Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{192007,
        author = {Aradhana Suryawanshi and Vinay Lowanshi},
        title = {A Data-Driven Deep Sequential Learning Approach for Digital Financial Asset Price Prediction Using LSTM Networks},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {9},
        pages = {130-133},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=192007},
        abstract = {The prediction of digital financial asset prices has become a challenging task due to the highly volatile and non-linear nature of modern financial markets. Traditional statistical and machine learning models often struggle to capture complex temporal dependencies present in financial time-series data. This study proposes a data-driven deep sequential learning approach for digital financial asset price prediction using Long Short-Term Memory (LSTM) networks. The proposed framework learns temporal patterns directly from historical market data without relying on predefined rules or assumptions.
In this work, Bitcoin is considered as a representative digital financial asset due to its high liquidity and availability of long-term historical data. Daily Open, High, Low, and Close (OHLC) price data spanning from 2019 to 2025 is utilized for model training and evaluation. To establish a performance baseline, a Random Forest regression model is implemented and compared with the proposed LSTM-based approach. The models are evaluated using standard performance metrics, including Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and the coefficient of determination (R²). Experimental results demonstrate that the LSTM model significantly outperforms the Random Forest model by effectively capturing long-term temporal dependencies in the price series. The proposed deep sequential learning framework achieves higher prediction accuracy and better generalization capability, making it suitable for digital financial market analysis and decision-support applications. The findings highlight the effectiveness of deep learning-based sequential models for price forecasting in highly volatile digital asset markets.},
        keywords = {Digital Assets managements, Bitcoin Price Prediction, LSTM Networks, Random Forest Regressor, Time Series Forecasting, Deep Learning, Cryptocurrency Market},
        month = {February},
        }