18DCS031 SGP-III(CS348)-HOUSE PRICE PREDICTION

A Project Report On
“HOUSE PRICE PREDICTION”

Prepared by
Dhariyashill Dhingani(18DCS021)
Shubham Kalola(18DCS031)
Mahir Thumar(18DCS128)

Under the guidance of

Prof. KRISHNA PATEL

A Report Submitted to
CharotarUniversity of Science and Technology
ForPartial Fulfillment of the Requirements for the
5th Semester Software Group Project-III(CS348)
Submitted at:

CSE
DEPSTAR
Computer Science And Engineering (CSE)
At :Changa,Dist: Anand – 388421
May 2020

DEPSTAR-CSE 1
18DCS031 SGP-III(CS348)-HOUSE PRICE PREDICTION

CERTIFICATE

This is to certify that the report entitled “House Price Prediction” is a bonafied work carried
out by Mr. Shubham Kalola(18DCS031) under the guidance and supervision of Prof. Krishna
Patel for the subject CS348 Software Group Project-III(CSE) of 5th Semester of Bachelor of
Technology in DEPSTAR at Faculty of Technology & Engineering – CHARUSAT, Gujarat.

To the best of my knowledge and belief, this work embodies the work of candidate himself, has
duly been completed, and fulfills the requirement of the ordinance relating to the B.Tech. Degree
of the University and is up to the standard in respect of content, presentation and language for
being referred to the examiner.

Prof. Krishna Patel

Assistant Professor
Branch Name CSE
DEPSTAR, Changa, Gujarat.

Dr. Amit Ganatra

Principal, DEPSTAR
Dean, FTE
CHARUSAT, Changa, Gujarat.

Devang Patel Institute of Advance Technology And Research At: Changa, Ta. Petlad, Dist. Anand,
PIN: 388 421. Gujarat

DEPSTAR-CSE 2
18DCS031 SGP-III(CS348)-HOUSE PRICE PREDICTION

ACKNOWLEDGEMENT
We, the developer of a “House Price Prediction”, have taken efforts in this project.
However, it would not have been possible without the kind support and help of many
individuals and organizations. I would like to extend my sincere thanks to all of them.

We with immense pleasure and commitment would like to present the project
assignment. The development of this project has given us wide opportunity to think,
implement and interact with various aspects of management skills as well as the new
emerging technologies.

Every work that one completes successfully stands on the constant encouragement, good
will and support of the people around. We hereby avail this opportunity to express our
gratitude to number of people who extended their valuable time, full support and
cooperation in developing the project.

We are highly indebted to Prof. Krishna Patel and for their guidelines and constant
supervision as well as for providing necessary information regarding the project and also
their support in completing the project.
Youtube has been our main source for gathering information and concepts that we
needed to apply in app development.
We are sincerely thankful to all the classmate at SGP- Labs who helped us complete the
project in one way or the other.
They altogether provided us favorable environment, and without them it would not have
been possible to achieve our goal.
We would like to thanks CHARUSAT University for adding subject like SGP for setting the
stage.
We would like to thanks our parents for their encouraging which helped us in completion
in project.

DEPSTAR-CSE 3
18DCS031 SGP-III(CS348)-HOUSE PRICE PREDICTION

ABSTRACT

Usually, House price index represents the summarized price changes of residential housing.
While for a single family house price prediction, it needs more accurate method based on
location, house type, size, build year, local amenities, and some other factors which could affect
house demand and supply. With limited dataset and data features, a practical and composite data
pre-processing, creative feature engineering method is examined.

Prediction house prices are expected to help people who plan to buy a house so they can know
the price range , then they can plan their finance well. In addition, house price predictions are
also beneficial for property investors to know the trend of housing prices in a certain location.
The goal of this project is to create a regression model that are able to accurately estimate the
price of the house on the basis of certain features.

