An Intelligent Recommendation System to Evaluate Teaching Faculty Performance using Self Adaptive HMM and PSO

Abstract

The addition of recommender systems has completely changed the landscape of digital marketing. The use of recommender systems in digital marketing, e-commerce, entertainment, and healthcare, among other industries, has greatly increased business. The right ideas have improved ease of usage and user experience as well. Nonetheless, there hasn't been much research done on the use of recommender systems in the field of education. This paper suggests a recommender system based on machine learning to provide a framework of suggestions for the teaching faculty based on different performance metrics. In terms of improving students' academic and research performance, it can have a significant impact on the education system as a whole. The accurate recommendation in this work has been achieved by the usage of self-adaptive HMM. Particle swarm optimization (PSO) has been used to optimize the tuning parameters in order to lower the model's temporal complexity. The recommendation in this work has been derived through the use of collaborative filtering. Through the experimental investigation, the suggested systems' performance was confirmed, and it was discovered that their accuracy was greater than 90%.