Progress and prospects of data-driven stock price forecasting research
Review of stock price forecasting methods using statistical, machine learning, and deep learning approaches, highlighting challenges and future directions.
What it examines
This survey reviews data-driven stock price forecasting methods, categorizing them into statistical analysis, traditional machine learning, and deep learning approaches. It also examines methods based on numerical data and those combining numerical and textual data, aiming to identify research challenges and future directions.
What it concludes
The study concludes that deep learning and combinatorial models are promising for stock price forecasting. Future research should focus on integrating textual data and improving model accuracy. Potential applications include better investment strategies and risk management in stock markets.
Evidence objects
The study concludes that deep learning and combinatorial models are promising for stock price forecasting. Future research should focus on integrating textual data and improving model accuracy. Potential applications include better investment strategies and risk management in stock markets.
key_findings bullet 1 · key_findings · validation V0
Raw abstract and provenance
With the rapid development of social economy and the continuous improvement of stock market, stock investment has become more and more widely concerned. Stock price prediction has become an important research direction in the field of cognitive computing in engineering. Data-driven stock price forecasting aims to predict future stock price trends based on historical values and textual data, which can effectively help people reduce risks and improve returns in the process of stock investment. The article reviews the literature on stock price forecasting methods, and classifies stock price forecasting methods from two different perspectives of model and feature. According to different model angles, the existing stock price prediction methods can be divided into statistical analysis methods, traditional machine learning methods and deep learning methods. According to different characteristic angles, the existing stock price prediction methods can be divided into those based on numerical data and those based on text mixed with numerical data. Finally, we summarize the research challenges faced by stock price prediction and provide future research directions.
Source row: 1616 · abstract type: unknown