Forecasting Non-Fungible Token (NFT) Market Volatility Through Hybrid GARCH–LSTM Models
- 1School of Economics, University of International Business and Economics, Beijing 100029, China
- 2Interdisciplinary Graduate School, Nanyang Technological University, Singapore 637371, Singapore
Abstract
This study forecasts price volatility in the non-fungible token (NFT) digital asset market. We develop a hybrid forecasting framework that integrates long short-term memory (LSTM) networks with a set of generalized autoregressive conditional heteroskedasticity (GARCH)-type models. Using daily data, we conduct a comparative evaluation of nine competing forecasting models across five representative NFT submarkets (i.e., OpenSea, Atomic, CryptoKitties, Gods Unchained, and Decentraland). Employing standard error metrics (RMSE, MSE, MAE, and RAE), a robust loss QLIKE function, and the Diebold–Mariano (DM) statistical test, our empirical results show that the hybrid GARCH-TGARCH-LSTM model achieves the lowest error metrics. Compared with the baseline LSTM model, it achieves RMSE reductions of approximately 14% for Atomic, 49% for CryptoKitties, 13% for Decentraland, 8% for Gods Unchained, and 29% for OpenSea. Furthermore, the EGARCH conditional variance specification underperforms the TGARCH counterpart in the most NFT submarkets. This finding suggests that combining the volatility clustering characteristics captured by standard GARCH models with the asymmetric volatility features captured by TGARCH models improves forecasting performance. This study contributes to research on hybrid deep learning approaches to volatility forecasting in emerging digital asset markets.
Related
- A Design Concept of Forecasting Software for Normalized Vector Autoregressions with Fat Tails and Stochastic Volatility
- Volatility-Corrected Prediction Intervals: Locally Adaptive Uncertainty Quantification for Probabilistic Time-Series Forecasting
- Neural Realized Measures: Forecast-Supervised Intraday Aggregation for Volatility Forecasting
- Compiling and forecasting implied volatility surfaces via survey sampling, tempered inverse-probability sequence learning, and causal activity clocks
- Bayesian inference, on-line forecasting and model choice for large VAR models with Cholesky stochastic volatility
BibTeX
@article{zhang2026forecasting,
title = {{Forecasting Non-Fungible Token (NFT) Market Volatility Through Hybrid GARCH–LSTM Models}},
author = {Jiemin Zhang and Shulin Liu and Mengzhong Ma},
journal = {Mathematics},
year = {2026},
month = nov,
doi = {10.3390/math14214024},
url = {https://www.mdpi.com/2227-7390/14/21/4024},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Forecasting Non-Fungible Token (NFT) Market Volatility Through Hybrid GARCH–LSTM Models
AU - Jiemin Zhang
AU - Shulin Liu
AU - Mengzhong Ma
PY - 2026
DA - 2026/11/04
JO - Mathematics
DO - 10.3390/math14214024
UR - https://www.mdpi.com/2227-7390/14/21/4024
AB - This study forecasts price volatility in the non-fungible token (NFT) digital asset market. We develop a hybrid forecasting framework that integrates long short-term memory (LSTM) networks with a set of generalized autoregressive conditional heteroskedasticity (GARCH)-type models. Using daily data, we conduct a comparative evaluation of nine competing forecasting models across five representative NFT submarkets (i.e., OpenSea, Atomic, CryptoKitties, Gods Unchained, and Decentraland). Employing standard error metrics (RMSE, MSE, MAE, and RAE), a robust loss QLIKE function, and the Diebold–Mariano (DM) statistical test, our empirical results show that the hybrid GARCH-TGARCH-LSTM model achieves the lowest error metrics. Compared with the baseline LSTM model, it achieves RMSE reductions of approximately 14% for Atomic, 49% for CryptoKitties, 13% for Decentraland, 8% for Gods Unchained, and 29% for OpenSea. Furthermore, the EGARCH conditional variance specification underperforms the TGARCH counterpart in the most NFT submarkets. This finding suggests that combining the volatility clustering characteristics captured by standard GARCH models with the asymmetric volatility features captured by TGARCH models improves forecasting performance. This study contributes to research on hybrid deep learning approaches to volatility forecasting in emerging digital asset markets.
SN - 2227-7390
ER -