ANALYSIS OF PRICE DYNAMICS OF BLOCKCHAIN-BASED CARBON CREDIT TOKENS IN THE CRYPTOCURRENCY MARKET USING DEEP LEARNING METHODS

Aynur İncekırık

doi:10.37880/cumuiibf.1940487

TR EN

KRİPTO PARA PİYASASINDA BLOCKCHAİN TABANLI KARBON KREDİ TOKENLERİNİN FİYAT DİNAMİKLERİNİN DERİN ÖĞRENME YÖNTEMLERİYLE ANALİZİ

Öz

Bu çalışmanın amacı, blockchain tabanlı karbon kredi tokenleri olan Base Carbon Tonne (BCT), Moss Carbon Credit (MCO2) ve KlimaDAO (KLIMA) ile ana akım kripto varlıklar olan Bitcoin (BTC), Ethereum (ETH), Cardano (ADA) ve Solana (SOL) ile spekülatif nitelikli Carboncoin (CARBON)’in günlük kapanış fiyat dinamiklerini derin öğrenme modelleriyle analiz etmeyi amaçlamaktadır. Analizde ayrıca piyasa duyarlılığını temsil eden Fear & Greed Endeksi, çok değişkenli modele girdi olarak dahil edilmiştir. Çalışmada 21.10.2021–01.11.2025 dönemine ait günlük kapanış fiyatları kullanılmış; değişkenler arası ilişkiler Pearson korelasyon analiziyle incelenmiştir. Çalışmada kullanılan veriler Yahoo Finance ve AI Key API üzerinden temin edilmiştir. Sonuçlar, BCT ve MCO2 arasında güçlü pozitif, bu tokenlerin BTC ile aralarında zayıf negatif korelasyon bulunduğunu göstermektedir. Bu bulgu, karbon kredi tokenlerinin ana kripto piyasasından kısmen bağımsız bir yapı sergilediğini ve kendi içinde ise tutarlı bir yapı oluşturduğunu ortaya koymaktadır. Ayrıca, CARBON ile ana kripto varlıklar arasında zayıf ya da orta düzeyde ilişki belirlenirken, Fear & Greed Endeksi’nin BTC, ETH ve SOL ile orta, karbon kredi tokenleri ile zayıf düzeyde ilişkili olduğu görülmüştür. Modelleme sürecinde LSTM, GRU, Transfer-LSTM ve Transfer-GRU mimarileri kullanılmış; veriler kronolojik bütünlük gözetilerek %70 eğitim, %30 doğrulama ve %30 test olarak ayrılmış; modeller MSE, RMSE, MAE, MAPE ve R² ölçütleriyle değerlendirilmiştir. Elde edilen sonuçlar, GRU mimarisinin genel olarak en yüksek tahmin doğruluğu sunduğunu ve BTC, ETH, BCT ve CARBON fiyat tahminlerinde yüksek R² ve düşük hata oranlarıyla öne çıktığını göstermektedir. KLIMA ve Fear & Greed (F&G) Endeksi tahminlerinde ise transfer öğrenme modelleri görece daha iyi performans sergilemiştir. Genel olarak çalışma, derin öğrenme ve transfer öğrenme yaklaşımlarının tokenleştirilmiş karbon kredi piyasalarının fiyat davranışlarını modellemede etkili olduğunu göstermektedir. Burada, transfer öğrenmenin her senaryoda otomatik üstünlük sağlamadığı, ancak belirli varlık gruplarında stratejik katkı sunduğu değerlendirilmektedir. Bu çalışma, dijital ekonomide sürdürülebilir finans araçlarının fiyatlanmasında yapay zekâ temelli modellerin stratejik bir karar destek mekanizması sunduğunu göstermektedir.

Anahtar Kelimeler

Etik Beyan

Bu çalışma etik kurul onayı gerektirmez.

Teşekkür

Thanks to the journal board.

