Integrated shannon entropy and COPRAS optimal model-based recommendation framework.

Multi-criteria decision-making (MCDM) techniques are increasing in product recommendation decisions, which typically entail several factors. This study aims to demonstrate the application of a novel strategy based on MCDM techniques as the core element of a consumer Decision Support System by suggesting the most appropriate items from a given set of alternatives. Ranking products based on online product ratings and consumer preferences is an important area of study, but there are currently few studies on this topic. This paper proposes a method for ranking products using multi-attribute online ratings. We propose a novel mobile recommendation-ranking system-based (MCDM) method to recommend the best alternative. Our proposed model differs from previous works in the following ways: (a) Rating information of each feature is used to identify user preferences and complementary criteria; (b) Criteria weights are determined by Shannon entropy (c) The complex proportional assessment method is employed to rank the alternatives and solve the best mobile recommendation problem. (d) The sensitivity study results showed that the rankings produced by the various MCDM approaches were highly consistent with the rankings of the evaluated compromise candidates. Demonstration of the proposed approach through a mobile phone selection case study. In our experiments, we have found that our approach provides a reliable ranking while reducing time and space complexity, indicating that our optimization model is accurate and efficient. With its superior product comparison skills and ability to offer a recommendation to the user as a final ranking of alternatives, a decision-making system like this may prove to be the optimal long-term answer for e-commerce sites and websites. [ABSTRACT FROM AUTHOR]