Witwisit Kesornsit

Work place: Data Analytics and Business Intelligence, Compliance Risk Management Division, Kasikorn Bank, Bangkok, Thailand

E-mail: witwisit.kes@gmail.com


Research Interests: Machine Learning, Data Mining, Data Analysis


Witwisit Kesornsit is currently working in Data Analytics and Business Intelligence, Compliance Risk Management Division, Kasikorn Bank, Bangkok, Thailand. His research interests include Data Mining, Machine Learning, and Data Analytics.

Author Articles
Predictive Model for Academic Training Course Recommendations Based on Machine Learning Algorithms

By Karanrat Thammarak Witwisit Kesornsit Yaowarat Sirisathitkul

DOI: https://doi.org/10.5815/ijmecs.2024.03.02, Pub. Date: 8 Jun. 2024

Given the significance of online education, a recommendation system provides a good opportunity to advise the most suitable courses according to their interest and preferences. This study proposes an academic training course recommendation that applies machine learning algorithms to provide the most appropriate 21st century learning based on individual preferences.  To address the issue of imbalanced classification, the eight development skills are grouped into three skill categories during the preprocessing stage. In the classification step, several machine learning algorithms, including Decision Tree, Random Forest, Gradient Boosting, and Backpropagation Neural Network, are used to create a predictive model, which is then compared to the results of Logistic Regression. These machine learning algorithms predict the skill group based on the teacher preference data, which results in the suggestion of training courses that are customized to the teacher's profile. According to the experimental results, all machine learning algorithms showed superior prediction performance than Logistic Regression. The Backpropagation Neural Network exhibits high precision, reaching up to 78%, and demonstrates the best performance for the testing data. This research demonstrates that machine learning algorithms significantly improve the accuracy and efficiency of the training course recommendation. On this basis, this training course recommendation system will be advantageous to both the teachers looking for up- and reskilling training courses for 21st century learning. Additionally, it will be appropriate for training course designers to establish training courses that develop 21st-century learning in accordance with participants’ interests and professional development.

[...] Read more.
Other Articles