Treffer: Hybrid Cyber-Physical Stock Exchange Robot with Artificial Intelligence and Fuzzy Module.

In modern conditions, the use of trading algorithms based on artificial intelligence, as well as mathematical algorithms, including fuzzy ones, which operate as a single system, which ensures the efficiency of trading operations, is very relevant. Despite a significant number of scientific papers on this topic, individual aspects have not been sufficiently studied, and there are some gaps that require additional research. The relevance lies in the fact that the algorithms of hybrid CP systems are increasingly used in exchange trading, increasing its efficiency. The scientific novelty lies in the fact that the authors proposed the simultaneous use of two algorithms in the trading bot: the deep learning model "Random Forest" (DL) and the fuzzy learning algorithm, which operate as a single system (GCFS). During the study, an exchange trading bot, a hybrid cyber-physical system, was formed. This study aims to develop a hybrid cyber-physical system (HCS) containing a DL model and a fuzzy algorithm. Methods used in the study: hybrid cyber-physical system, deep learning model, and fuzzy algorithm. The significant conclusion is that the goal has been achieved and the cyber-physical system has been successfully developed. One of the factors of the bot's effective trading is the low error in asset price forecasting. For example, the average absolute error of the MCE does not exceed USD 0.9495 or 0.11%. Fuzzy provides profit, in our example $2.10 positive margin of $2.10, instead of a negative margin of $1.61, for 11 minutes of trading one contract. [ABSTRACT FROM AUTHOR]

Copyright of International Journal of Technology is the property of Universitas Indonesia, International Journal of Technology and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)