An Ensemble Learning Based Career Prediction Model

Selecting an appropriate career path is a pivotal decision, and in today’s world of expanding career choices, it has become increasingly daunting for individuals seeking employment. Unfortunately, resources like career counsellors are often limited in availability and can be expensive, creating barriers for many students to access them. In response to this challenge, we suggest the development of a prediction model for a career that employs an ensemble learning technique i.e. voting classifier which includes a classifier such as K-Nearest Neighbour, Support Vector Machine, Stochastic Gradient Descent, Random Forest, and Decision Tree. The first set of voting classifier includes the K-nearest neighbour, Support Vector Machine, Stochastic Gradient Descent, and Decision Tree and the second set B contain the K-nearest neighbour, Support Vector Machine, Stochastic Gradient Descent, and Random Forest. The set with the highest accuracy and lowest fluctuation is set A with classifier K-Nearest Neighbour, Support Vector Machine, Stochastic Gradient Descent, and Decision Tree with an accuracy of 89.45%.