Ai-Based Predictive Modeling of Academic Job Satisfaction and Institutional Performance
Evidence From Private Universities in Bangladesh
Bibliographic Data
| ID | 19490150 |
|---|---|
| Authors | Md Rofiqul Islam (Guru Kashi University), Sandeep Kaur (0000-0002-4871-8586, Guru Kashi University) |
| Year | 2026 |
| Volume | 7 |
| Issue | 10s |
| Publication date | 2026-05-20 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | ShodhKosh: Journal of Visual and Performing Arts (JOURNAL) |
| Journal identifiers | ISSN: 2582-7472 • E-ISSN: 2582-7472 |
| Publisher | Granthaalayah Publications and Printers (PUBLISHER • IN) |
| DOI | 10.29121/shodhkosh.v7.i10s.2026.8224 |
| OpenAlex | W7161799191 |
| Language | EN |
| References cited | 17 |
Rapid expansion in number of private higher education institutions in Bangladesh has emphasized faculty members' satisfaction and organizational performance. While there is an increasing trend in applying AI technologies for managing human resources, empirical studies are limited that combine predictive machine learning algorithms with Bangladeshi private university field data. This quantitative cross-sectional research paper analyzes data from 420 academic faculties at 28 private universities and seven machine learning algorithms to address research gap. Proposed hybrid ensemble algorithm combining Random Forest and Extreme Gradient Boosting (XGBoost) achieves high classification accuracy of 91.4% in predicting job satisfaction, outperforming all benchmark algorithms. Adoption of AI tools, organizational environment, equitable remuneration, and professional development programs positively influence job satisfaction, whereas workload negatively affects it (β = -0.187, p
Empirical research · Job performance · Job satisfaction · Workload · Advanced Technologies in Various Fields · AI and HR Technologies · Organizational and Employee Performance
| Highly cited | No |
|---|