Sentiment Trumps Fundamentals: Machine-Learning Evidence on the Drivers of Cryptocurrency Returns
DOI:
https://doi.org/10.63646/YYOR9860Keywords:
Cryptocurrency; investor sentiment; economic fundamentals; machine learning; return predictability; social-media analytics; explainable AI; behavioral financeAbstract
Whether investor sentiment is more informative than network fundamentals for cryptocurrency returns remains an empirical question. This study evaluates that proposition using a transparent, time-ordered forecasting design for Bitcoin and Ether. Daily prices and on-chain activity are drawn from Coin Metrics community data, and the Bitcoin-oriented Crypto Fear & Greed Index is obtained from Alternative.me. The index is a composite market-mood proxy rather than a pure measure of emotion because its documented components include volatility and market momentum. Daily log returns are forecast using market-history features alone or augmented with sentiment, blockchain-activity proxies, or both. Ridge regression and histogram-based gradient boosting are specified with fixed hyperparameters. Models are developed on data from June 2018 to December 2021, assessed on 2022, and refitted through 2022 before testing on 2023–2024. After common complete-case filtering, each asset has 723 test observations. In the test period, the gradient-boosting market-only root mean squared errors are 2.546 percentage points for Bitcoin and 2.967 for Ether, compared with 2.558 and 2.967 when the sentiment block is added. The sentiment block does not consistently improve forecasting relative to the market-only or network-augmented models, and all gradient-boosting variants have negative out-of-sample R² relative to a zero-return forecast. Paired block-bootstrap intervals show substantial uncertainty in the incremental comparisons. The title’s proposition is therefore not supported as a general conclusion by this restricted test. The results illustrate the importance of release timing, overlapping information, simple benchmarks, and reproducible validation when interpreting claims about the drivers of cryptocurrency returns.
How to Cite
References
Altmann, A., Toloşi, L., Sander, O., & Lengauer, T. (2010). Permutation importance: A corrected feature importance measure. Bioinformatics, 26(10), 1340–1347. https://doi.org/10.1093/bioinformatics/btq134
Amirshahi, B., & Lahmiri, S. (2025). Investigating the effectiveness of Twitter sentiment in cryptocurrency close price prediction by using deep learning. Expert Systems, 42(1), e13428. https://doi.org/10.1111/exsy.13428
Arian, H., Norouzi Mobarekeh, D., & Seco, L. (2024). Backtest overfitting in the machine learning era: A comparison of out-of-sample testing methods in a synthetic controlled environment. Knowledge-Based Systems, 305, 112477. https://doi.org/10.1016/j.knosys.2024.112477
Bailey, D., Borwein, J., López de Prado, M., & Zhu, Q. J. (2016). The probability of backtest overfitting. The Journal of Computational Finance. https://doi.org/10.21314/jcf.2016.322
Berger, D., & Turtle, H. J. (2015). Sentiment bubbles. Journal of Financial Markets, 23, 59–74. https://doi.org/10.1016/j.finmar.2015.01.002
Berger, T., & Koubová, J. (2024). Forecasting Bitcoin returns: Econometric time series analysis vs. machine learning. Journal of Forecasting, 43(7), 2904–2916. https://doi.org/10.1002/for.3165
Biswas, P., & Sharma, C. (2025). Does fear sentiment drive cryptocurrency volatility? Evidence from Google trends data. Finance Research Letters, 86, 108510. https://doi.org/10.1016/j.frl.2025.108510
Borri, N., & Shakhnov, K. (2022). The cross-section of cryptocurrency returns. The Review of Asset Pricing Studies, 12(3), 667–705. https://doi.org/10.1093/rapstu/raac007
