Employability Prediction of Engineering Graduates using Machine Learning Algorithms

Abstract

Number of graduates produced in each year by higher education institutions is increasing. Thus prediction of employability of graduate’s plays a vital role for any industry for proper talent acquisition and Utilization and also it helps students in identifying the qualification and skills that they need to improve, before completion of degree to get desired jobs. In this Digital Revolution, informal learning and skill enhancements is happening in unconditional method, relating and converging all this learning’s to the employability rate is one of a biggest issue. The main objective is to address this issue by predicting and forecasting the skill acquisition continuously and mapping to industry needs using machine learning Algorithms. The proposed work used different machine learning algorithms like Logistic Regression, Decision tree, k-nearest neighbor, Support Vector Machine and Naïve Bayes for building model where ANN classifier resulted with the highest accuracy of 87.42%. This research would be helpful for all the organization including government, Private and corporations, including students and teachers for employability prediction.

Undergraduate engineering students employment prediction using hybrid approach in machine learning

“…Lau et al [16] has presented a method with both conservative numerical analysis and neural network modelling for prediction of students performance. It [17], [18] tried to forecast the placements and results of programming competitions through machine learning without complicated evaluation. Descriptive variables used for machine learning are classified into different categories.…”