Integrating High-Dimensional Technical Indicators into Machine Learning Models for Predicting Cryptocurrency Price Movements and Trading Performance: Evidence from Bitcoin, Ethereum, and Ripple
Open accessThe DOI matches its Crossref record; 45 of the 45 references it cites were found in a registry or an index.
Abstract
The rapid evolution of digital assets transforms cryptocurrencies into one of the most volatile and data-rich financial markets. Their nonlinear and unpredictable nature limits the effectiveness of traditional forecasting models, motivating the use of machine learning methods to identify hidden patterns and short-term price movements. This study compares the performance of Logistic Regression (LR), Random Forest (RF), XGBoost, Support Vector Classifier (SVC), K-Nearest Neighbors (KNNs), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU) models in predicting the daily price directions of Bitcoin (BTC), Ethereum (ETH), and Ripple (XRP). Extensive data preprocessing and feature engineering are performed, integrating a broad set of technical indicators to enhance model generalization and capture temporal market dynamics. The results show that XGBoost achieves the highest classification accuracy of 55.9% for BTC and 53.8% for XRP, while LR provides the best result for Ethereum with an accuracy of 54.4%. In trading simulations, XGBoost achieves the strongest performance, generating a cumulative return of 141.4% with a Sharpe ratio of 1.78 for Bitcoin and 246.6% with a Sharpe ratio of 1.59 for Ripple, whereas LSTM delivers the best results for Ethereum with a 138.2% return and a Sharpe ratio of 1.05. Compared to recent studies, the proposed approach attains slightly higher accuracy, while demonstrating stronger robustness and profitability in practical backtesting. Overall, the findings confirm that through rigorous preprocessing machine learning-based strategies can effectively capture short-term price movements and outperform the conventional buy-and-hold benchmark, even under a simple rule-based trading framework.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cited works that were retracted
Works this paper cites that were later retracted, from the retraction notices publishers deposit. Major when the notice came out before this paper was published.
A note, not an issue: for example, a cited work that was retracted only after this paper was published, which its authors could not have known.
In the paper
“By October 2025, the overall value of the global cryptocurrency market surpassed 4 trillion US dollars according to Investing [2], marking one of the strongest recoveries in the sector’s history.”
Cited work 10.1016/j.irfa.2018.09.003 · retracted 2026-02-01 · notice 10.1016/j.irfa.2026.105078 · this paper published 2025-12-18
Citations
Cites
1 retracted
RETRACTED: Cryptocurrencies as a financial asset: A systematic analysis
Corbet, S., Lucey, B., Urquhart, A., & Yarovaya, L. (2019) · International Review of Financial Analysis · doi:10.1016/j.irfa.2018.09.003 · Cited by 1,172 · cited 2×
“By October 2025, the overall value of the global cryptocurrency market surpassed 4 trillion US dollars according to Investing [2], marking one of the strongest recoveries in the sector’s history.”
RetractedBreiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 1×
“Random Forest is an ensemble learning method that builds several decision trees to enhance classification accuracy and minimize overfitting [43].”
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“The Long Short-Term Memory network is a type of Recurrent Neural Network (RNN) specifically developed to learn long-term patterns in sequential data [47].”
Cortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
XGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569
Cortes, C., & Vapnik, V. (1995) · Machine-mediated learning · doi:10.1023/a:1022627411411 · Cited by 48,445 · cited 1×
“SVM seeks to determine the optimal hyperplane that separates two classes with the widest possible margin [45].”
Nearest neighbor pattern classification
Cover, T., & Hart, P. (1967) · IEEE Transactions on Information Theory · doi:10.1109/tit.1967.1053964 · Cited by 16,936 · cited 1×
“KNN is a simple, non-parametric algorithm that classifies a sample by considering the majority class among its k closest neighbors in the feature space [46].”
Hosmer, D. W., Lemeshow, S., & Sturdivant, R. X. (2013) · Wiley Series in Probability and Statistics · doi:10.1002/9781118548387 · Cited by 13,861 · cited 1×
“Logistic Regression is widely used in financial forecasting because of its interpretability and effectiveness in identifying linear decision boundaries between upward and down-ward price movements [42].”
On the Properties of Neural Machine Translation: Encoder–Decoder Approaches
Cho, K., van Merrienboer, B., Bahdanau, D., & Bengio, Y. (2014) · Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation · doi:10.3115/v1/w14-4012 · Cited by 7,099 · cited 1×
“The Gated Recurrent Unit (GRU) is a simplified variant of the LSTM network that merges the forget and input gates into a single update gate, while still effectively capturing temporal patterns in sequential data [48].”