ANALYSIS OF PRICE DYNAMICS OF BLOCKCHAIN-BASED CARBON CREDIT TOKENS IN THE CRYPTOCURRENCY MARKET USING DEEP LEARNING METHODS

Öz

The aim of this study is to analyze the price dynamics of blockchain-based carbon credit tokens, namely Base Carbon Tonne (BCT), Moss Carbon Credit (MCO2), and KlimaDAO (KLIMA) as well as mainstream crypto assets such as Bitcoin (BTC), Ethereum (ETH), Cardano (ADA), and Solana (SOL) and the speculative asset Carboncoin (CARBON). In addition, the Fear & Greed Index, which represents investor sentiment, has been incorporated into the model in line with the role of sentiment-driven effects in price formation processes in cryptocurrency markets, as highlighted in the literature. The study utilized daily closing prices from the period October 21, 2021, to November 1, 2025; correlation analyses were performed on raw daily price series using the Pearson correlation method, which was chosen to examine the direction and strength of the linear relationship between variables. Prior to modeling, the dataset was cleaned, Min-Max normalization was applied, and it was split into a 70% training set and a 30% test set while preserving chronological integrity. While the assumption of stationarity in time series is important from the perspective of classical econometric approaches, this study focuses on deep learning-based methods within the scope of nonlinear modeling frameworks. The data used in the study were obtained from Yahoo Finance and the AI Key API. The findings indicate that there are strong internal linkages among carbon credit tokens. In particular, while a strong positive relationship was observed between BCT and MCO2, it was determined that these tokens exhibit a weak negative correlation with Bitcoin. This suggests that carbon credit tokens are only marginally linked to the broader crypto market but form a more cohesive structure within their own ecosystem. Additionally, it was observed that the CARBON asset exhibits relationships ranging from weak to moderate with major crypto assets. The Fear & Greed Index, meanwhile, showed moderate relationships with BTC, ETH, and SOL, and weaker relationships with carbon credit tokens. During the modeling process, LSTM, GRU, Transfer-LSTM, and Transfer-GRU architectures were used; the data was split into 70% training, 30% validation, and 30% test sets while maintaining chronological integrity; the models were evaluated using MSE, RMSE, MAE, MAPE, and R² metrics. The results show that the GRU architecture generally offers the highest prediction accuracy, while transfer learning models perform relatively better in predictions for the KLIMA and Fear & Greed (F&G) Index. Overall, the study demonstrates that deep learning and transfer learning approaches are effective in modeling price behavior in tokenized carbon credit markets. Here, it is assessed that transfer learning does not automatically provide an advantage in every scenario, but offers strategic contributions for specific asset groups. In conclusion, the study demonstrates that AI-based models can be used as a decision-support mechanism in the pricing of sustainable financial instruments in the digital economy.

Anahtar Kelimeler

Etik Beyan

This study does not require ethical committee approval.

Teşekkür

Dergi kuruluna teşekkür ederim.

Kaynakça

Abiodun, T. P., Nwulu, N. I., & Olukanmi, P. O. (2024). Application of blockchain technology in carbon trading market: A systematic review. IEEE Access, 13, 5446-5470. https://doi.org/10.1109/ACCESS.2024.3523672
Akarsu, O. N. (2025). Bitcoin Price Forecasting Using Machine Learning and Deep Learning Methods: Explaining the Most Effective Model via SHAP Analysis. In: Ok Ergün, H. & Ergün, T. (eds.), Current Research in the Field of Digital Finance. Özgür Publications. DOI: https://doi.org/10.58830/ozgur.pub785.c3294
Alternative.me. (2025). Crypto Fear & Greed Index historical values [Data set]. https://api.alternative.me/fng/?limit=0, Accessed on (11/26/2025)
Ballesteros-Rodríguez A, De-Lucio J, and Sicilia M-Á (2024). Tokenized carbon credits in voluntary carbon markets: the case of KlimaDAO. Front. Blockchain 7:1474540. https://doi.org/10.3389/fbloc.2024.1474540
Bhattacharyya, A., Chakraborty, T., & Rai, S. N. (2022). Stochastic forecasting of COVID-19 daily new cases across countries with a novel hybrid time-series model. Nonlinear Dynamics, 107(3), 3025–3040. https://doi.org/10.1007/s11071-021-07099-3
Büyükkantarcı Tolgay, S. (2023). The impact of digital transformation on sustainable competitive advantage. In C. Dumrul, Z. Kılıçarslan, & Y. Dumrul (Eds.), Current research on digitalization and digital transformation (pp. 73–89). Ekin Publishing House.
Cao, H., Gu, H., & Guo, X. (2023). Feasibility of transfer learning: A mathematical framework. arXiv preprint arXiv:2305.12985.
Caruana, R. (1997). Multitask learning. Machine Learning, 28(1), 41–75. https://doi.org/10.1023/A:1007379606734