DEPSTAR-CSE 4
18DCS031 SGP-III(CS348)-HOUSE PRICE PREDICTION

INDEX
Chapter

1. Project Definition……………………………………………………………………………………………………..….7
2. Description……………………………………………………………………………………………………………….….8
3. Software and Hardware Requirements…………………………………………………….………………….9
4. Major Functionality……………………………………………………………………………………….…….…....10
5. System Flow Chart.……………………………………………………………………………………….…..……...11
6. Screenshots of our project output……………………………………………………………….…………...13
7. Limitations of project………………………………………………………………………………………….…....15
8. Project Outcomes……………………………………………………………………………………………….….…16
9. Future Enhancement………………………………………………………………………………………….…..…17
10. References…………………………………………………………………………………………………………….....18

Table of Figures

FIGURE DESCRIPTION Page No.

No.
1 Flowchart 11
2 Implementation Snapshot - 1 12
3 Implementation Snapshot – 2 12

DEPSTAR-CSE 5
18DCS031 SGP-III(CS348)-HOUSE PRICE PREDICTION

CHAPTER 1: PROJECT DEFINITION

 In India, there are multiple real estate classified websites where properties are listed for
sell/buy/rent and more. However, in each of these websites we can see lot of
inconsistencies in terms of pricing of an apartment and there are some cases when similar
apartments are priced differently and thus there is lot of in-transparency.

 Sometimes the consumers may feel the pricing is not justified for a particular listed
apartment but there no way to confirm that either. Proper and justified prices of
properties can bring in a lot of transparency and trust back to the real estate industry,
which is very important as for most consumers especially in India the transaction prices
are quite high and addressing this issue will help both the customers and the real estate
industry in the long run. We propose to use machine learning and artificial intelligence
techniques to develop an algorithm that can predict housing prices based on certain input
features.

DEPSTAR-CSE 6
18DCS031 SGP-III(CS348)-HOUSE PRICE PREDICTION

CHAPTER 2 :DESCRIPTION

 As we all know that buying the house is stressful thing, so many problem is faced during
buying a house. We all know that real estate agents are trusted with the communication
between buyers and seller so this just create a increases the cost of the house.
 The main objective of the system is to predict the possible accurate price of the house
depended on the many features other than the area.
 This proposed system predict the price of the house on the basis of the Area of the house,
Bedroom, Bathroom, Balcony and the location of the house.(Locality)

DEPSTAR-CSE 7
18DCS031 SGP-III(CS348)-HOUSE PRICE PREDICTION

CHAPTER 3: SOFTWARE AND HARDWARE REQUIREMENTS

2.1 : Software Requirements

1) Anaconda
Anaconda is a free and open-source distribution of the Python and R programming languages for
scientific computing, that aims to simplify package management and deployment. The distribution
includes data-science packages suitable for Windows, Linux, and macOS.

2) Spyder (Model Training).

Spyder is an open source cross-platform integrated development environment (IDE) for scientific
programming in the Python language. Spyder integrates with a number of prominent packages in
the scientific Python stack, including NumPy, SciPy, Matplotlib, pandas, IPython, SymPy and
Cython, as well as other open source software.[3][4] It is released under the MIT license.[5]

3)Sublime.
Sublime Text is a shareware cross-platform source code editor with a Python application
programming interface. It natively supports many programming languages and markup languages,
and functions can be added by users with plugins, typically community-built and maintained under
free-software licenses.

4) Pycharm (For Flask Web Framework).

PyCharm is the most popular IDE used for Python scripting language. PyCharm offers some of
the best features to its users and developers in the following aspects −
 Code completion and inspection
 Advanced debugging
 Support for web programming and frameworks such as Django and Flask.

Flask is a web framework. This means flask provides you with tools, libraries and technologies
that allow you to build a web application. This web application can be some web pages, a blog, a
wiki or go as big as a web-based calendar application or a commercial website.

