History, Current State, and Prospects for the Development of Automated Trading Systems in the Stock Market
Year: 2025
Type: article
Abstract: The paper deals with the rapid development of automated trading systems, which requires a systematisation of knowledge about the methods, models and technologies they use. The subject of the study is automated trading on the stock market. The study of the history of automated trading systems allows to formulate the main hypothesis of the study: the development of automated trading systems based on quan-tum computing and machine learning methods can significantly increase the efficiency of algorithmic trad-ing. The study aims to summarise the existing knowledge, models and methods used by stock market partic-ipants in trading robots, to study and identify possible directions of their future development. To achieve the research objective, the corpus of scientific literature devoted to automated trading, machine learning and quantum computing will be studied. The research uses historical, systemic and comparative analysis, expert judgement and statistical methods. The authors outline the main stages in the development of automated trading systems on the stock market. They specify the software part of the automated trading system and propose the classification of al-pha and risk models used in algorithmic trading. The study reveals the problems of modern quantum com-puters, which do not allow using these machines for full automation of trading decisions. It shows that while quantum computing algorithms are developing faster than quantum computers themselves, the solu-tion to some applied problems in finance is already being tested on a new type of computing machine. Fi-nancial market practitioners can use the results of the research to determine the directions of development of the automated trading systems they use, and scientists can identify promising areas of scientific research.
DOI: 10.14529/em250107
Author: Dmitry Kandaurov
Institution: South Ural State University
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: diamond
OpenAlex ID: W4409272848