SEMINAR PRESENTATION

ON

HOUSE PRICE PREDICTION USING ML

PRESENTED BY: KUSHAGRA PANDEY

ROLL NO: 2021071020
CONTENT
• Introduction

• Data Collection

• Data Visualization

• Statistical Analysis of Feature

• Data Pre-Processing

• EDA

• Performance Metrices

• Model Fitting

• SWOT

• Application

• Conclusion
ABSTRACT

• House price prediction is an important topic of real estate. The literature attempts to
derive useful knowledge from historical data of property markets. Machine learning
techniques are applied to analyze historical property transactions in India to discover
useful models for house buyers and sellers.

• Moreover, experiments demonstrate that the Linear Regression , Random forest and Xgboost
that is based on mean squared error measurement is a competitive approach.
 INTRODUCTION
• Machine learning is an area of artificial intelligence (AI) with a concept that a computer program can learn
and adapt to new data without human intervention.

• Supervised learning is the types of machine learning in which machines are trained using well "labelled"
training data, and on basis of that data, machines predict the output. The labelled data means some input
data is already tagged with the correct output..

• Types of Supervised learning:

 Regression
 Classification

• Linear Regression

• Decision Tree

• Support vector machine

• House is one of human life's most essential needs, along with other fundamental needs such as food, water.
House price prediction can be done using multiple prediction models (Machine Learning Model) such as
linear regression ,Random Forest etc.
 TOOLS USED
These are the tools used to create the house price prediction
model using machine learning
 DATA COLLECTION
To create a machine learning model, the first thing we required is a dataset as a machine
learning model completely works on data. The collected data for a particular problem in a
proper format is known as the dataset.
 DATA VISUALISATION
Data visualization is a crucial aspect of machine learning that enables analysts to understand and
make sense of data patterns, relationships, and trends.
STATISTICAL ANALYSIS OF FEATURES
Descriptive Statistics
Analyzing key statistical measures
such as mean, median, standard
deviation, and skewness to understand
the central tendencies and distributions
of the features.

Feature Importance
Utilizing statistical techniques to
determine the significance of each
feature in influencing house prices.

Correlation Analysis
Exploring the correlation matrix to
identify the relationships between
features and their potential impact on
predicting house prices.
 DATA PRE-PROCESSING
 Getting the dataset
 Importing libraries
 Importing datasets
 Finding Missing Data
 Encoding Categorical Data
 Splitting dataset into training and test set
 Feature scaling
 EDA
 Import libraries and dataset
 Correlation between attributes
 Missing Values
i. Finding missing values
ii. Inputting missing values

 Dealing with character variables

 Dropping irrelevant column

 Feature Engineering
 Preparing Data for Modelling
i. Dropping high correlated variables
ii. Removing outliers

 Splitting the Data

 CRITERIA TO MEASURE THE
PERFORMANCE

 Root Mean Square Error (RMSE)

 R Squared (R2)

 Mean absolute error (MAE)

 Mean square error (MSE)

 MODEL FITTING
 Linear regression is a type of
supervised learning model algorithm
that computes the linear relationship
between the dependent variable and
one or more independent features
by fitting a linear equation to
observed data.

 Using linear regression is to locate

the best-fit line, which implies that
the error between the predicted and
actual values should be kept to a
minimum.
 MODEL FITTING

 Random Forest algorithm is a powerful tree

learning technique in Machine Learning. It
works by creating a number of Decision
Tree during the training phase

 Key Features of Random Forest

i. Resistance to Overfitting
ii. Large Datasets Handling
 FLASK

 Flask is a web framework that

allows developers to build
lightweight web applications quickly
and easily with Flask Libraries.

 It is classified as a
microframework because it does
not require particular tools or
libraries. It has no database or any
other components where pre-
existing third-party libraries provide
common functions.
 SWOT ANALYSIS

Strengths Weaknesses
1. Accuracy 1. Data Quality
2. Efficiency 2. Model Complexity
3. Scalability 3. Overfitting
4. Data-driven Insights 4. External Factors

Threats Opportunities
1. Competition 1. Feature Engineering
2. Cybersecurity Risks 2. Integration with Other Systems
3. Model Decay 3. Personalization
4. Ethical Concerns 4. Education and Outreach
APPLICATION OF MACHINE LEARNING MODELS

 Real Estate
Investment

 Property Valuation

 Property Tax
Assessment

 Personal Finance

 Insurance

 Market Analysis
 CONCLUSION

• The RSME of the random forest model are very low, which tells us the
prediction in the random forest model tends to be more central than
regression model.
• However the R squared of the training set is very good. But the R
squared of the test set is relatively low, which may show that random
forest model is a little bit overfitting.
• The RSME and R squared of Xgboost are both good and shows that
model is reasonable and not overfitting, hence Xgboost is the final
model.
REFERENCE
• https://towardsdatascience.com/workflow-of-a-machine-learning-
projectec1dba419b94
• https://www.geeksforgeeks.org/what-is-reinforcement-learning/
• https://www.javatpoint.com/unsupervised-machine-learning
• https://www.edureka.co/blog/supervised-learning/
• https://www.einfochips.com/blog/understanding-image-recognition-and-its-uses/
• https://www.caranddriver.com/research/a31996016/what-is-a-self-driving-car/
• https://en.wikipedia.org/wiki/Virtual_assistant
• https://deepmind.com/blog/article/traffic-prediction-with-advanced-graphneural-
networks
Thank you