Department of Information Science and

Department of Information Science and Engineering

Engineering

Prediction of Purchases from Social Media Apps

Tanmay Sharan 1NT19IS177

Randheer Prasad 1NT19IS127
Suryansh Arya 1NT19IS168
Sourav Dey 1NT19IS159
Vishal Raj 1NT19IS190
Suman Kr. Das 1NT19IS164
01/12/2022
Contents
Click to edit Master title style

1. Problem Statement
2. Overview of Dataset
3. Algorithms Used
4. Implementation

01-12-22 Department of Information Science and Engineering 2

Problem
Click toStatement
edit Master title style

To develop a SVM model that will predict if they person will

purchase the product after watching the advertisement on
any social media app.

01-12-22 Department of Information Science and Engineering 3

Overview
Click to edit
of Dataset
Master title style

Most of the columns in a dataset are noisy and contain lots of

information. But with feature engineering you do, you will get more good
results. The only problem is we are having less data, but we will obtain a
good accuracy over it. The only good thing is it is better to have a large
data.

01-12-22 Department of Information Science and Engineering 4

Algorithm
Click to edit
UsedMaster title style

SUPPORT VECTOR MACHINE ALGORITHM

Support Vector Machine(SVM) is a supervised machine learning algorithm
used for both classification and regression. Though we say regression
problems as well its best suited for classification. The objective of SVM
algorithm is to find a hyperplane in an N-dimensional space that distinctly
classifies the data points. The dimension of the hyperplane depends upon the
number of features. If the number of input features is two, then the
hyperplane is just a line. If the number of input features is three, then the
hyperplane becomes a 2-D plane. It becomes difficult to imagine when the
number of features exceeds three. 
01-12-22 Department of Information Science and Engineering 5
Algorithm
Click to edit
UsedMaster title style

Advantages of using SVM

• Effective in high dimensional spaces.
• Still effective in cases where number of dimensions is greater than the
number of samples.
• Uses a subset of training points in the decision function (called support
vectors), so it is also memory efficient.
• Versatile: different Kernel functions can be specified for the decision
function. Common kernels are provided, but it is also possible to specify
custom kernels.

01-12-22 Department of Information Science and Engineering 6

Algorithm
Click to edit
UsedMaster title style

Disadvantages of using SVM

• If the number of features is much greater than the number of samples,
avoid over-fitting in choosing Kernel functions and regularization term is
crucial.
• SVMs do not directly provide probability estimates, these are calculated
using an expensive five-fold cross-validation.

01-12-22 Department of Information Science and Engineering 7

Implementation
Click to edit Master title style

DESIGN AND DEVELOPMENT OF VIRTUAL OPERATING SYSTEM

01-12-22 8
Department of Information Science and Engineering
Implementation
Click to edit Master title style

01-12-22 DESIGN AND DEVELOPMENT OF VIRTUAL OPERATING SYSTEM 9

Department of Information Science and Engineering
Implementation
Click to edit Master title style

01-12-22 DESIGN AND DEVELOPMENT OF VIRTUAL OPERATING SYSTEM 10

Department of Information Science and Engineering
Click to edit Master title style
Thank You

Project Title | Department of Information Science and

09/01/2023 11
Engineering