Analysis of Lecturer Publication Performance Using Predictive Analytics and Reinforcement Learning(Case Study of a Public University in West Java)
Downloads
Lecturers are valuable and essential assets who serve as the cornerstone of higher education institutions in carrying out the Tridharma Perguruan Tinggi functions: education, research, and community service. They also play a vital role in supporting the implementation of the university’s strategic plans. Evaluating lecturers’ publication performance is a crucial aspect of assessing how well they fulfill their responsibilities. Research and publication are mandatory duties in the field of research and development, and the resulting publications contribute to scientific knowledge as well as to society and national progress.
XYZ University is one of the public universities in Indonesia that implements the Tridharma Perguruan Tinggi. By leveraging information technology and data-driven approaches in managing lecturer performance, the university can conduct more accurate and systematic evaluations.
This study aims to explore the application of predictive analytics by forecasting lecturers’ performance for the upcoming year based on data from the past five years. The goal is to provide an overview of publication productivity. The results of this study are expected to offer valuable insights to enhance the quality of lecturers’ publication performance, while also supporting the university’s efforts to improve academic quality and institutional reputation.
The ANOVA analysis results show that some demographic factors, such as academic rank and department or study program, do not have a significant impact on publication scores. However, there is a significant interaction between academic rank and department, indicating that the effect of position on publication scores may vary depending on the department in which the lecturer is based. These findings offer important insights for educational institutions in designing more tailored career development policies according to each department’s needs.
The use of larger and more heterogeneous data in predictive analytics models such as training history, teaching load, education level, and involvement in research or publication can help develop a people analytics model in the context of human resource management. This can generate more relevant and useful insights for decision-makers in educational institutions.
Reinforcement Learning (RL), particularly Q-Learning, is used to recommend appropriate interventions for lecturers based on predicted performance outcomes. Through this approach, the system can identify the most effective actions to support the improvement of future publication performance. Institutions are advised to adopt a differentiated approach in evaluating lecturer performance by considering department-specific characteristics and providing more tailored support according to each department’s needs.
Downloads
1. Andreanus, J., & Kurniawan, A. (2018). Sejarah, Teori Dasar dan Penerapan Reinforcement Learning: Sebuah Tinjauan Pustaka. Jurnal Telematika, 12(2), 113–118. https://doi.org/10.61769/telematika.v12i2.193
2. Arulkumaran, K., Deisenroth, M. P., Brundage, M., & Bharat, and A. A. (2017). Deep Reinforcement Learning. Reinforcement Learning for Sequential Decision and Optimal Control, 365–402. https://doi.org/10.1007/978-981-19-7784-8_10
3. Davenport, T. H. (2019). "Is HR the Most Analytics-Driven Function. https://hbr.org/2019/04/is-hr-the-most-analytics-driven-function
4. Hasibuan. (2016). Manajemen Sumber Daya Manusia. Penerbit Bumi Aksara.
5. Indiyati, D. (2018). The role of organisational culture, intellectual capital and competitive advantage in supporting the government policies in education. International Journal of Economic Policy in Emerging Economies, 11(1–2), 68–82. https://doi.org/10.1504/IJEPEE.2018.091028
6. Indiyati, D., Ghina, A., & Romadhona, A. F. (2021). Human Resource Competencies, Organizational Culture, and Employee Performance. International Journal of Science and Society, 3(1), 1–10. https://doi.org/10.54783/ijsoc.v3i1.251
7. Indiyati, D., Yulianti, E., Yunyun, M., & Ramdhany, M. A. (2016). Personality as a determinant of the performance of lecturers. International Journal of Applied Business and Economic Research, 14(10), 6165–6180.
8. Jamarani, A., Haddadi, S., Sarvizadeh, R., Haghi Kashani, M., Akbari, M., & Moradi, S. (2024). Big data and predictive analytics: A sytematic review of applications. In Artificial Intelligence Review (Vol. 57, Issue 7). Springer Netherlands. https://doi.org/10.1007/s10462-024-10811-5
9. Naeem, M., Rizvi, S. T. H., & Coronato, A. (2020). A Gentle Introduction to Reinforcement Learning and its Application in Different Fields. IEEE Access, 8, 209320–209344. https://doi.org/10.1109/ACCESS.2020.3038605
10. Nasril, F., Indiyati, D., & Ramantoko, G. (2021). Talent Performance Analysis Using People Analytics Approach. Budapest International Research and Critics Institute (BIRCI-Journal): Humanities and Social Sciences, 4(1), 216–230. https://doi.org/10.33258/birci.v4i1.1585
11. Panda, K., & Agrawal, S. (2024). Predictive Analytics: An Overview of Evolving Trends and Methodologies. The Journal of Scientific and Engineering Research, 8(May), 175–180.
12. Pişirgen, A., Öztunç, F., & Peker, S. (2025). Examining scholar-level publishing performance across bibliometric databases by cluster analysis. Information Discovery and Delivery, February 2024. https://doi.org/10.1108/IDD-02-2024-0031
13. Putri, R. K., & Hertina, D. (2019). Iklim Akademik Dan Dukungan Organsasi Pengaruhnya Terhadap Berbagi Pengetahuan Implikasinya Pada Kinerja Publikasi Ilmiah Dosen. Media Manajemen Jasa, 6(1), 81–99. https://doi.org/10.52447/mmj.v6i1.1399
14. Sin, K., & Muthu, L. (2015). "Application of Big Data in Education Data Mining and Learning Analytics – a Literature Review ". ICTACT Journal on Soft Computing, 05(04), 1035–1049. https://doi.org/10.21917/ijsc.2015.0145
15. Soegoto, E. S., Indiyati, D., & Marhaliyyah, S. A. (2017). The Effect of “The Big Five Model” Personality on Employee’s Performance at Aviation Manufacturing. Journal of Engineering and Applied Science, 12(2), 253–258.
16. THUNNISSEN, M., & GALLARDO GALLARDO, E. (2017). Talent Management in Practice: An Integrated and Dynamic Approach. Emerald Publishing Limited. https://doi.org/10.1108/9781787145979
17. Utomo, A., Indiyati, D., & Ramantoko, G. (2021). Talent Acquisition Implementation with People Analytic Approach. Budapest International Research and Critics Institute (BIRCI-Journal): Humanities and Social Sciences, 4(1), 204–215. https://doi.org/10.33258/birci.v4i1.1584
18. Vuong, T. T., Nguyen, H. K. T., Ho, T. M., Ho, T. M., & Vuong, Q. H. (2018). The (In)significance of socio-demographic factors as possible determinants of vietnamese social scientists’ contribution-adjusted productivity: Preliminary results from 2008–2017 scopus data. Societies, 8(1). https://doi.org/10.3390/soc8010003
19. Wardhana, A., Sari, A. P., Limgiani, Gunaisah, E., Suroso, Mukhsin, M., Yanti, N., Siagian, A. O., Herawati, M., Sattar, Rinda, R. T., & Harto, B. (2022). MANAJEMEN KINERJA (KONSEP, TEORI, DAN PENERAPANNYA).
Copyright (c) 2025 Ervin E Khoeruman, Dian Indiyati, Gadang Ramantoko
This work is licensed under a Creative Commons Attribution 4.0 International License.
