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{194823,
        author = {R Harsha Vardhan Reddy and Dr. J Krishna and J Kavya and U Soma Sekhar and G Manikanta and K Venkata Thriveni},
        title = {Deep Learning-Based Forecasting of Cryptocurrency Prices : Short to Long Horizon},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {6339-6345},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=194823},
        abstract = {The unstable cryptocurrency markets present new opportunities and threats. The possibility of exposure to the cryptocurrency assets is quite high as the exchange rates can change on a daily basis. The project estimates the price of cryptocurrency by the use of the potent machine learning tools. The Neutral Networks were the most efficient in the best forecast and best validation as compared to other two seven models having minor errors. The neural networks used in the prediction of the tendencies in the future have been long short term memory (LMST). Multiple associations of financial data can be assessed also, regarding LSTM model. Over fifty cryptocurrencies were subjected to the Exploratory Data Analysis (EDA), which first took the historical data collection, followed by the feature engineering, integrative binning, data preparation, and standardization. The most successful ones were identified based on the price movement, the market size and volumes. The Python written LSTM-based model has been applied in studying the intricate trends and associations in 90 days of price movement statistics. The performance measures were RMSE and MAE, which were used to monitor the performance of the model. These findings support the Adaptive Market Hypothesis (AMH) that states that adaptive changes in the behavior of investors and markets influence the dynamic efficiency of cryptocurrency market. The study highlights the potential of machine learning models in financial economics and how they will aid with risk management techniques and investment decision-making.},
        keywords = {LSTM neural networks, machine learning, financial economics, model prediction, and currency forecasting},
        month = {March},
        }