Real estate price prediction using decision tree algorithm in python

 

Real estate price prediction using decision tree algorithm

 

 PROJECT ID: PYTHON23

 

PROJECT NAME: Real estate price prediction using decision tree algorithm

 

PROJECT CATEGORY: MCA / BCA / BCCA / MCM / POLY / ENGINEERING

 

PROJECT ABSTRACT:

Gentrification is a loaded term that is seen in both a positive and negative light. On the one hand, gentrification raises the value of property enriching existing house owners, on the other hand it pushes the price of rentals up, driving out non-house owners who may have lived in that neighbourhood their entire lives. One place that has experienced massive change over the last 2 or so decades is Brooklyn. Gentrification has driven up property and rentals so much so that even the Marvel Cinematic Universe's Captain America, despite being an Avenger, indicated that he could not afford to stay there.

Captain America seemingly looking up in awe at Brooklyn property prices Source: DeadBeatsPanel

For this analysis I decided to download a Kaggle dataset on Brooklyn Home Sales between 2003 and 2017, with the objective of observing home sale prices between 2003 and 2017, visualising the most expensive neighbourhoods in Brooklyn and using and comparing multiple machine learning models to predict the price of houses based on the variables in the dataset.

Exploring the Data

I found it appropriate to start my analysis by visualising the distribution of house sale prices by year to possibly spot potential outliers and get a better understanding of interesting trends in my dataset.

 

SOFTWARE REQUIREMENTS:

OS                                : Windows

Python IDE                  : Python 2.7.x and above

Language                             : Python Programming

Database                             : MYSQL

 

HARDWARE REQUIREMENTS:

 RAM                :  4GB and Higher

Processor          :  Intel i3 and above

Hard Disk         : 500GB Minimum

 

Removing Outliers

For my analysis I decided to remove outlier sales. Since I want to predict the price of houses using regression models I believed that it would be harder to get a model that performs well for both normal and outlier pattern sales, the latter of which may include multiple commercial properties (for example the 28 commercial units sold for ±$500 million). I understand that doing this renders my models incapable of generalising to outlier house prices and may 'artificially' improve the performance of my regression models.

Data Clean Up

The Brooklyn house sales database contains 111 columns, a number of these columns contain too many NA values to be of significant value to my analysis. After trying out a few options I opted to drop all columns with 75% or more NA values.

TABLE OF CONTENTS

·        Title Page      

·        Declaration

·        Certification Page

·        Dedication

·        Acknowledgements

·        Table of Contents

·        List of Tables

·        Abstract

 

CHAPTER SCHEME

CHAPTER ONE: INTRODUCTION

CHAPTER TWO: OBJECTIVES

CHAPTER THREE: PRELIMINARY SYSTEM ANALYSIS

·         Preliminary Investigation

·         Present System in Use

·         Flaws In Present System

·         Need Of New System

·         Feasibility Study

·         Project  Category

CHAPTER FOUR: SOFTWARE ENGINEERING AND PARADIGM APPLIED   

·         Modules

·         System / Module Chart

CHAPTER FIVE: SOFTWARE AND HARDWARE REQUIREMENT

CHAPTER SIX: DETAIL SYSTEM ANALYSIS

·         Data Flow Diagram

·         Number of modules and Process Logic

·         Data Structures  and Tables

·         Entity- Relationship Diagram

·         System Design

·         Form Design 

·         Source Code

·         Input Screen and Output Screen

CHAPTER SEVEN: TESTING AND VALIDATION CHECK

CHAPTER EIGHT: SYSTEM SECURITY MEASURES

CHAPTER NINE: IMPLEMENTATION, EVALUATION & MAINTENANCE

CHAPTER TEN: FUTURE SCOPE OF THE PROJECT

CHAPTER ELEVEN: SUGGESTION AND CONCLUSION

CHAPTER TWELE: BIBLIOGRAPHY& REFERENCES          

Other Information

 

PROJECT SOFWARE	ZIP
PROJECT REPORT PAGE	60 -80 Pages
CAN BE USED IN	Marketing (MBA)
PROJECT COST	1500/- Only
PDF SYNOPSIS COST	250/- Only
PPT PROJECT COST	300/- Only
PROJECT WITH SPIRAL BINDING	1750/- Only
PROJECT WITH HARD BINDING	1850/- Only
TOTAL COST (SYNOPSIS, SOFTCOPY, HARDBOOK, and SOFTWARE, PPT)	2500/- Only
DELIVERY TIME	1 OR 2 Days (In case Urgent Call: 8830288685)
SUPPORT / QUERY	www.projectsready.in
CALL	8830288685
Email	help@projectsready.in
[Note: We Provide Hard Binding and Spiral Binding only Nagpur Region]	Download