Time-Series Stock Price Forecasting Based on Neural Networks: A Comprehensive Survey

As financial markets grow increasingly complex and volatile, time-series-based stock price forecasting has become a critical research focus in the field of finance. Traditional forecasting methods face significant limitations in handling nonlinear and high-dimensional data, while neural networks (NNs) have demonstrated great potential due to their powerful feature extraction and pattern recognition capabilities. Although several existing surveys discuss the applications of NNs in stock forecasting, they often lack a detailed examination of models that use time-series data as input and fail to cover the latest research developments. In response, this paper reviews relevant literature from 2015 to 2025 and classifies time-series-based stock forecasting methods into four categories: NNs, recurrent NNs (RNNs), convolutional NNs (CNNs), Transformers and other models. We analyze their performance under different market conditions, highlight strengths and limitations, and identify recent trends in model design. Our findings show that hybrid architectures and attention-based models consistently achieve superior forecasting stability and adaptability across volatile market scenarios. This survey offers a systematic reference for researchers and practitioners and outlines promising future research directions.