Predicting Purchases based on Social Network Ads using Support Vector Classifier in Python

By Jahnavi Ravi

In this project, we will predict whether an individual purchases a product or not only based on Social Network Advertisements using Support Vector Classifier in Python.

In this project, "Predicting purchases based on Social Network Ads", we will predict whether a person purchases a product or not based on the Social Network Advertisement the person had seen.

Our Dataset consists of 400 rows and 5 columns.

A Supervised Machine Learning model known as Support Vector Classifier is used on our Dataset to predict whether an individual purchases a product or not.

This Machine Learning model gave us a training accuracy of 78% and a testing accuracy of 75%.

The dataset is undersampled so we used a method known as SMOTE to make the dataset balanced and to get a better accuracy. After using the SMOTE method, the Machine Learning model gave us a training and testing accuracy worth 72% and 76% respectively.