Job Success Prediction: An Exploration of Machine Learning and Deep Learning in Bangladesh

Abstract

Unemployment is one of the critical challenges in Bangladesh, with an approximate unemployment rate of 4.20%. However, over the past year, more than 8 lakh graduates from public and private universities entered the job market. This research exposes the machine learning and deep learning algorithms to address issues related to job success rate. By employing ensembled learning-based algorithms the study achieves an impressive accuracy rate of 95% that significantly outperforms traditional methods. This methodology aims to help employers to identify their ideal employees and attract candidates who can be a good fit for the industry. Therefore, we aspire to help institutions in redesigning their curriculum that will help students to prepare for the market needs. This research holds immense significance for the country, not only by addressing the employment gap but also by enhancing the overall job market. Through the development of computational methods, the study aims to improve the unemployment crisis by addressing problems like shortage of skill, while accelerating the socioeconomic aspect of the country. The integration of predictive analysis within the hiring process will benefit both companies and colleges in the study-to-work transition. Moreover, deploying such system in Bangladesh has great potential to overcome social and economic challenges, paving the way for a more prosperous and stable future.