A Model for Investment Type Recommender System based on the Potential Investors’ Demographic and feedback using ANFIS
Asefeh Asemi, Asefeh Asemi, Andrea Kő · Research Square · 2023
Abstract Due to advances in investment recommender systems, the demand for the development of such technologies has increased. The study aimed to present a novel investment recommender system model based on the potential investors’ demographic data and their feedback using fuzzy neural inference solutions. Qualitative and quantitative methods were used in this research. In the proposed model, by combining the experts' knowledge and potential investors’ demographic data, the investment type is present by the adaptive neuro-fuzzy inference recommender system. The model is processed in three steps. These steps are, respectively, data collection, data analysis, and decision-making. This model is implemented in JMP and MATLAB. In a general format, this study provides a framework for investment recommender systems. Specifically, this study shows how to provide relevant and accurate recommendations for the most suitable type of investment for potential and actual investors in the form of this general framework.