International Journal of Engineering and Manufacturing (IJEM)
IJEM Vol. 16, No. 5, 8 Oct. 2026
Cover page and Table of Contents: PDF (size: 1279KB)
MA-Helformer: A Sentiment-Aware Adaptive Framework for Multi-Horizon Crypto Forecasting
PDF (1279KB), PP.75-91
Views: 0 Downloads: 0
Author(s)
Preeti Pandey
1
Geeta Sharma
2
Mukesh Kumar
3,4,*
Index Terms
Cryptocurrency Forecasting, Deep Learning, FinBERT, Hidden Markov Model, Holt-Winters Smoothing, Long Short-Term Memory, Market Regime Detection, Multivariate Time Series, Sentiment Analysis, Transformer
Abstract
The cryptocurrency market is highly non-linear, non-stationary and driven by sentiment volatility, which poses fundamental challenges for price prediction. The recently proposed Helformer model couples a Transformer-based architecture with Holt-Winters exponential smoothing and shows excellent performance for univariate forecasting. However, the model relies only on closing price data and does not incorporate external sentiment sources, and uses static decomposition parameters without taking into account market conditions. Finally, the Helformer model has only been evaluated on a single asset. To systematically address these limitations, this paper proposes the Multivariate Adaptive Helformer (MA-Helformer), an improved deep learning framework with three main contributions. First, the input feature space is enriched with a complete multivariate set of 13 technical indicators, six on-chain metrics, seven macroeconomic variables, and three sentiment scores from FinBERT. Second, an adaptive market regime detection module based on Hidden Markov Models (HMM) dynamically conditions Holt-Winters decomposition parameters on detected market state (Bull, Bear, Sideways). Third, a multi-horizon forecasting head is trained jointly to produce price forecasts for 1-day, 7-day, and 30-day horizons simultaneously. We experiment on Bitcoin (BTC), Ethereum (ETH) and Solana (SOL) using daily data from January 2017 to December 2024. MA-Helformer reduces next-day RMSE by 49.2% relative to the baseline Helformer, achieves a Sharpe Ratio of 2.34 in a realistic trading simulation that accounts for variable transaction costs and slippage, and shows particularly strong improvements in Bear market regimes. All reported performance gains are statistically significant ("p<0.01" ) according to the Diebold-Mariano test. Experimental results demonstrate that MA-Helformer consistently outperforms the baseline Helformer and several competitive forecasting models across multiple evaluation metrics and forecast horizons, while achieving statistically significant improvements under the adopted experimental protocol. Although the proposed framework demonstrates promising predictive performance, its evaluation is based on historical market data and simulated trading conditions; therefore, further validation using real-time deployment and additional financial assets remains future work.
Cite This Paper
Preeti Pandey, Geeta Sharma, Mukesh Kumar, "MA-Helformer: A Sentiment-Aware Adaptive Framework for Multi-Horizon Crypto Forecasting", International Journal of Engineering and Manufacturing(IJEM), Vol.16, No.5, pp. 75-92, 2026. DOI:10.5815/ijem.2026.05.04
Reference
[1]Chandankar, P., & Burchard, R., Sensor-Specific Transformer (PatchTST) Ensembles with Test-Matched Augmentation. In Companion of the 2025 ACM International Joint Conference on Pervasive and Ubiquitous Computing (pp. 1055-1060), 2025. DOI: https://doi.org/10.1145/3714394.3756196
[2]Abu Bakar, N., & Rosbi, S., Autoregressive integrated moving average (ARIMA) model for forecasting cryptocurrency exchange rate in high volatility environment: A new insight of bitcoin transaction. International Journal of Advanced Engineering Research and Science, 4(11), 130-137, 2017. DOI: https://dx.doi.org/10.22161/ijaers.4.11.20
[3]Wu, H., Hu, T., Liu, Y., Zhou, H., Wang, J., & Long, M., Timesnet: Temporal 2d-variation modeling for general time series analysis. arXiv preprint arXiv:2210.02186, 2022. DOI: https://doi.org/10.48550/arXiv.2210.02186
[4]Zeng, A., Chen, M., Zhang, L., & Xu, Q., Are transformers effective for time series forecasting? In Proceedings of the AAAI conference on artificial intelligence (Vol. 37, No. 9, pp. 11121-11128), 2023. DOI: https://doi.org/10.1609/aaai.v37i9.26317
[5]Seabe, P. L., Moutsinga, C. R. B., & Pindza, E., Forecasting cryptocurrency prices using LSTM, GRU, and bi-directional LSTM: a deep learning approach. Fractal and Fractional, 7(2), 203, 2023. DOI: https://doi.org/10.3390/fractalfract7020203
[6]Ashish, V., Noam, S., Niki, P., Jakob, U., Llion, J., Aidan, N. G., ... & Illia, P., Attention is all you need: Advances in neural information processing systems. In NeurIPS Proceedings. 2017, pp. 5998-6008, DOI: https://dl.acm.org/doi/abs/10.5555/3295222.3295349
[7]Kehinde, T. O., Adedokun, O. J., Joseph, A., Kabirat, K. M., Akano, H. A., & Olanrewaju, O. A., Helformer: an attention-based deep learning model for cryptocurrency price forecasting. Journal of Big Data, 12(1), 81. 2025, DOI: https://doi.org/10.1186/s40537-025-01135-4
