Implementasi Arsitektur Temporal Fusion Transformer (Tft) Berbasis Interpretable Multi-Horizon Forecasting Prediksi Volatilitas Harga Aset Kripto Solana

Mahmudi Husain Hasbullah; Ghufron Ghufron

doi:10.58192/populer.v5i3.5520

Authors

Mahmudi Husain Hasbullah Universitas Islam Sultan Agung
Ghufron Ghufron Universitas Islam Sultan Agung

DOI:

https://doi.org/10.58192/populer.v5i3.5520

Keywords:

Crypto Assets, Explainable AI, Generative AI, Solana, Temporal Fusion Transformer

Abstract

The cryptocurrency market, specifically Solana (SOL), exhibits extreme volatility that is difficult for conventional algorithms to predict accurately. Additionally, advanced Deep Learning models often act as black-boxes. This study implements the Temporal Fusion Transformer (TFT) architecture for robust and interpretable multi-horizon volatility prediction of SOL/USDT. High-frequency historical data (1-hour intervals) was acquired via Binance API from January 2023 to December 2024. Data preprocessing included technical indicator feature engineering, Z-Score normalization, and chronological data splitting. Hyperparameters were optimized using Optuna. The TFT architecture performed exceptionally, achieving a Root Mean Squared Error (RMSE) of 2.5191 USDT and a Coefficient of Determination (R2) of 0.9987. Probabilistically, the model successfully mapped risk ranges with a Weighted Mean Quantile Loss of 0.4629. Explainable AI analysis revealed that predictions were heavily influenced by historical closing price, RSI, Volume, and MACD. Innovatively, TFT outputs were integrated into a Decision Support System utilizing Google Gemini 2.5-Flash to automatically generate market analysis narratives. In conclusion, this study produced a robust forecasting model, successfully resolving the black-box problem into a transparent virtual analyst assistant.

References

Cerqueira, V., Torgo, L., & Mozetič, I. (2020). Evaluating time series forecasting models. arXiv. https://doi.org/10.48550/arXiv.2103.10936

Charfeddine, L., Benlagha, N., & Maouchi, Y. (2019). Investigating the dynamic relationship between cryptocurrencies and conventional assets: Implications for financial investors. Economic Modelling, 85, 126–141. https://doi.org/10.1016/j.econmod.2019.05.016

Chen, J., & Tsai, Y. (2020). Encoding candlesticks as images for pattern classification using convolutional neural networks. Financial Innovation, 6, Article 26. https://doi.org/10.1186/s40854-020-00187-0

Chicco, D., Warrens, M. J., & Jurman, G. (2021). The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Computer Science, 7, e623. https://doi.org/10.7717/peerj-cs.623

Derbentsev, V. (2020). Forecasting cryptocurrency prices using ensembles-based machine learning approach. In 2020 IEEE International Conference on Problems of Infocommunications. Science and Technology (PIC S&T) (pp. 707–712). IEEE. https://doi.org/10.1109/PICST51311.2020.9468090

Fang, F., Ventre, C., Basios, M., Kanthan, L., Martinez-Rego, D., Dervilis, N., & Bourdais, G. (2021). Cryptocurrency trading: A comprehensive survey. Financial Innovation, 8, Article 13. https://doi.org/10.1186/s40854-021-00321-6

Gavhane, S., et al. (2026). Cryptocurrency price prediction using sentiment analysis. International Journal of Engineering Research & Technology (IJERT), 15(4), 1–10. https://doi.org/10.5281/zenodo.20687167

Jaquart, P., Dann, D., & Weinhardt, C. (2021). Short-term bitcoin market prediction via machine learning. The Journal of Finance and Data Science, 7, 45–66. https://doi.org/10.1016/j.jfds.2021.03.001

Kong, X., et al. (2025). Deep learning for time series forecasting: A survey. International Journal of Machine Learning and Cybernetics. https://doi.org/10.1007/s13042-025-02560-w

Lee, J., et al. (2025). A survey of large language models in finance (FinLLMs). Neural Computing and Applications, 37, 24853–24867. https://doi.org/10.1007/s00521-024-10495-6

Lim, B., Arik, S. Ö., Loeff, N., & Pfister, T. (2021). Temporal fusion transformers for interpretable multi-horizon time series forecasting. International Journal of Forecasting, 37(4), 1748–1764. https://doi.org/10.1016/j.ijforecast.2021.03.012

Livieris, I. E., Pintelas, E., & Pintelas, P. (2020). A CNN–LSTM model for gold price time-series forecasting. Neural Computing and Applications, 32, 17351–17360. https://doi.org/10.1007/s00521-020-04867-x

Nguyen, M. H., et al. (2026). Reviving error correction in modern deep time-series forecasting. arXiv.

Nti, I. K., Adekoya, A. F., & Weyori, B. A. (2020). A systematic review of fundamental and technical analysis of stock market predictions. Artificial Intelligence Review, 53, 3007–3057. https://doi.org/10.1007/s10462-019-09754-z

Passalis, N., Tefas, A., Kanniainen, J., Gabbouj, M., & Iosifidis, A. (2020). Deep adaptive input normalization for time series forecasting. IEEE Transactions on Neural Networks and Learning Systems, 31(9), 3760–3765. https://doi.org/10.1109/TNNLS.2019.2944933

Rojat, T., Bonnet, A., & Frindel, C. (2021). Explainable artificial intelligence (XAI) on time series data: A survey. arXiv.

Sebastião, H., & Godinho, P. (2021). Forecasting and trading cryptocurrencies with machine learning under changing market conditions. Financial Innovation, 7, Article 3. https://doi.org/10.1186/s40854-020-00217-x

Sezer, O. B., Gudelek, M. U., & Özbayoğlu, A. M. (2020). Financial time series forecasting with deep learning: A systematic literature review: 2005–2019. Applied Soft Computing, 90, 106181. https://doi.org/10.1016/j.asoc.2020.106181