Student Dropout Analysis in Higher Education and Retention by Artificial Intelligence and Machine Learning

Student dropouts are a long-standing, substantial issue in academia that has never received meaningful attention globally. Numerous research studies have indisputably demonstrated that this issue impacts both developed and developing countries, including India. It is now required to assess it and proceed appropriately based on the results. This study’s objectives included analyzing and evaluating the effects of student dropouts in higher education and investigating how artificial intelligence (AI) and machine learning (ML) may help students to continue their education. For dropouts, five colleges were chosen, and data on dropouts were gathered. The administrative team, students, and instructional staff were the target audiences for the questionnaire. Utilizing the information acquired by the five colleges, interviews with targeted individuals, and literature analysis effectively made the study straightforward and more efficient. Information was gathered from colleges of various faculties in terms of gender, programmes, categories, and demographics. The correctness of the information gathered was then evaluated for the quantitative analysis design using the t test, ANOVA test, regression correlation, and descriptive analysis. Most of the findings were in line with expectations. Results were found to be more than expected in terms of gender and demographics. Furthermore, in accordance with the results of the analysis, AI and ML approaches were examined to improve college student retention. Then, it was discovered that both of these methods were effective and trustworthy for preventing dropouts in today's world, including India. © 2024, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.