
• Pressman, R. S. (2014). Software Engineering: A Practitioner's Approach - Focuses on
software development methodologies.
• McConnell, S. (2004). Code Complete - Offers practical advice on software construction
and coding practices.
8.2 Research-Journal Papers
• Kaur, A., & Kaur, M. (2019). Agri-Tech: A Study of Agricultural Technologies - Explores
technology's role in modern agriculture.
• Chaudhary, V., & Kapoor, R. (2020). Smart Farming: Current Trends - Discusses the
impact of smart farming on agriculture.
• Rani, S., & Sharma, A. (2021). Development of Agricultural Management Systems -
Reviews software for improving farming practices.
• Patel, R., & Choudhary, V. (2021). Machine Learning in Agricultural Technologies -
Explores machine learning applications in agriculture.
8.3 Websites
• Agri-Tech East (2022). Agri-Tech East - A platform for exploring agricultural technology
innovations.( https://www.agri-tech-e.co.uk)
• TechCrunch (2021). Agriculture and Technology - Covers technology's impact on
agriculture.( https://techcrunch.com)
• Agri Connect (2022). Official Website - Provides details on the Agri Connect platform.
( http://www.agriconnect.com)
• IFPRI (2022). The Role of Technology in Modernizing Agriculture - Resources on how
technology is transforming farming.( https://www.ifpri.org)
• GitHub (2022). Agri Connect Repository - GitHub repository for Agri Connect project.
(https://github.com)
Page 20