Borup, D. (2019). Asset pricing model uncertainty. Journal of Empirical Finance, 54, 166–189. https://doi.org/10.1016/j.jempfin.2019.07.005
Bouri, E., Azzi, G., & Dyhrberg, A. H. (2017). On the return-volatility relationship in the Bitcoin market around the price crash of 2013. Economics, 11(1), 2. https://doi.org/10.5018/economics-ejournal.ja.2017-2
Bouteska, A., Mefteh-Wali, S., & Dang, T. (2022). Predictive power of investor sentiment for Bitcoin returns: Evidence from COVID-19 pandemic. Technological Forecasting and Social Change, 184, 121999. https://doi.org/10.1016/j.techfore.2022.121999
Byun, S.-J., Cho, S., & Kim, D.-H. (2024). Can a machine learn from behavioral biases? Evidence from stock return predictability of deep learning models. Journal of Behavioral and Experimental Finance, 41, 100881. https://doi.org/10.1016/j.jbef.2023.100881
Caporale, G. M., Kang, W.-Y., Spagnolo, F., & Spagnolo, N. (2021). Cyber-attacks, spillovers and contagion in the cryptocurrency markets. Journal of International Financial Markets, Institutions and Money, 74, 101298. https://doi.org/10.1016/j.intfin.2021.101298
Cavalheiro, E. A., Vieira, K. M., & Thue, P. S. (2024). The impact of investor greed and fear on cryptocurrency returns: A granger causality analysis of Bitcoin and Ethereum. Review of Behavioral Finance, 16(5), 819–835. https://doi.org/10.1108/rbf-08-2023-0224
Chen, W., Xu, H., Jia, L., & Gao, Y. (2021). Machine learning model for Bitcoin exchange rate prediction using economic and technology determinants. International Journal of Forecasting, 37(1), 28–43. https://doi.org/10.1016/j.ijforecast.2020.02.008
Chen, Y.-L., & Hu, M.-C. (2026). Sentiment spillovers from news and social media in cryptocurrency markets. Journal of International Financial Markets, Institutions and Money, 110, 102357. https://doi.org/10.1016/j.intfin.2026.102357
Chen, Z., Li, C., & Sun, W. (2020). Bitcoin price prediction using machine learning: An approach to sample dimension engineering. Journal of Computational and Applied Mathematics, 365, 112395. https://doi.org/10.1016/j.cam.2019.112395
Choi, H. (2021). Investor attention and Bitcoin liquidity: Evidence from Bitcoin tweets. Finance Research Letters, 39, 101555. https://doi.org/10.1016/j.frl.2020.101555
Conn, D., Ngun, T., Li, G., & Ramirez, C. M. (2019). Fuzzy forests: Extending random forest feature selection for correlated, high-dimensional data. Journal of Statistical Software, 91(9). https://doi.org/10.18637/jss.v091.i09
Deng, A. (2023). Time series cross validation: A theoretical result and finite sample performance. Economics Letters, 233, 111369. https://doi.org/10.1016/j.econlet.2023.111369
Dias, I. K., Fernando, J. M. R., & Fernando, P. N. D. (2022). Does investor sentiment predict Bitcoin return and volatility? A quantile regression approach. International Review of Financial Analysis, 84, 102383. https://doi.org/10.1016/j.irfa.2022.102383
Diebold, F. X. (2015). Comparing predictive accuracy, twenty years later: A personal perspective on the use and abuse of diebold–mariano tests. Journal of Business & Economic Statistics, 33(1), 1–1. https://doi.org/10.1080/07350015.2014.983236
Diebold, F. X., & Mariano, R. S. (1995). Comparing predictive accuracy. Journal of Business & Economic Statistics, 13(3), 253–263. https://doi.org/10.1080/07350015.1995.10524599
Dunbar, K., & Owusu-Amoako, J. (2022). Cryptocurrency returns under empirical asset pricing. International Review of Financial Analysis, 82, 102216. https://doi.org/10.1016/j.irfa.2022.102216
Gaies, B., Nakhli, M. S., Sahut, J.-M., & Schweizer, D. (2023). Interactions between investors’ fear and greed sentiment and Bitcoin prices. The North American Journal of Economics and Finance, 67, 101924. https://doi.org/10.1016/j.najef.2023.101924
