Key points are not available for this paper at this time.
Our study is a comprehensive examination of the existing literature pertaining to algorithmic trading and its temporal progression in a framework driven by technology development. A total of 4552 papers were analyzed, spanning the period from 1990 to 2023. Performance metrics evaluation and science mapping approaches were utilized in this study. The data was obtained from the Scopus database, and the analysis was conducted using the Biblioshiny environment. The research landscape has undergone significant changes in recent years due to advancements in data-driven technology and the implementation of sophisticated algorithms such as machine learning, deep learning, and genetic algorithms. The shift in research interest has been particularly pronounced in the last decade compared to earlier periods. The most significant contribution in terms of production is associated with authors who are affiliated with the People's Republic of China. Another significant discovery is the limited knowledge dissemination and collaboration among scholars, as seen by the examination of co-authorship in academic papers. In relation to the conceptual framework of the study domain, we have identified two primary trajectories, specifically financial markets, and energy markets, whereby the utilization of deep learning techniques has garnered significant attention. • Global interest in algorithmic trading is surging, evidenced by a steady increase in published research. • Machine learning and deep learning technologies are transforming financial and energy markets. • Key areas are portfolio optimization, high-frequency trading, machine learning applications, and transaction optimization. • Algorithmic trading expands beyond traditional finance to environmental sustainability, energy management, and blockchain. • Lack of researcher collaboration suggests a chance to share knowledge and progress science.
Horobeţ et al. (Wed,) studied this question.