2.2 : Hardware Requirements

Minimum :

 Microsoft Windows 7/8/10 (32-bit or 64-bit)

 2 core CPU
 2 GB RAM.
 20 GB of available disk space minimum,

DEPSTAR-CSE 8
18DCS031 SGP-III(CS348)-HOUSE PRICE PREDICTION

CHAPTER 4: MAJOR FUNCTIONALITY

Following were the stages of planning and implementation:

1. Gathering Data.

2. Data Analysis and Data cleaning.

3. Model Training.

4. Deployment of the model using Flask.

We began the development of this project by gaining insights from data by utilizing the data
visualizing libraries in python and then moved on to Feature Engineering srep.
From the dataset all NaN values in feature Engineering step was removed and many independent
variables are also removed.
Data was then split into train set and test set and was fed to a Linear Regression. Predictions were
made and accuracy was calculated using R2 score.
After finalizing the model, model was dumped using pickle and used later on Flask files to make
appropriate predictions.

Json File was also used to transmit data between a server and web applications.
The website templates were made using HTML,CSS and basic Javascript.
Hence the complete functionality would be:
1. User enters the data for House Price and fed to model with pretrained parameters using
Flask using HTTP POST).
2. Calculations of Price is made based on entered parameters.
3. Template is rendered again, displaying the predicted production value.

DEPSTAR-CSE 9
18DCS031 SGP-III(CS348)-HOUSE PRICE PREDICTION

CHAPTER 5:SYSTEM FLOWCHART

Figure 1

DEPSTAR-CSE 10
18DCS031 SGP-III(CS348)-HOUSE PRICE PREDICTION

CHAPTER 6: SCREENSHOT OF PROJECT OUTPUT

Figure 2

Figure 2

DEPSTAR-CSE 11
18DCS031 SGP-III(CS348)-HOUSE PRICE PREDICTION

CHAPTER 7: LIMITATIONS
 It doesn't predict Exact future prices of the houses mentioned by the customer. Due to
this, the risk in investment in an apartment or an area increases considerably. To
minimize this error, customers tend to hire an agent which again increases the cost of
the process.

 When there is an update in the price per square foot in the house it May or may not
predict the exact prices of the houses.

 There is only 85% accuracy for prediction of house prices, later by applying advanced
Machine Learning Algorithm we can improve the accuracy.

DEPSTAR-CSE 12
18DCS031 SGP-III(CS348)-HOUSE PRICE PREDICTION

CHAPTER 8: OUTCOMES

 This project was a very good way to probe into the unknown spaces of Machine learning.

 Different Regression Algorithms was effectively learnt and implemented.

 Anaconda & Spyder provides simplicity in the development process.

 Flask framework does a great job by providing an excellent framework to build website
in a truly platform independent way.
 This project also taught us the importance of teamwork, coordination and time
management.

 Every error came up as challenge for us and was solved efficiently with teamwork.

DEPSTAR-CSE 13
18DCS031 SGP-III(CS348)-HOUSE PRICE PREDICTION

CHAPTER 9: FUTURE ENHANCEMENT

 we can try to make this model more accurate by applying the advance regression
algorithms to this model in future.

 Also we can make model in future , By analyzing previous market trends

and price ranges, and also upcoming developments future prices will be predicted .

 One of the major future scopes is adding estate database of more cities which will
provide the user to explore more estates and reach an accurate decision.

DEPSTAR-CSE 14
18DCS031 SGP-III(CS348)-HOUSE PRICE PREDICTION

CHAPTER 10: REFERENCES

 https://www.geeksforgeeks.org/machine-learning/.

 https://towardsdatascience.com/predicting-house-prices-with-linear-regression-
machine-learning-from-scratch-part-ii-47a0238aeac1.

 https://medium.com/artificial-intelligence-solutions/make-your-own-model-to-predict-
house-prices-in-python-ad843aee1e2

 https://docs.anaconda.com/

 https://numpy.org/doc/

 https://pandas.pydata.org/docs/

DEPSTAR-CSE 15