[8]Poongodi, M., Sharma, A., Vijayakumar, V., Bhardwaj, V., Sharma, A. P., Iqbal, R., & Kumar, R., Prediction of the price of Ethereum blockchain cryptocurrency in an industrial finance system. Computers & Electrical Engineering, 81, 106527, 2020. DOI: https://doi.org/10.1016/j.compeleceng.2019.106527
[9]Girsang, A. S., Hybrid LSTM and GRU for cryptocurrency price forecasting based on social network sentiment analysis using FinBERT. Ieee Access, 11, 120530-120540, 2023. DOI: 10.1109/ACCESS.2023.3324535
[10]Wang, W., Wang, Y., Qi, X., & Chen, H., EIAformer: Empowering transformer with enhanced information acquisition for time series forecasting. Neurocomputing, 131700, 2025. DOI: https://doi.org/10.1016/j.neucom.2025.131700
[11]Hu, Y., Liu, P., Zhu, P., Cheng, D., & Dai, T., Adaptive multi-scale decomposition framework for time series forecasting. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 39, No. 16, pp. 17359-17367, 2025, DOI: https://doi.org/10.1609/aaai.v39i16.33908
[12]Kristjanpoller, W., & Minutolo, M. C., A hybrid volatility forecasting framework integrating GARCH, artificial neural network, technical analysis and principal components analysis. Expert Systems with Applications, 109, 1-11, 2018, DOI: 10.1016/j.eswa.2018.05.011
[13]Alonso-Monsalve, S., Suárez-Cetrulo, A. L., Cervantes, A., & Quintana, D., Convolution on neural networks for high-frequency trend prediction of cryptocurrency exchange rates using technical indicators. Expert Systems with Applications, 149, 113250, 2020, DOI: 10.1016/j.eswa.2020.113250
[14]Zhou, H., Zhang, S., Peng, J., Zhang, S., Li, J., Xiong, H., & Zhang, W., Informer: Beyond efficient transformer for long sequence time-series forecasting. In Proceedings of the AAAI conference on artificial intelligence, Vol. 35, No. 12, pp. 11106-11115, 2021, DOI: https://doi.org/10.1609/aaai.v35i12.17325
[15]Haixu, W., Jiehui, X., Wang, J., & Mingsheng, L., Decomposition transformers with auto-correlation for long-term series forecasting. Autoformer, 2021, DOI: https://dl.acm.org/doi/10.5555/3540261.3541978
[16]Lim, B., Arık, S. Ö., Loeff, N., & Pfister, T., Temporal fusion transformers for interpretable multi-horizon time series forecasting. International journal of forecasting, 37(4), 1748-1764, 2021, DOI: 10.1016/j.ijforecast.2021.03.012
[17]Cavalli, S., & Amoretti, M., CNN-based multivariate data analysis for bitcoin trend prediction. Applied Soft Computing, 101, 107065, 2021, DOI: https://doi.org/10.1016/j.asoc.2020.107065
[18]Araci, D., Finbert: Financial sentiment analysis with pre-trained language models. arXiv preprint arXiv:1908.10063. 2019, DOI: https://doi.org/10.48550/arXiv.1908.10063
[19]Goodell, J. W., Jabeur, S. B., Saâdaoui, F., & Nasir, M. A., Explainable artificial intelligence modeling to forecast bitcoin prices. International Review of Financial Analysis, 88, 102702, 2023, DOI: 10.1016/j.irfa.2023.102702
[20]Golnari, A., Komeili, M. H., & Azizi, Z., Probabilistic deep learning and transfer learning for robust cryptocurrency price prediction. Expert Systems with Applications, 255, 124404. 2024, DOI: 10.1016/j.eswa.2024.124404
[21]Sbrana, A., & Lima de Castro, P. A., N-BEATS perceiver: a novel approach for robust cryptocurrency portfolio forecasting. Computational Economics, 64(2), 1047-1081, 2024, DOI: https://doi.org/10.1007/s10614-023-10470-8
[22]Jin, C., & Li, Y., Cryptocurrency price prediction using frequency decomposition and deep learning. Fractal and Fractional, 7(10), 708, 2023, DOI: https://doi.org/10.3390/fractalfract7100708
[23]Hansun, S., Wicaksana, A., & Khaliq, A. Q., Multivariate cryptocurrency prediction: comparative analysis of three recurrent neural networks approaches. Journal of Big Data, 9(1), 50, 2022, DOI: https://doi.org/10.1186/s40537-022-00601-7
[24]Fallah, M. F., Pourmansouri, R., & Ahmadpour, B., Presenting a new deep learning-based method with the incorporation of error effects to predict certain cryptocurrencies. International Review of Financial Analysis, 95, 103466, 2024, DOI: 10.1016/j.irfa.2024.103466
[25]Zhou, T., Ma, Z., Wen, Q., Wang, X., Sun, L., & Jin, R., Fedformer: Frequency enhanced decomposed transformer for long-term series forecasting. In International conference on machine learning (pp. 27268-27286). PMLR. , 2022
[26]Das, B., Dagdogen, H. A., Kaya, M. O., & Das, R., A new hybrid approach combining transformer-based language models and graph neural networks for cryptocurrency forecasting. Engineering Applications of Artificial Intelligence, 164, 113179, 2026, DOI: https://doi.org/10.1016/j.engappai.2025.113179
[27]Li, M., Jia, L., Ma, X., & Su, X., Graph diffusion arithmetic feature interaction transformer with temporal information for bitcoin anti-money laundering. Applied Intelligence, 56(6), 192, 2026, DOI: https://doi.org/10.1007/s10489-026-07232-y
[28]Zhang, Y., & Yan, J., Crossformer: Transformer utilizing cross-dimension dependency for multivariate time series forecasting. In The eleventh international conference on learning representations, 2023, Corpus ID: 259298223
[29]B. G. Malkiel, "The efficient market hypothesis and its critics," J. Econ. Perspect., vol. 17, no. 1, pp. 59-82, 2003.