Cho, K., van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning phrase representations using RNN encoder–decoder for statistical machine translation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 1724–1734). Association for Computational Linguistics. https://doi.org/10.3115/v1/D14-1179
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555. https://doi.org/10.48550/arXiv.1412.3555
CoinGecko. (2025). CoinGecko API. https://www.coingecko.com/en/api, Accessed on (11/26/2025)
Çoban, E. (2025). Time Series-Based Temperature Forecasting for Isparta Province Using LSTM and Hybrid CNN–LSTM Deep Learning Approaches. Uluborlu Journal of Vocational Sciences, 8(3), 104-117. https://doi.org/10.71445/umbd.1761095
Diaz-Valdivia, A., & Poblet-Balcell, M. (2025). The Governance of the ReFi Ecosystem: Integrity in Voluntary Carbon Markets as a Common Resource. International Journal of the Commons, 19(1).
Ene Yalçın, S. (2025). Estimation of CO₂Emissions in Transportation Systems Using Artificial Neural Networks, Machine Learning, and Deep Learning: A Comprehensive Approach. Systems, 13(3), 194. https://doi.org/10.3390/systems13030194
Eylasov, N., & Çiçek, M. (2024). Forecasting Cryptocurrency Prices: A Comparison of ARIMA-GARCH and LSTM Methods. Journal of Finance, Economics, and Social Research, 9(1), 48-62. https://doi.org/10.29106/fesa.1380870
Gautam, M. (2025). Crypto price prediction using LSTM+XGBoost. arXiv preprint arXiv:2506.22055.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
Hao, J., Bao, X., Guan, S., & Jiang, G. (2023). Transfer Prediction for the Price Volatility of Carbon Trading with Hybrid Gated Recurrent Unit. Available at SSRN 4648762.
He, Q. Q., Pang, P. C. I., & Si, Y. W. (2019). Transfer learning for financial time series forecasting. In Pacific rim international conference on artificial intelligence (pp. 24-36). Cham: Springer International Publishing.
Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.
İlhan, C., & Şahin, A. E. (2025). Evaluation of the EU Aviation Sector’s Progress Towards Net-Zero CO2 Emission by 2050. Süleyman Demirel University Visioner Journal, 16(45), 261–277. https://doi.org/10.21076/vizyoner.1500869
Kaur, R., Uppal, M., Gupta, D., Juneja, S., Arafat, S. Y., Rashid, J., ... & Alroobaea, R. (2025). Development of a cryptocurrency price prediction model: leveraging GRU and LSTM for Bitcoin, Litecoin, and Ethereum. Peer J Computer Science, 11, e2675.
Kılıçarslan, Z., & Dumrul, Y. (2023). On digitalization and its effects on the economy. In C. Dumrul, Z. Kılıçarslan, & Y. Dumrul (Eds.), Current research on digitalization and digital transformation (pp. 1–27). Ekin Publishing House.
Kotsompolis, G., Cheilas, P., Konstantakis, K. N., Sfakianakis, E., Goutte, S., & Michaelides, P. G. (2026). Smart forecasting of carbon prices using machine learning and neural networks: when ARIMA meets XGBoost and LSTM. Journal of Forecasting, 45(1), 47-60.
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444.
Li, Y., Yang, N., Bi, G., Chen, S., Luo, Z., & Shen, X. (2025). Carbon Price Forecasting Using a Hybrid Deep Learning Model: TKMixer-BiGRU-SA. Symmetry, 17(6), 962. https://doi.org/10.3390/sym17060962