Principal components analysis (PCA)
Maćkiewicz, A., & Ratajczak, W. (1993) · Computers & Geosciences · doi:10.1016/0098-3004(93)90090-r · Cited by 1,734
Predicting the Price of Bitcoin Using Machine Learning
McNally, S., Roche, J., & Caton, S. (2018) · 2018 26th Euromicro International Conference on Parallel, Distributed and Network-based Processing (PDP) · doi:10.1109/pdp2018.2018.00060 · Cited by 665 · cited 1×
“These approaches can learn hidden dependencies and evolving temporal patterns from large volumes of historical data, outperforming classical statistical methods in cryptocurrency price predictions [12,13].”
Cryptocurrency forecasting with deep learning chaotic neural networks
Lahmiri, S., & Bekiros, S. (2019) · Chaos, Solitons & Fractals · doi:10.1016/j.chaos.2018.11.014 · Cited by 376
Hamayel, M. J., & Owda, A. Y. (2021) · AI · doi:10.3390/ai2040030 · Cited by 294 · cited 1×
“Hamayel and Owda [21] evaluated LSTM, GRU, and Bi-LSTM architectures for forecasting the prices of Bitcoin, Ethereum, and Litecoin.”
Mushtaq, R. (2011) · SSRN Electronic Journal · doi:10.2139/ssrn.1911068 · Cited by 289 · cited 1×
“Since most machine learning models require stationary input data, all numerical input features (prices, volumes, and technical indicators) are checked for stationarity using the Augmented Dickey–Fuller (ADF) test [39] provided by the statsmodels library.”
Prediction of cryptocurrency returns using machine learning
Akyildirim, E., Goncu, A., & Sensoy, A. (2021) · Annals of Operations Research · doi:10.1007/s10479-020-03575-y · Cited by 263 · cited 1×
“Akyildirim et al. [16] analyzed twelve of the most liquid cryptocurrencies at daily and intraday frequencies using support vector machines, logistic regression, feed-forward neural networks and random forests to classify the sign of future returns.”
Machine Learning for Evolution Strategies
Kramer, O. (2016) · Studies in Big Data · doi:10.1007/978-3-319-33383-0 · Cited by 244
Forecasting and trading cryptocurrencies with machine learning under changing market conditions
Sebastião, H., & Godinho, P. (2021) · Financial Innovation · doi:10.1186/s40854-020-00217-x · Cited by 237
Forecasting Cryptocurrency Prices Using LSTM, GRU, and Bi-Directional LSTM: A Deep Learning Approach
Seabe, P. L., Moutsinga, C. R. B., & Pindza, E. (2023) · Fractal and Fractional · doi:10.3390/fractalfract7020203 · Cited by 207 · cited 1×
“Seabe et al. [24] also compared LSTM, GRU and BiLSTM for BTC, ETH and LTC exchange rates and found that BiLSTM consistently delivered the best performance in terms of RMSE and MAPE, underscoring the usefulness of bidirectional architectures.”
An Advanced CNN-LSTM Model for Cryptocurrency Forecasting
Livieris, I. E., Kiriakidou, N., Stavroyiannis, S., & Pintelas, P. (2021) · Electronics · doi:10.3390/electronics10030287 · Cited by 183 · cited 3×
“Livieris et al. [27] further proposed a multi-input CNN-LSTM architecture that processed the return series of Bitcoin, Ethereum and Ripple through separate convolutional branches before merging them in LSTM layers.”
Ensemble Deep Learning Models for Forecasting Cryptocurrency Time-Series
Livieris, I. E., Pintelas, E. G., Stavroyiannis, S., & Pintelas, P. (2020) · Algorithms · doi:10.3390/a13050121 · Cited by 164
Ortu, M., Uras, N., Conversano, C., Bartolucci, S., & Destefanis, G. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.116804 · Cited by 155
On Forecasting Cryptocurrency Prices: A Comparison of Machine Learning, Deep Learning, and Ensembles
Murray, K., Rossi, A., Carraro, D., & Visentin, A. (2023) · Forecasting · doi:10.3390/forecast5010010 · Cited by 141 · cited 1×
“Murray et al. [28] carried out a systematic comparison of ARIMA, traditional ML models, LSTM, CNN and the Tempo-FinTech ral Fusion Transformer (TFT) for daily data on five major cryptocurrencies.”
Analysis of Bitcoin Price Prediction Using Machine Learning
Chen, J. (2023) · Journal of risk and financial management · doi:10.3390/jrfm16010051 · Cited by 138 · cited 1×
“Chen [20] extended the explanatory set substantially by combining daily Bitcoin prices with 47 additional variables, including other cryptocurrencies, commodity prices, stock indices, exchange rates and Google search indices.”
