The ability of artificial neural network (ANN) models to predict future stock prices has been the focus of extensive recent research, particularly in comparison to other models. However, recent literature reviews have yet to comprehensively examine the current state of research on ANN models regarding hybrid model integration, feature engineering and selection strategies, uncertainty quantification and risk assessment, transfer learning for market adaptability, and the challenges they face in predicting stock prices. This paper aims to fill this gap by critically reviewing the efforts made to explore the ability of ANN models to predict future stock prices. Using a methodology based on variables analysis, method analysis, software context, and a conclusion, this paper synthesizes 21+ papers published between 2011 and 2023. The findings indicate that ANN models have a strong potential for predicting stock market prices although there is room for improvement in some areas. This paper's findings will be of interest and use to academics and practitioners interested in ANN models for stock price prediction, particularly in development initiatives related to financial technology.