Yazarlar
Yayınlar
- MakaleYayıncıda açık erişim2026Asymmetric Nexus Between Gold and Bitcoin: New Evidence from Hidden Cointegration Approach
Yildiz, Umit
The main objective of this study is to investigate the symmetric and asymmetric linkages between gold, a traditional investment instrument, and Bitcoin, often referred to as the digital gold of cryptocurrencies, and to determine their direction and magnitude. Forthis purpose, the study examines cointegration relationships amongthe variables using weekly data from January 2, 2022, to April 5, 2026. According to the Engle & Granger (1987) cointegration test, there is no long-term relationship between the variables. However, the Granger &Yoon (2002) hidden cointegration test determined hidden cointegration relationships from the gold's positive components to the Bitcoin's positive components and from the Bitcoin's positive components to the gold's negative components. Subsequently, longterm coefficients are estimated using FMOLS, DOLS, and CCR estimators. The results show that a 1% increase in gold's positive shocks leads to approximately a 0.92%-0.95% decrease in Bitcoin's positive shocks. A 1% increase in Bitcoin's positive shocks results in approximately a 0.08%-0.10% increase in gold's negative shocks. The estimation results show that increases in gold prices significantly constrain the rise in Bitcoin prices, but the impact of Bitcoin price increases on gold price decreases remains limited. Finally, the findings demonstrate that gold's market-making capacity as a traditional investment vehicle is stronger than that of modern financial investment vehicles.
- MakaleYalnız künye2026Scopus SJRQ4Global Economic Policy Uncertainty and Bitcoin: A Transient Nexus
Yıldız, Ümit
Uncertainty plays a significant role in shaping investment decisions, both directly and indirectly. In an uncertain economic environment, investors’ motivations for decision-making may vary. While some investors tend to seek safe-haven assets, others may engage in speculative behavior. Therefore, uncertainty can influence financial instruments through various mechanisms. One of these instruments is Bitcoin, which is often regarded as the “gold” of cryptocurrencies. Compared to traditional financial investment instruments, Bitcoin exhibits higher volatility and is among the primary assets that may be affected by uncertainty. However, an important question is whether this effect is temporary or per-manent. By adopting a frequency-domain causality approach, this study seeks to investigate the causal linkages between Global Economic Policy Uncertainty (GEPU) and Bitcoin price movements. In this context, the causal nexus between GEPU and BTC prices is examined for the entire period and for different frequencies. Although the study's findings show no causal nexus between the variables over the entire period, the analyses for the short, medi-um, and long run indicate a causal relationship from GEPU to BTC in the medium run. Accordingly, GEPU can be considered one of the factors affecting BTC price; however, its impact does not appear to be persistent.
- MakaleAçık Erişim2026Scopus SJRQ2The Effect of Data Types’ on the Performance of Machine Learning Algorithms for Cryptocurrency Prediction
Tanrikulu, Hulusi Mehmet; Pabuccu, Hakan
Forecasting cryptocurrencies as a financial issue is crucial as it provides investors with possible financial benefits. A slight improvement in forecasting performance can lead to increased profitability; Therefore, obtaining a realistic forecast is very important for investors. Bitcoin, frequently mentioned in recent due to its volatility and chaotic behavior, has become an investment tool, especially during and after the COVID-19 pandemic. In this study, selected ML techniques were investigated for predicting cryptocurrency movements by using technical indicator-based data sets and measuring the applicability of the techniques to cryptocurrencies that do not have sufficient historical data. In order to measure the effect of data size, Bitcoin’s last 1 year and 7 years of data were used. Following the related literature, Google trends and the number of tweets were used as input features, in addition to the most commonly used twelve technical indicators. Random Forest, K-Nearest Neighbors, Extreme Gradient Boosting (XGBoost-XGB), Support Vector Machine (SVM), Naive Bayes (NB), Artificial Neural Networks (ANN), and Long-Short-Term Memory (LSTM) network were optimized for best results. Accuracy, F1, and area under the ROC curve values were used to compare the model performance. For continuous data, ANN and SVM performed the best with the highest accuracy and outperformed the other ML models for complete and reduced sets. LSTM reached the best accuracy for trend data, but SVM, NB, and XGB models showed similar performance. The research shows that some indicators significantly affect prediction performance, and the data discretization process also improved the model’s accuracy. While the number of samples affects the results of many ML models, correctly optimized and fine-tuned models may also give excellent results even with less data.
AtıfScopus1OpenAlex2
İncele - Yüksek Lisans TeziAçık Erişim2021Bitcoin fiyat hareketlerinin makine öğrenme algoritmaları ile tahmini
Hulusi Mehmet Tanrıkulu
Kripto para terimi her ne kadar finans dünyasına geçtiğimiz on yıl içerisinde girmiş olsa da başlangıç döneminde var olan güven kaygıları yenmiş ve bir ticaret ve yatırım aracı olarak piyasalarda yerini almıştır. Kripto para birimlerinin internet kaynaklı bir değer olması, arzının sınırlı olması, bir merkeze bağlı olmaması ve 7/24 anında finansal işlemlerin yapılabilmesi kripto paraları cazip bir yatırım aracı haline getirmektedir. Günümüzde bilinen binin üzerinde kripto para birimi vardır. Bu kripto para birimlerinin ilki ve en yaygın kullanılanı olan Bitcoin'dir. Son günlerde fiyatlarındaki hareketlilikten dolayı medyada kendinden sıkça söz ettiren Bitcoin, sadece yatırım olmaktan çıkmış günlük ihtiyaçlarında karşılanabildiği genel bir değer haline gelmiştir. Bu çalışmada Blok Zincir, Kripto Para kavramlarına değinilerek, şimdiye kadar Bitcoin özelinde fiyat hareketlerinin tahminlerinde kullanılan makine öğrenme algoritmaları, tahmin için kullanılan analiz göstergeleri(indikatörler) ve geçmiş akademik çalışmalarda izlenen yöntemler ve verimlilik bulguları üzerine incelemeler yapılmıştır. Yapılan incelemeler sonunda; makine öğrenme yöntemlerinin çok veri ve az veri ile performansların kıyaslanabilmesi adına geçtiğimiz 7 yıllık ve 1 yıllık Bitcoin hareketleri üzerine analizler yapılmıştır. Teknik indikatörlerle beraber günlük Tweet sayıları ve Google Arama Trendleri verisinin dahil edildiği veri setleri 7 farklı makine öğrenme yöntemi ile fiyat yönünün tespiti üzerine performans analizi yapılmıştır. Son olarak eğitilen makine öğrenme yöntemlerinin tahmin performansları yeni bir veri seti üzerinde ölçülmüştür. Bu performans analizleri ile, henüz uzun vadeli verisi oluşmamış yeni kripto paraların fiyat yönü tahmininde kullanılabilecek makine öğrenme yöntemlerinin belirlenmesinde yol gösterici olması hedeflenmiştir.