Proceedings of the International Education Conference
Integrating system dynamics into technology enhanced learning (TEL) infrastructure planning: a multifaceted approach for decision-making for technology forecasting with a simulation
Dr. Pregalathan Reddy
This article deals with a novel approach to the development of a recommendation system which was used in the recently completed doctoral thesis by the author. Recommendation systems follow the artificial intelligence (AI) machine learning (ML) approach (Singh 2020; Joshi 2023), which uses trained or untrained data sets to recommend something based on known criteria about the users’ preferences. This could be, for example, recommending a product based on previous purchases, or browsing history, or a related product based on the users’ stated interests. In one sense, recommendation systems also provide decision-making features, but in a different way, where the user is not in control or aware of the mechanics behind the suggestions made for them. An important distinction between the two systems is that the former uses aggregation as its main source of sentient suggestions, while the latter is much more transparent, and allows decision makers to be become more aware of the factors influencing their decisions. In this study the decision making system and recommendation system was architected to provide future scenarios based on user input, this real-time process facilitated recursive input by allowing the user to adjust parameters and run the simulation until the optimal scenario is obtained. This article will start with an introduction, followed by a summary of the relevant literature, and then the methodology used to develop the application, and then conclude with reflections on how well it worked to achieve its objectives.
keywords: artificial intelligence (AI), Decision-making features, future scenarios, machine learning (ML), recommendation system