Risk-Optimized Crypto Trading Bot
1
Issued Date
2024-01-01
Resource Type
Scopus ID
2-s2.0-85216537427
Journal Title
19th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2024
Rights Holder(s)
SCOPUS
Bibliographic Citation
19th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2024 (2024)
Suggested Citation
Sivaraksa M., Kaihatsu R., Phisithaporn K., Rusuwannakul P., Pritranun T. Risk-Optimized Crypto Trading Bot. 19th International Joint Symposium on Artificial Intelligence and Natural Language Processing, iSAI-NLP 2024 (2024). doi:10.1109/iSAI-NLP64410.2024.10799212 Retrieved from: https://repository.li.mahidol.ac.th/handle/123456789/105280
Title
Risk-Optimized Crypto Trading Bot
Author's Affiliation
Corresponding Author(s)
Other Contributor(s)
Abstract
Cryptocurrency has become one of the biggest digital assets. One of the problems arising in the cryptocurrency market is that the investors/traders cannot maximize the profit due to the volatility and ability to accurately the future price. Moreover, the investor must monitor the progress 24 hours to maximise profits and prevent lossesThis paper introduces a bot that can work 24 hours and can monitor, predict and trade so that it is best to maximize the benefits. Our tool provides suggestions for buy and sell point and price prediction using random forest regression. The regression results show a high r-squared value of more than 0.9.The trading bot also provides three different trading strategies, which are aggressive, conservative, and moderate modes which suit different types of users. The aggressive mode is more suitable for users who prefer higher risks with an opportunity for high returns. On average, the aggressive mode yields the best profits but can result in huge losses in return. However, the conservative strategy provides the lower risk strategy, which creates minimum loss but results in less benefit. Finally, the moderate strategy provides a combination of the two strategies. The result shows that the moderate strategy is the most balanced strategy between profit and loss.This paper presents a comprehensive overview of the development process, from system architecture to the deployment of the trading bot. It also evaluates the performance of the model using various metrics such as r-squared(R2) and mean squared error (MSE) and highlights the potential risks and limitations of automated trading systems.