TimeGPT’s Potential in Cryptocurrency Forecasting: Efficiency, Accuracy, and Economic Value
Open Access
- 10 September 2025
- journal article
- research article
- Published by MDPI AG in Forecasting
- Vol. 7 (3) , 48
Abstract
Accurate and efficient cryptocurrency price prediction is vital for investors in the volatile crypto market. This study comprehensively evaluates nine models—including baseline, zero-shot, and deep learning architectures—on 21 major cryptocurrencies using daily and hourly data. Our multi-dimensional evaluation assesses models based on prediction accuracy (MAE, RMSE, MAPE), speed, statistical significance (Diebold–Mariano test), and economic value (Sharpe Ratio). Our research found that the optimally fine-tuned TimeGPT model (without variables) demonstrated superior performance across both Daily and Hourly datasets, with its statistical leadership confirmed by the Diebold–Mariano test. Fine-tuned Chronos excelled in daily predictions, while TFT was a close second to TimeGPT for hourly forecasts. Crucially, zero-shot models like TimeGPT and Chronos were tens of times faster than traditional deep learning models, offering high accuracy with superior computational efficiency. A key finding from our economic analysis is that a model’s effectiveness is highly dependent on market characteristics. For instance, TimeGPT with variables showed exceptional profitability in the volatile ETH market, whereas the zero-shot Chronos model was the top performer for the cyclical BTC market. This also highlights that variables have asset-specific effects with TimeGPT: improving predictions for ICP, LTC, OP, and DOT, but hindering UNI, ATOM, BCH, and ARB. Recognizing that prior research has overemphasized prediction accuracy, this study provides a more holistic and practical standard for model evaluation by integrating speed, statistical significance, and economic value. Our findings collectively underscore TimeGPT’s immense potential as a leading solution for cryptocurrency forecasting, offering a top-tier balance of accuracy and efficiency. This multi-dimensional approach provides critical, theoretical, and practical guidance for investment decisions and risk management, proving especially valuable in real-time trading scenarios.Keywords
Funding Information
- Basic Research Program at the National Research University, Higher School of Economics (HSE University)
This publication has 15 references indexed in Scilit:
- Bitcoin Ordinals: Bitcoin Price and Transaction Fee Rate PredictionsIEEE Access, 2025
- Time-Series Cryptocurrency Forecasting Using Ensemble Deep Learning2023
- LSTM–GARCH Hybrid Model for the Prediction of Volatility in Cryptocurrency PortfoliosComputational Economics, 2023
- A short-term electric load forecast method based on improved sequence-to-sequence GRU with adaptive temporal dependenceInternational Journal of Electrical Power & Energy Systems, 2022
- Temporal Fusion Transformers for interpretable multi-horizon time series forecastingInternational Journal of Forecasting, 2021
- Nothing but noise? Price discovery across cryptocurrency exchangesJournal of Financial Markets, 2021
- A novel cryptocurrency price trend forecasting model based on LightGBMFinance Research Letters, 2020
- Exploring disorder and complexity in the cryptocurrency spacePhysica A: Statistical Mechanics and its Applications, 2019
- Comparing Predictive AccuracyJournal of Business & Economic Statistics, 2002
- Mutual Fund PerformanceThe Journal of Business, 1966