FPE - AT: Faculty Performance Evaluation AI Tool Using a Reinforcement Learning Based System

View at publisher Summarise with VIRAT
Authors: Alexander R, Lavanya T, A Lakshana, Sameera Fathima G, Kavya N, Vishnu Raj R
Cited by: 0
References: 10

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The Faculty Performance -System is a application designed to initiative tackles and flaws in contemporary faculty evaluation procedures-often manual, subjective, and convoluted--by creating an AI-based standalone using RL to provide feedback on how to improve performance. The new faculty evaluation system gathers and antics ultimate data on individual faculty (student feedback, research output, attendance), performs RL by mapping performance states to potential improvements, and over time constantly learns through experimentation and exploitation”. Security architecture, automated reporting, and user experience design all contribute to optimizing access, transparency, scalability and continuous professional development. The timing of performance comparisons between the RL-based evaluation model and the traditional faculty evaluation process found that the RL was at an overall model accuracy 95.2% with a strong sensitivity 82% and specificity 86.1% and overall found that the RL model outperformed the Decision Tree 91%, CNN+DNN 93.4% and Hybrid Ensemble model 92.1%. Thus, demonstrating the potential of RL and indication of data-driven based faculty development.

Fields of Study & Subjects

AI and HR Technologies Online Learning and Analytics Educational Technology and Pedagogy

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
888–894
Publication date
21 January 2026
Language
EN