Bitcoin price forecasting method based on CNN‐LSTM hybrid neural network model
Li, Y., & Dai, W. (2020) · The Journal of Engineering · doi:10.1049/joe.2019.1203 · Cited by 108
Forecasting of Cryptocurrency Prices Using Machine Learning
Derbentsev, V. D., Matviychuk, A. V., & Soloviev, V. (2020) · Springer eBooks · doi:10.1007/978-981-15-4498-9_12 · Cited by 102
Borges, T. A., & Neves, R. F. (2020) · Applied Soft Computing · doi:10.1016/j.asoc.2020.106187 · Cited by 99 · cited 1×
“Borges and Neves [18] developed a machine learning investment framework employing Logistic Regression, Random Forest, SVM, and Gradient Boosting combined with resampling techniques.”
Investigating the Problem of Cryptocurrency Price Prediction: A Deep Learning Approach
Pintelas, E. G., Livieris, I. E., Stavroyiannis, S., Kotsilieris, T., & Pintelas, P. (2020) · IFIP advances in information and communication technology · doi:10.1007/978-3-030-49186-4_9 · Cited by 98
Ascertaining price formation in cryptocurrency markets with machine learning
Fang, F., Chung, W., Ventre, C., Basios, M., Kanthan, L., Li, L., & Wu, F. (2021) · European Journal of Finance · doi:10.1080/1351847x.2021.1908390 · Cited by 96 · cited 1×
“Fang et al. [34] introduced a hybrid approach combining autoen-coders and LSTM networks, using limit-order-book features to classify the direction and magnitude of the next-tick mid-price change.”
DL-GuesS : Deep Learning and Sentiment Analysis-Based Cryptocurrency Price Prediction
Parekh, R., Patel, N., Thakkar, N., Gupta, R., Tanwar, S., Sharma, G., Davidson, I. E. A., & Sharma, R. (2022) · IEEE Access · doi:10.1109/access.2022.3163305 · Cited by 92 · cited 1×
“Parekh et al. [30] developed DL-GuesS, a deep learning and sentiment-analysis framework that combined LSTM and GRU models with Twitter-derived sentiment indicators for Dash, Litecoin, Bitcoin and Bitcoin Cash.”
Time-Series Prediction of Cryptocurrency Market using Machine Learning Techniques
Iqbal, M., Iqbal, M. H., Jaskani, F. H., Iqbal, K., & Hassan, A. (2021) · EAI Endorsed Transactions on Creative Technologies · doi:10.4108/eai.7-7-2021.170286 · Cited by 86 · cited 1×
“Iqbal et al. [19] compared ARIMA, FBProphet, and XGBoost models on Bitcoin market data, concluding that the ARIMAX variant achieved the lowest RMSE and MAE values, demonstrating that classical statistical methods remain competitive under certain conditions, yet the limited feature set and single…”
Ripple vs. SWIFT: Transforming Cross Border Remittance Using Blockchain Technology
Qiu, T., Zhang, R., & Gao, Y. (2019) · Procedia Computer Science · doi:10.1016/j.procs.2019.01.260 · Cited by 81 · cited 1×
“Ripple, through its XRP token, focuses on institutional and cross-border payment solutions, demonstrating how different technological designs can serve distinct financial purposes [5].”
Cryptocurrency Price Prediction with Convolutional Neural Network and Stacked Gated Recurrent Unit
Kang, C. Y., Lee, C. P., & Lim, K. M. (2022) · Data · doi:10.3390/data7110149 · Cited by 47 · cited 1×
“Kang et al. [26] introduced a 1D-CNN and stacked GRU hybrid model for one-minute OHLC data on Bitcoin, Ethereum and Ripple.”
Deep Learning Forecasting in Cryptocurrency High-Frequency Trading
Lahmiri, S., & Bekiros, S. D. (2021) · Cognitive Computation · doi:10.1007/s12559-021-09841-w · Cited by 43 · cited 1×
“Lahmiri and Bekiros [22] investigated deep feed-forward neural networks (DFFNNs) for high-frequency Bitcoin trading.”
Belcastro, L., Carbone, D., Cosentino, C., Marozzo, F., & Paolo Trunfio, A. (2023) · Algorithms · doi:10.3390/a16120542 · Cited by 39 · cited 1×
“Belcastro et al. [31] constructed a trading-recommendation system that integrated OHLCV data, Twitter sentiment, measures of correlation between social activity and price changes, and Granger-causal links among coin prices.”
High-Frequency Cryptocurrency Price Forecasting Using Machine Learning Models: A Comparative Study
Rodrigues, F., & Machado, M. (2025) · Information · doi:10.3390/info16040300 · Cited by 39
A new hybrid machine learning model for predicting the bitcoin (BTC-USD) price
Nagula, P. K., & Alexakis, C. A. (2022) · Journal of Behavioral and Experimental Finance · doi:10.1016/j.jbef.2022.100741 · Cited by 37
Quantitative cryptocurrency trading: exploring the use of machine learning techniques
Attanasio, G., Cagliero, L., Garza, P., & Baralis, E. (2019) · doi:10.1145/3336499.3338003 · Cited by 30
Using machine learning for cryptocurrency trading
Sun, J., Zhou, Y., & Lin, J. (2019) · IEEE International Conference on Industrial Cyber-Physical Systems (ICPS) · doi:10.1109/icphys.2019.8780358 · Cited by 27 · cited 1×
“Sun et al. [14] implemented a random forest model using features derived from Alpha101 factors and OHLCV data to anticipate cryptocurrency price changes.”