Lin, R., Zhang, D., Ling, L., Huang, J., & Cai, G. (2023). Transfer learning based on long short-term memory network for financial time series forecasting. In M. Tanveer, S. Agarwal, S. Ozawa, A. Ekbal, & A. Jatowt (Eds.), Neural information processing (pp. 1–12). Springer. https://doi.org/10.1007/978-981-99-1645-0_1
Mitchell, T. M. (1997). Machine Learning. New York: McGraw-Hill.
Naeem, M. A., Mbarki, I., & Shahzad, S. J. H. (2021). Predictive role of online investor sentiment for cryptocurrency market: Evidence from happiness and fears. International Review of Economics & Finance, 73, 496-514.
Nguyen, T.-T., & Yoon, S. (2019). A Novel Approach to Short-Term Stock Price Movement Prediction using Transfer Learning. Applied Sciences, 9(22), 4745. https://doi.org/10.3390/app9224745
Saracık, Ö., & İncekırık, A. (2023). Stock Price Forecasting with Deep Learning Techniques. Alphanumeric Journal, 11(2), 137-156. https://doi.org/10.17093/alphanumeric.1357466
Shen, Z., Zhang, Y., Lu, J., Xu, J., & Xiao, G. (2020). A novel time series forecasting model with deep learning: A case study on international tourism demand. Neurocomputing, 396, 302–313. https://doi.org/10.1016/j.neucom.2018.12.084
Sorensen, D. (2023). Tokenized carbon credits: Opportunities and challenges in voluntary markets. Ledger, 8, 283–304. https://doi.org/10.5195/ledger.2023.294
Thalhammer, F., Schöttle, P., Janetschek, M., & Ploder, C. (2022). Blockchain use cases against KLIMA destruction. Cloud Computing and Data Science, 3(2), 60–76. https://doi.org/10.37256/ccds.3220221277
Thompson, A. (2022). Transfer learning with time series prediction: Review. SSRN. https://doi.org/10.2139/ssrn.4214809
Tlili, H. (2025). Blockchain and tokenized carbon markets: Empirical evidence on market efficiency and transaction dynamics. Sustainable Futures,10, 101109.
Turing, A. M. (1987). Computing machinery and intelligence (1950). Mind, 59(236), 33-60.
Wang, H., Pang, Y., & Shang, D. (2024). Carbon price fluctuation prediction using blockchain information: A new hybrid machine learning approach. arXiv preprint arXiv:2411.02709.
Wang, J. N., Liu, H. C., & Hsu, Y. T. (2024). A U-shaped relationship between the crypto fear-greed index and the price synchronicity of cryptocurrencies. Finance Research Letters, 59, 104763.
Yahoo Finance. (2025). Historical daily closing prices for BTC-USD, ETH-USD, KLIMA-USD, and other carbon tokens [Data set]. https://finance.yahoo.com/ Accessed on (11/26/2025)
Yang, F., Abedin, M. Z., Hajek, P., & Qiao, Y. (2025). Blockchain and machine learning in the green economy: Pioneering carbon neutrality through innovative trading technologies. IEEE Transactions on Engineering Management.
Yousufi, M. L., & İncekırık, A. (2024). An analysis of Ethereum price forecasting in the digital economy using deep learning techniques. In GENÇLERLE 360° 10th International Student Congress / The Circular Economy in a Globalizing World – Recycling / Circular Economy in the Globalizing World (Vol. 1, (1), 58–66). Manisa Celal Bayar University. https://genclerle360.mcbu.edu.tr/wp-content/uploads/sites/11/2025/01/01.08.-Onuncu-bildiri-kitabi.pdf
Zhang, X., Dou, Y., Mao, J., Liu, W., & Han, H. (2023). Carbon Price Forecasting Approach Based on Multi-Scale Decomposition and Transfer Learning. Journal of Beijing Institute of Technology, 32(2), 242–255.

