AN EFFICIENT MACHINE LEARNING APPROACH FOR ACADEMICPERFORMANCE AND PLACEMENT PREDICTION

Abstract

Colleges and institutions allocate substantial resources to the placement process. The placement variables significantly influence the naming of institutions and the individuals who opt to attend. Consequently, educational institutions such as colleges and universities allocate substantial resources toward enhancing their programs to facilitate student employment. The objective of this paper is to evaluate student placement statistics from the preceding academic year, formulate informed projections regarding current student placement outcomes, and propose measures to enhance the placement rate within the educational system. This paper presents a methodology to assist educational institutions in selecting candidates for admission. When a student is correctly positioned, they can utilize historical data from prior students employed by the same organization to forecast the company's future performance. Machine learning employs a range of classification algorithms, such as the Naive Bayes Classifier and the K-Nearest Neighbors (KNN) model. These two algorithms categorize materials into specific categories. The dataset is utilized to evaluate the performance of the algorithms, which subsequently predict future events. The company's placement department may utilize the aforementioned framework to identify prospective candidates and assist them in concentrating their efforts on enhancing their technical and interpersonal skills.