Bio-Inspired Meta-Learning(Student Performance Prediction)

  • Unique Paper ID: 203134
  • Volume: 12
  • Issue: 12
  • PageNo: 10124-10127
  • Abstract:
  • Educational institutions today face increasing pressure to support diverse learner populations with limited resources. Traditional assessment methods and static analytics tools often fail to provide timely, personalized insights, leading to delayed interventions, higher dropout rates, and suboptimal learning outcomes. This paper presents a web-based intelligent platform that leverages bioinspired meta learning for accurate student performance prediction and early risk detection. The system integrates evolutionary computation and swarm intelligence principles with meta learning algorithms to rapidly adapt to new student cohorts and learning contexts. Interactive dashboards provide clear visualizations of predicted outcomes, risk heatmaps, and intervention recommendations. Initial evaluations on benchmark educational datasets demonstrate 88–94% accuracy in academic risk prediction and 40–60% faster adaptation to new cohorts compared to conventional baselines, indicating strong potential for practical deployment in educational settings.

Copyright & License

Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

BibTeX

@article{203134,
        author = {Dr. Shah Saloni Niranjan and Bansode Ashish Shamrao and Darade Aniket Utreshwar and Sathe Atish Prabhakar},
        title = {Bio-Inspired Meta-Learning(Student Performance Prediction)},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {10124-10127},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=203134},
        abstract = {Educational institutions today face increasing pressure to support diverse learner populations with limited resources. Traditional assessment methods and static analytics tools often fail to provide timely, personalized insights, leading to delayed interventions, higher dropout rates, and suboptimal learning outcomes. This paper presents a web-based intelligent platform that leverages bioinspired meta learning for accurate student performance prediction and early risk detection. The system integrates evolutionary computation and swarm intelligence principles with meta learning algorithms to rapidly adapt to new student cohorts and learning contexts. Interactive dashboards provide clear visualizations of predicted outcomes, risk heatmaps, and intervention recommendations. Initial evaluations on benchmark educational datasets demonstrate 88–94% accuracy in academic risk prediction and 40–60% faster adaptation to new cohorts compared to conventional baselines, indicating strong potential for practical deployment in educational settings.},
        keywords = {Bioinspired Computing, Meta Learning, Student Performance Prediction, Educational Data Mining, Evolutionary Algorithms, Swarm Intelligence, Machine Learning, Web Application, Early Intervention, Personalized Learning.},
        month = {May},
        }

Cite This Article

Niranjan, D. S. S., & Shamrao, B. A., & Utreshwar, D. A., & Prabhakar, S. A. (2026). Bio-Inspired Meta-Learning(Student Performance Prediction). International Journal of Innovative Research in Technology (IJIRT), 12(12), 10124–10127.

Related Articles