Gessie, L. (2026). Do Bitcoin returns move sentiment? Evidence from the crypto fear & greed index. Finance Research Open, 2(1), 100094. https://doi.org/10.1016/j.finr.2026.100094
Gu, S., Kelly, B., & Xiu, D. (2020). Empirical asset pricing via machine learning. The Review of Financial Studies, 33(5), 2223–2273. https://doi.org/10.1093/rfs/hhaa009
Guégan, D., & Renault, T. (2021). Does investor sentiment on social media provide robust information for Bitcoin returns predictability? Finance Research Letters, 38, 101494. https://doi.org/10.1016/j.frl.2020.101494
Hachicha, F., Masmoudi, A., Abid, I., & Obeid, H. (2023). Herding behavior in exploring the predictability of price clustering in cryptocurrency market. Finance Research Letters, 57, 104178. https://doi.org/10.1016/j.frl.2023.104178
Han, S. (2025). Investor sentiment and cross-section of cryptocurrency returns. Journal of Behavioral and Experimental Finance, 46, 101043. https://doi.org/10.1016/j.jbef.2025.101043
Hansen, E. (2022). Economic evaluation of asset pricing models under predictability. Journal of Empirical Finance, 68, 50–66. https://doi.org/10.1016/j.jempfin.2022.06.001
He, C.-W., & Wang, Y.-J. (2023). Bitcoin price jumps and investor sentiment indicators. Applied Economics Letters, 30(18), 2626–2630. https://doi.org/10.1080/13504851.2022.2102122
Hwang, I., & Kwon, J. H. (2024). Cryptocurrency returns and consumption-based asset pricing. Applied Economics, 56(55), 7393–7408. https://doi.org/10.1080/00036846.2024.2358214
Jia, Y., Wu, Y., Yan, S., & Liu, Y. (2023). A seesaw effect in the cryptocurrency market: Understanding the return cross predictability of cryptocurrencies. Journal of Empirical Finance, 74, 101428. https://doi.org/10.1016/j.jempfin.2023.101428
Karasiński, J. (2023). The adaptive market hypothesis and the return predictability in the cryptocurrency markets. Economics and Business Review, 9(1), 94–118. https://doi.org/10.18559/ebr.2023.1.4
Koltun, V., & Yamshchikov, I. P. (2023). Pump it: Twitter sentiment analysis for cryptocurrency price prediction. Risks, 11(9), 159. https://doi.org/10.3390/risks11090159
Kondor, D., Bulatovic, N., Stéger, J., Csabai, I., & Vattay, G. (2021). The rich still get richer: Empirical comparison of preferential attachment via linking statistics in Bitcoin and Ethereum. Frontiers in Blockchain, 4, 668510. https://doi.org/10.3389/fbloc.2021.668510
Koutmos, D. (2018). Bitcoin returns and transaction activity. Economics Letters, 167, 81–85. https://doi.org/10.1016/j.econlet.2018.03.021
Kunsch, H. R. (1989). The jackknife and the bootstrap for general stationary observations. The Annals of Statistics, 17(3), 1217–1241. https://doi.org/10.1214/aos/1176347265
Leong, M., & Kwok, S. (2023). The pricing of jump and diffusive risks in the cross-section of cryptocurrency returns. Journal of Empirical Finance, 74, 101420. https://doi.org/10.1016/j.jempfin.2023.101420
Leong, M., & Kwok, S. (2025). Bitcoin spillovers: A high‐frequency cross‐asset analysis. Financial Review, 60(2), 453–479. https://doi.org/10.1111/fire.12418
Li, S., & Ma, J. (2024). The impact of sentiment and engagement of Twitter posts on cryptocurrency price movement. Finance Research Letters, 65, 105598. https://doi.org/10.1016/j.frl.2024.105598
Liu, K., Manahov, V., & Stafylas, D. (2025). An investigation into the relationship between cryptocurrency active addresses and prices during major geopolitical conflicts. The European Journal of Finance, 31(18), 2323–2351. https://doi.org/10.1080/1351847x.2025.2585957
