Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ International Journa...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Article . 2026
License: CC BY
Data sources: ZENODO
ZENODO
Article . 2026
License: CC BY
Data sources: Datacite
ZENODO
Article . 2026
License: CC BY
Data sources: Datacite
versions View all 3 versions
addClaim

AI-Powered Token Prediction and Automated Trading in Web3 Using On-chain Data and Decentralized Exchanges

Authors: Edward N., Udo; Goodness E., Mbakara;

AI-Powered Token Prediction and Automated Trading in Web3 Using On-chain Data and Decentralized Exchanges

Abstract

This article investigates the efficacy of implementing an AI-powered automated trading system on the blockchain using advanced machine learning algorithms and smart contract technology. The work addresses the challenges of cryptocurrency market volatility, the need for real-time decision making and the limitations of traditional trading approaches that often result in suboptimal returns and exposure to increased risk. This work develops a comprehensive trading platform that combines Long Short-Term Memory (LSTM) neural networks, Q-Learning reinforcement learning algorithms and blockchain-based smart contracts to create an autonomous, intelligent trading system. The methodology follows a multi-layered approach that integrates real-time market data collection from CoinGecko and Snowtrace APIs, advanced AI model training using TensorFlow.js, and smart contract deployment on the Avalanche C-Chain using Hardhat and OpenZeppelin libraries. LSTM model is used for price prediction and Q-Learning agent is used for trading strategy optimization, while comprehensive risk management is implemented using Value at Risk (VaR) calculations, portfolio rebalancing algorithms and automated stop-loss mechanisms. The trading execution is facilitated through direct integration with Pangolin DEX smart contracts to ensure decentralized and trustless trade execution. The performance of the system is evaluated using a sophisticated backtesting engine with Monte Carlo simulations, comparing the AI-driven strategy against traditional buy-and-hold approaches. The performance metrics used were Sharpe ratio, maximum drawdown, win rate, and total return. The AI-powered token prediction system demonstrates a superior performance due to its ability to process complex, non-linear market patterns and adapt to changing market conditions through reinforcement learning, and execute trades with minimal latency through blockchain integration. The findings are expected to provide cryptocurrency traders and institutional investors with a robust and automated trading solution that leverages the benefits of both artificial intelligence and blockchain technology for improved investment outcomes and risk management.

Related Organizations
Keywords

Artificial Intelligence, Automated Trading, Blaockchain, Cryptocurrency, Decentralized exchanges, LSTM, Reinforcement learning algorithm, Smart Contract, Token Prediction, Web3

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green
gold