Machine Learning Based Classification on Factors Used for Identifying Competency Gap In Engineering Students In Thanjavur District

The quantity of graduates generated annually by education institutions is on the rise. The prediction of graduates' employability is of significant importance to industries as it facilitates effective talent acquisition and use. Additionally, it assists students in recognizing the qualifications and abilities they need to enhance prior to completing their degrees in order to secure desired employment opportunities. During the current era of the Digital Revolution, there is a notable occurrence of informal learning with skill development taking place in an unrestricted manner. However, a significant challenge is in effectively connecting and aligning these acquired knowledge and skills with the overall employability rate. The primary aim is to effectively tackle this matter by employing machine learning algorithms to continuously predict and forecast the ongoing skill acquisition and align it with the demands of the industry. The study included various machine learning methods, including Logistic Regression (LR), Decision tree (DT), k-nearest neighbor (K-NN), Support Vector Machine (SVM), and Naïve Bayes (NB), to construct the model. This research holds potential benefits for various entities, encompassing governmental bodies, private enterprises, and businesses, as well as individuals such as students and educators, with the aim of enhancing employability.