Ayrıntılar

Birincil Dil

İngilizce

Konular

Ekonometrik ve İstatistiksel Yöntemler

Bölüm

Araştırma Makalesi

Yazarlar

Aynur İncekırık ^*
0000-0002-5029-6036
Türkiye

Yayımlanma Tarihi

26 Temmuz 2026

Gönderilme Tarihi

29 Nisan 2026

Kabul Tarihi

28 Haziran 2026

Yayımlandığı Sayı

Yıl 2026 Cilt: 27 Sayı: 3

DOI

https://doi.org/10.37880/cumuiibf.1940487

IZ

https://izlik.org/JA73TX58ZE

Kaynak Göster

RIS / Bibtex

APA

İncekırık, A. (2026). ANALYSIS OF PRICE DYNAMICS OF BLOCKCHAIN-BASED CARBON CREDIT TOKENS IN THE CRYPTOCURRENCY MARKET USING DEEP LEARNING METHODS. Cumhuriyet Üniversitesi İktisadi ve İdari Bilimler Dergisi, 27(3), 872-893. https://doi.org/10.37880/cumuiibf.1940487

AMA

1.İncekırık A. ANALYSIS OF PRICE DYNAMICS OF BLOCKCHAIN-BASED CARBON CREDIT TOKENS IN THE CRYPTOCURRENCY MARKET USING DEEP LEARNING METHODS. Cumhuriyet Üniversitesi İktisadi ve İdari Bilimler Dergisi. 2026;27(3):872-893. doi:10.37880/cumuiibf.1940487

Chicago

İncekırık, Aynur. 2026. “ANALYSIS OF PRICE DYNAMICS OF BLOCKCHAIN-BASED CARBON CREDIT TOKENS IN THE CRYPTOCURRENCY MARKET USING DEEP LEARNING METHODS”. Cumhuriyet Üniversitesi İktisadi ve İdari Bilimler Dergisi 27 (3): 872-93. https://doi.org/10.37880/cumuiibf.1940487.

EndNote

İncekırık A (01 Temmuz 2026) ANALYSIS OF PRICE DYNAMICS OF BLOCKCHAIN-BASED CARBON CREDIT TOKENS IN THE CRYPTOCURRENCY MARKET USING DEEP LEARNING METHODS. Cumhuriyet Üniversitesi İktisadi ve İdari Bilimler Dergisi 27 3 872–893.

IEEE

[1]A. İncekırık, “ANALYSIS OF PRICE DYNAMICS OF BLOCKCHAIN-BASED CARBON CREDIT TOKENS IN THE CRYPTOCURRENCY MARKET USING DEEP LEARNING METHODS”, Cumhuriyet Üniversitesi İktisadi ve İdari Bilimler Dergisi, c. 27, sy 3, ss. 872–893, Tem. 2026, doi: 10.37880/cumuiibf.1940487.

ISNAD

İncekırık, Aynur. “ANALYSIS OF PRICE DYNAMICS OF BLOCKCHAIN-BASED CARBON CREDIT TOKENS IN THE CRYPTOCURRENCY MARKET USING DEEP LEARNING METHODS”. Cumhuriyet Üniversitesi İktisadi ve İdari Bilimler Dergisi 27/3 (01 Temmuz 2026): 872-893. https://doi.org/10.37880/cumuiibf.1940487.

JAMA

1.İncekırık A. ANALYSIS OF PRICE DYNAMICS OF BLOCKCHAIN-BASED CARBON CREDIT TOKENS IN THE CRYPTOCURRENCY MARKET USING DEEP LEARNING METHODS. Cumhuriyet Üniversitesi İktisadi ve İdari Bilimler Dergisi. 2026;27:872–893.

MLA

İncekırık, Aynur. “ANALYSIS OF PRICE DYNAMICS OF BLOCKCHAIN-BASED CARBON CREDIT TOKENS IN THE CRYPTOCURRENCY MARKET USING DEEP LEARNING METHODS”. Cumhuriyet Üniversitesi İktisadi ve İdari Bilimler Dergisi, c. 27, sy 3, Temmuz 2026, ss. 872-93, doi:10.37880/cumuiibf.1940487.

Vancouver

1.Aynur İncekırık. ANALYSIS OF PRICE DYNAMICS OF BLOCKCHAIN-BASED CARBON CREDIT TOKENS IN THE CRYPTOCURRENCY MARKET USING DEEP LEARNING METHODS. Cumhuriyet Üniversitesi İktisadi ve İdari Bilimler Dergisi. 01 Temmuz 2026;27(3):872-93. doi:10.37880/cumuiibf.1940487