Systematic Review and Propose an Investment Type Recommender System Using Investor’s Demographic Using ANFIS

Abstract

The development of investment recommender systems (IRSs) has increased due to advancements in technology. This study aims to present a new model for IRSs based on potential investor’s demographic data and feedback, using fuzzy neural inference solutions. Both qualitative and quantitative methods were used in this research, including a review of past studies and analysis of data through Scopus analyze tool, Voyant, and VosViewer. The proposed model combines expert’s knowledge with demographic data to present the most suitable type of investment through an adaptive neuro-fuzzy inference recommender system. The model is processed in several steps, including clustering investment data types in JMP and proposing the results through MATLAB. This study provides a framework for IRSs that can give relevant and accurate recommendations for potential and actual investors, thus enhancing their investment experience.