Cryptocurrency direction forecasting using deep learning algorithms
Cherati, M. R., Haeri, A., & Ghannadpour, S. F. (2021) · Journal of Statistical Computation and Simulation · doi:10.1080/00949655.2021.1899179 · Cited by 26 · cited 1×
“Recently, machine learning (ML) and deep learning (DL) methods have gained wide adoption for capturing the intricate and nonlinear patterns observed in cryptocurrency data [6–11].”
Bitcoin Trend Prediction with Attention-Based Deep Learning Models and Technical Indicators
Lee, M.-C. (2024) · Systems · doi:10.3390/systems12110498 · Cited by 26 · cited 1×
“Lee [36] proposed attention-based LSTM and GRU models for Bitcoin that took OHLCV data and moving-average indicators (SMA, EMA, TEMA, MACD) as inputs and classified each day into uptrend, downtrend or neutral regimes.”
Leveraging the momentum effect in machine learning-based cryptocurrency trading
Bellocca, G. P., Attanasio, G., Cagliero, L., & Fior, J. (2022) · Machine Learning with Applications · doi:10.1016/j.mlwa.2022.100310 · Cited by 18
An Intelligent System for Trading Signal of Cryptocurrency Based on Market Tweets Sentiments
Leung, M.-F., Chan, L., Hung, W.-C., et al. (2023) · FinTech · doi:10.3390/fintech2010011 · Cited by 10 · cited 1×
“Leung et al. [32] designed an intelligent web-based platform that merged tweet sentiment scores, simple ML classifiers and live price feeds to generate buy/sell recommendations for retail users.”
Seeing Beyond Noise: Improving Cryptocurrency Forecasting with Linear Bias Correction
Syed, S., Talha, S. M. U., Iqbal, A., Ahmad, N., & Alshara, M. A. (2024) · AI · doi:10.3390/ai5040136 · Cited by 8 · cited 1×
“Syed et al. [23] introduced a post hoc bias-correction layer for LSTM, GRU and BiL-STM models applied to BTC, BNB, XRP and USDT.”
High-Frequency Cryptocurrency Price Forecasting using Machine Learning Models: A Comparative StudyPreprint
Rodrigues, F., & Machado, M. (2025) · Preprints.org · doi:10.20944/preprints202503.0261.v1 · Cited by 5
Chen, W., & Zheng, H. (2025) · Quantitative Finance and Economics · doi:10.3934/qfe.2025023 · Cited by 3
Research works printed but not linked: 1
- Raju, S.M., and Tarif, A.M. (2020). Real-time prediction of Bitcoin price using machine learning techniques and public sentiment analysis. arXiv.
Cited by
A Novel Hybrid Transformer-Based Deep Learning Approach for Multi-Step Bitcoin Price Forecasting
Hasanli, R., & Dursun, M. (2026) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.16684 · Cited by 3
Self-citationMapping the Main Topics of Cryptocurrency: A Bibliometric Analysis by Text Mining
Liu, S., Xiang, X., Luo, C., & Lu, X. (2026) · Journal of Economic Surveys · doi:10.1111/joes.70131
Metadata
- Authors
- Hasanli, R., & Dursun, M.
- Affiliations
- Gazi University (TR)
- Azerbaijan University of Architecture and Construction (AZ)
- Corresponding author
- Hasanli, Rza
- Venue
- FinTech
- Publisher
- MDPI AG
- Published
- 2025-12-18
- Volume
- 4
- Issue
- 4
- Pages
- 77
- ISSN
- 2674-1032 (ISSN-L)
- OpenAlex
- W7115889901
- Cited by
- 3
- References
- 41
- Citations by year
- 2026: 3
- FWCI
- 2.32
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- FinTech (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Social Sciences › Decision Sciences › Management Science and Operations Research › Stock Market Forecasting Methods
- Physical Sciences › Computer Science › Information Systems › Blockchain Technology Applications and Security
- Social Sciences › Economics, Econometrics and Finance › Finance › Financial Markets and Investment Strategies
- Keywords
- cryptocurrency price prediction, technical indicators, Bitcoin, Ethereum, ripples, trading strategy performance, XGBoost, LSTM, gated recurrent unit, feature engineering, backtesting, Sharpe ratio, short-term price movements
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.