Bitcoin Fiyat Tahmininde Makine Öğrenimi ve Nitel Değişkenler: Model Performansının Uygulamalı Değerlendirmesi

Year 2025, Volume: 9 Issue: 1, 18 - 30, 30.06.2025

Gökhan Seçme

https://doi.org/10.69851/car.1718027

Abstract

Bu çalışmada tahmin yöntemlerinin performans değerlendirmesi için Bitcoin fiyat tahmini problem kullanılmıştır. Bitcoin fiyat tahmini için geleneksel doğrusal regresyon yöntemi ile makine öğrenmesi uygulamalarından neural net fitting ve neural net time series yöntemleri karşılaştırılmıştır. Ayrıca Bitcoin fiyatının volatilitesinin yüksek olması ve sosyal, politik ve davranışsal olayların etkili olması sebebiyle kalitatif faktörlerin de tahmin performansı üzerindeki etkileri incelenmiştir. Bu bağlamda Bitcoin fiyat tahmininde kullanılan kantitatif değişkenlere ilave olarak kalitatif değişkenler olarak korku ve açgözlülük indeksi ve duyarlılık indeks değerleri de kullanılarak oluşturulan modellerin tahmini yapılmıştır. Elde edilen sonuçlara göre, geleneksel çoklu doğrusal regresyon yönteminin tahmin performansının oldukça zayıf olduğu, neural net fitting metodunun ise göreli olarak daha başarılı tahminler yapabildiği görülmüştür. Ayrıca, tek başına kantitatif değişkenlerin kullanıldığı modelin çalışmada kullanılan tüm tahmin yöntemlerinde zayıf performans sergilediği görülmüştür. Kalitatif değişkenlerin kullanıldığı tahmin modelinin ise tüm yöntemlerde en başarılı tahmin sonuçları ürettiği görülmüştür. Dolayısıyla Bitcoin fiyat tahmininde kalitatif değişkenlerin kullanılmasının tahmin performansını arttırdığı, bununla birlikte neural net fitting tahmin yönteminin düşük MSE değerleri ile en başarılı tahmin yönetimi olduğu belirlenmiştir.

Keywords

Tahmin , Bitcoin fiyat tahmini , Makine öğrenmesi , Nitel değişkenler

Machine Learning and Qualitative Variables in Bitcoin Price Prediction: An Empirical Evaluation of Model Performance

Abstract

This study employs the problem of Bitcoin price prediction to evaluate the performance of forecasting methods. Traditional linear regression is compared with machine learning techniques, specifically neural net fitting and neural net time series, to assess their predictive accuracy. Given Bitcoin’s high volatility and susceptibility to social, political, and behavioral influences, the study also examines the impact of qualitative factors on prediction performance. In addition to quantitative variables, qualitative variables—such as the Fear and Greed Index and sentiment analysis metrics—are incorporated into the models to enhance forecasting robustness.
The results indicate that traditional multiple linear regression yields relatively weak predictive performance, whereas neural net fitting demonstrates superior accuracy. Furthermore, models relying solely on quantitative variables underperform across all tested methods. In contrast, the inclusion of qualitative variables significantly improves prediction outcomes in all approaches. The study concludes that integrating qualitative variables enhances Bitcoin price forecasting accuracy, with neural net fitting emerging as the most effective method due to its lower mean squared error (MSE) values.

Keywords

Forecasting , Bitcoin price forecasting , Machine learning , Qualitative variables