Liu, Y., & Tsyvinski, A. (2021). Risks and returns of cryptocurrency. The Review of Financial Studies, 34(6), 2689–2727. https://doi.org/10.1093/rfs/hhaa113
Mariano, R. S., & Preve, D. (2012). Statistical tests for multiple forecast comparison. Journal of Econometrics, 169(1), 123–130. https://doi.org/10.1016/j.jeconom.2012.01.014
Meister, B. K., & Price, H. C. W. (2024). Gas fees on the Ethereum blockchain: From foundations to derivative valuations. Frontiers in Blockchain, 7, 1462666. https://doi.org/10.3389/fbloc.2024.1462666
Murray, K., Rossi, A., Carraro, D., & Visentin, A. (2023). On forecasting cryptocurrency prices: A comparison of machine learning, deep learning, and ensembles. Forecasting, 5(1), 196–209. https://doi.org/10.3390/forecast5010010
Naifar, N., & Altamimi, S. (2023). Asymmetric impact of investor sentiment and media coverage news on Bitcoin returns. Managerial Finance, 49(8), 1342–1354. https://doi.org/10.1108/mf-08-2022-0400
Neuhierl, A., & Schlusche, B. (2011). Data snooping and market-timing rule performance. Journal of Financial Econometrics, 9(3), 550–587. https://doi.org/10.1093/jjfinec/nbq032
Panagiotidis, T. (2010). An out-of-sample test for nonlinearity in financial time series: An empirical application. Computational Economics, 36(2), 121–132. https://doi.org/10.1007/s10614-010-9225-z
Politis, D. N., & Romano, J. P. (1994). The stationary bootstrap. Journal of the American Statistical Association, 89(428), 1303–1313. https://doi.org/10.1080/01621459.1994.10476870
Ranjan, S., Kayal, P., & Saraf, M. (2023). Bitcoin price prediction: A machine learning sample dimension approach. Computational Economics, 61(4), 1617–1636. https://doi.org/10.1007/s10614-022-10262-6
Romano, J. P., & Wolf, M. (2005). Stepwise multiple testing as formalized data snooping. Econometrica, 73(4), 1237–1282. https://doi.org/10.1111/j.1468-0262.2005.00615.x
Su, X., Zhan, W., & Li, Y. (2021). Quantile dependence between investor attention and cryptocurrency returns: Evidence from time and frequency domain analyses. Applied Economics, 53(55), 6439–6471. https://doi.org/10.1080/00036846.2021.1940826
Subramaniam, S., & Chakraborty, M. (2020). Investor attention and cryptocurrency returns: Evidence from quantile causality approach. Journal of Behavioral Finance, 21(1), 103–115. https://doi.org/10.1080/15427560.2019.1629587
Suhonen, A., Lennkh, M., & Perez, F. (2017). Quantifying backtest overfitting in alternative beta strategies. The Journal of Portfolio Management, 43(2), 90–104. https://doi.org/10.3905/jpm.2017.43.2.090
Svogun, D., & Bazán-Palomino, W. (2022). Technical analysis in cryptocurrency markets: Do transaction costs and bubbles matter? Journal of International Financial Markets, Institutions and Money, 79, 101601. https://doi.org/10.1016/j.intfin.2022.101601
Szeberényi, A., & Kovács, M. I. (2026). Fear, greed and Bitcoin return distributions: Evidence from digital asset market states. Digital Finance, 8(3), 50. https://doi.org/10.1007/s42521-026-00218-y
White, H. (2000). A reality check for data snooping. Econometrica, 68(5), 1097–1126. https://doi.org/10.1111/1468-0262.00152
Yae, J., & Luo, Y. (2023). Robust monitoring machine: A machine learning solution for out-of-sample R²-hacking in return predictability monitoring. Financial Innovation, 9(1), 94. https://doi.org/10.1186/s40854-023-00497-z
Yi, E., Yang, B., Jeong, M., Sohn, S., & Ahn, K. (2023). Market efficiency of cryptocurrency: Evidence from the Bitcoin market. Scientific Reports, 13(1), 4789. https://doi.org/10.1038/s41598-023-31618-4
Zhu, P., Zhang, X., Wu, Y., Zheng, H., & Zhang, Y. (2021). Investor attention and cryptocurrency: Evidence from the Bitcoin market. PLOS ONE, 16(2), e0246331. https://doi.org/10.1371/journal.pone.0246331
