Abstract
PurposeThis study aims to endeavour to decode artificial intelligence (AI)-based tokens' complex dynamics and predictability using a comprehensive multivariate framework that integrates technical and macroeconomic indicators.Design/methodology/approachIn this study we used advance machine learning techniques, such as gradient boosting regression (GBR), random forest (RF) and notably long short-term memory (LSTM) networks, this research provides a nuanced understanding of the factors driving the performance of AI tokens. The study’s comparative analysis highlights the superior predictive capabilities of LSTM models, as evidenced by their performance across various AI digital tokens such as AGIX-singularity-NET, Cortex and numeraire NMR.FindingsThis study finding shows that through an intricate exploration of feature importance and the impact of speculative behaviour, the research elucidates the long-term patterns and resilience of AI-based tokens against economic shifts. The SHapley Additive exPlanations (SHAP) analysis results show that technical and some macroeconomic factors play a dominant role in price production. It also examines the potential of these models for strategic investment and hedging, underscoring their relevance in an increasingly digital economy.Originality/valueAccording to our knowledge, the absence of AI research frameworks for forecasting and modelling current aria-leading AI tokens is apparent. Due to a lack of study on understanding the relationship between the AI token market and other factors, forecasting is outstandingly demanding. This study provides a robust predictive framework to accurately identify the changing trends of AI tokens within a multivariate context and fill the gaps in existing research. We can investigate detailed predictive analytics with the help of modern AI algorithms and correct model interpretation to elaborate on the behaviour patterns of developing decentralised digital AI-based token prices.
Reference37 articles.
1. Volatility persistence in cryptocurrency markets under structural breaks;International Review of Economics and Finance,2020
2. Quantile price convergence and spillover effects among Bitcoin, Fintech, and artificial intelligence stocks;International Review of Finance,2023
3. NFTs and asset class spillovers: lessons from the period around the COVID-19 pandemic;Finance Research Letters,2022
4. Alessandretti, L., ElBahrawy, A., Aiello, L.M. and Baronchelli, A. (2018), “Machine learning the cryptocurrency market”, Complexity, available at: https://openaccess.city.ac.uk/id/eprint/19829/