References

• Abraham, J., Higdon, D., Nelson, J., & Ibarra, J. (2018). Cryptocurrency price prediction using tweet volumes and sentiment analysis. SMU Data Science Review, 1(3), 1.
• Baker, M., & Wurgler, J. (2006). Investor sentiment and the cross-section of stock returns. Journal of Finance, 61(4), 1645-1680. https://doi.org/10.1111/j.1540-6261.2006.00885.x
• Baur, D. G., & Dimpfl, T. (2021). The impact of fear and greed on Bitcoin returns. Finance Research Letters, 39, 101573.
• Biais, B., Bisière, C., & Bouvard, M. (2023). The Blockchain Folk Theorem. Review of Financial Studies, 36(2), 599-636.
• Böhme, R., Christin, N., Edelman, B., & Moore, T. (2015). "Bitcoin: Economics, technology, and governance." Journal of Economic Perspectives.
• Bouoiyour, J., & Selmi, R. (2015). What does Bitcoin look like? Economics Bulletin, 35(4), 2548–2559.
• Demirci, E., & Karaatlı, M. (2023). Kripto para fiyatlarinin lstm ve gru modelleri ile tahmini. Journal of Mehmet Akif Ersoy University Economics and Administrative Sciences Faculty, 10(1), 134-157. https://doi.org/10.30798/makuiibf.1035314
• Chaum, D. (1983). "Blind signatures for untraceable payments." Advances in Cryptology.
• Chu, J., Chan, S., Nadarajah, S., & Osterrieder, J. (2015). GARCH modelling of cryptocurrencies. Journal of Risk and Financial Management, 8(4), 447–464.
• Ciaian, P., Rajcaniova, M., & Kancs, D. (2016). The economics of Bitcoin price formation. Applied Economics, 48(19), 1799–1815.
• CoinMarketCap (2018). Historical Bitcoin Price Data.
• Cong, L. W., Li, Y., & Wang, N. (2021). Tokenomics: Dynamic adoption and valuation. Review of Financial Studies, 34(3), 1105-1155.
• Corbet, S., Larkin, C., & Lucey, B. (2020). "The contagion effects of the COVID-19 pandemic on Bitcoin and traditional assets." Finance Research Letters.
• Corbet, S., Lucey, B., & Yarovaya, L. (2018). "Datesamping the Bitcoin and Ethereum bubbles." Finance Research Letters, 26, 81-88.
• Demirci, E., & Karaatlı, M. (2023). Kripto para fiyatlarinin lstm ve gru modelleri ile tahmini. Journal of Mehmet Akif Ersoy University Economics and Administrative Sciences Faculty, 10(1), 134-157. https://doi.org/10.30798/makuiibf.1035314
• Financial Stability Board (2022). "Assessment of risks to financial stability from crypto-assets." FSB Report.
• Financial Stability Board. (2023). Assessment of Risks to Financial Stability from Crypto-Assets.
• Hayes, A. (2019). The Bitcoin Mining Network: Trends, Composition, and Energy Consumption. SSRN. DOI: https://dx.doi.org/10.2139/ssrn.3378231
• Hegazy, O. A., Abbas, H., & Dousoky, A. M. (2021). Forecasting cryptocurrency prices using LSTM recurrent neural networks. Expert Systems with Applications, 166, 114010. https://alternative.me/crypto/fear-and-greed-index/#google_vignette, Crypto Fear & Greed Index data, 09.06.2025.
• https://lunarcrush.com/developers/api/public/topic/:topic/time-series/v2?topic=bitcoin&bucket=day social sentiment score data, 09.06.2025.
• https://www.blockchain.com/explorer/charts/n-transactions-total, total number of transactions, hash rate data, 09.06.2025
• https://www.coingecko.com/en/coins/bitcoin/historical_data, market capitalization, total trading volume, bitcoin price data, 09.06.2025.
• In re Celsius Network LLC, Chapter 11 Case No. 22-10964 (Bankr. S.D.N.Y. 2022).
• Işıldak, M. S. (2021). Garch Modellerle Oynaklık Tahmini: Bitcoin Örneği [Volatility forecasting with GARCH models: The case of Bitcoin]. Journal of Business and Trade, 2(2), 49-61.
• Jang, H., & Lee, J. (2017). An empirical study on modeling and prediction of Bitcoin prices with Bayesian neural networks based on blockchain information. IEEE Access, 6, 5427–5437.
• Kartal, A. (2020). Modeling bitcoin prices with k-star algorithm. (2020). Business & Management Studies: An International Journal, 8(1), 213-231. https://doi.org/10.15295/bmij.v8i1.1380
• Katsiampa, P. (2017). "Volatility estimation for Bitcoin: A comparison of GARCH models." Economics Letters.
• Kim, T., Kim, H., & Kim, D. (2021). Comparative study of deep learning architectures for Bitcoin price prediction. Journal of Computational Finance, 25(1), 1–22.
• Kristjanpoller, W., & Minutolo, M. C. (2018). Forecasting volatility in Bitcoin markets: A comparative study of GARCH models. Journal of Risk and Financial Management, 11(2), 23.
• Kristoufek, L. (2015). What are the main drivers of the Bitcoin price? Evidence from wavelet coherence analysis. PLoS ONE, 10(4), e0123923.
• Teker, D., Teker, S., Gumustepe, E.D., (2024a). Backtesting Bitcoin volatility: ARCH and GARCH approaches. PressAcademia Procedia (PAP), 20, 14-16. https://doi.org/10.17261/Pressacademia.2024.1918
• Teker, D., Teker, S., Gumustepe, E. D., (2024b). Determinants of Bitcoin price movements. PressAcademia Procedia (PAP), 19, 75-78. http://doi.org/10.17261/Pressacademia.2024.1911
• Mai, F., Shan, Z., Bai, Q., Wang, X., & Chiang, R. H. L. (2018). How does social media impact Bitcoin value? A test of the silent majority hypothesis. Journal of Management Information Systems, 35(1), 19–52.
• Mallqui, D. C., & Fernandes, R. A. (2019). Predicting the direction, maximum, minimum and closing prices of daily Bitcoin exchange rate using machine learning techniques. Applied Soft Computing, 75, 596–606.
• McNally, S., Roche, J., & Caton, S. (2018). "Predicting the price of Bitcoin using machine learning." *26th Euromicro International Conference on Parallel, Distributed and Network-based Processing (PDP)*.
• Mudassir, M., Raza, B., & Ejaz, A. (2020). Bitcoin price forecasting using a high-order long short-term memory model. Financial Innovation, 6(1), 1–18.
• Nakamoto, S. (2008). "Bitcoin: A peer-to-peer electronic cash system." Whitepaper. Eylasov, N. M., & Çiçek, D. (2024). Forecasting cryptocurrency prices: A comparison of ARIMA-GARCH and LSTM methods. FESA Journal of Scientific Research, 9(1), 40-52.
• Panagiotid Böhme, R., Christin, N., Edelman, B., & Moore, T. (2015). "Bitcoin: Economics, technology, and governance." Journal of Economic Perspectives.
• Panagiotidis, T., Stengos, T., & Vravosinos, O. (2018). "On the determinants of Bitcoin returns: A LASSO approach."Finance Research Letters, 27, 235-240.
• Rotela Junior, P., Silva, J., & Amorim, L. (2023). Bitcoin price prediction using Transformer-based deep learning models. Journal of Computational Finance, 27(2), 55–77.
• Sahoo, S., Sreejith, S., & Dash, R. K. (2019). A hybrid machine learning approach for Bitcoin price prediction. Journal of Big Data, 6(1), 1–14.
• Sebastião, H., & Godinho, P. (2021). Bitcoin price forecasting with a deep multi-source model integrating technical, blockchain, and sentiment indicators. Expert Systems with Applications, 172, 114552.
• Shen, D., Urquhart, A., & Wang, P. (2019). "Does Twitter predict Bitcoin?" Economics Letters, 174, 118-122.
• Songur, M., & Ordu, S. (2023). Bitcoin haberlerinin bitcoin fiyat ve getirisi üzerine etkisi [The effect of Bitcoin news on Bitcoin price and returns]. Bingöl Üniversitesi Sosyal Bilimler Enstitüsü Dergisi [Bingöl University Journal of Social Sciences Institute], (25), 220-234. https://doi.org/10.29029/busbed.1207935
• Tabachnick, B. G., & Fidell, L. S. (2013). Using multivariate statistics (6th ed.). Pearson
• Teker, T., Konuşkan, A., Ömürbek, V., & Bekçi, İ. (2020). Bitcoin Ve Kripto Paralar Hakkında Çıkan Haberlerin Bitcoin Fiyatları Üzerine Etkisi [The impact of news about Bitcoin and cryptocurrencies on Bitcoin prices].
• Maliye Ve Finans Yazıları [Public Finance and Financial Studies], (113), 65-74. https://doi.org/10.33203/mfy.567989
• Wang, Y., & Liu, J. (2019). Integrating social media sentiment analysis into multivariate time series forecasting of Bitcoin prices. Neurocomputing, 352, 146–156.
• Yavuz, U., Özen, Ü., Taş, K., Çağlar, B. (2020). Yapay Sinir Ağları ile Blockchain Verilerine Dayalı Bitcoin Fiyat Tahmini [Bitcoin price prediction using artificial neural networks based on blockchain data]. Journal of Information Systems and Management Research, 2(1), 1-9.