Predicting Bitcoin Price Direction Using Machine Learning Models

Yıl 2024, Cilt: 2 Sayı: 2, 205 - 213, 30.12.2024

Tanju Açi , Hakan Kekül

Öz

In the financial sector, as past economic and social events have shaken trust, this trust is being regained through the internet and computer technologies. Emerging in the 19th century, financial technology has led to a new economic understanding with digital money and especially bitcoin. The decentralized structure of bitcoin and the encryption systems used for security play an important role in preventing fraud and have become the center of attention of investors. As its value has increased, studies on price predictions have naturally increased. This study aims to predict the impact of data obtained from digital economy news sites on bitcoin price using natural language processing and machine learning techniques. In line with this goal, text vectorization was performed with the TF-IDF statistical method. Synthetic Minority Oversampling Technique (SMOTE) was applied to eliminate the imbalance in the vectorized data set. Classification models such as Logistic Regression, Decision Trees, Random Forest, Support Vector Machines, K-Nearest Neighbor, Extra Trees, Bernoulli Naive Bayes and Multilayer Perceptron were applied to the obtained output.
According to the results of the performance of different machine learning models in predicting the direction of bitcoin price fluctuation, the Extra Trees Classifier model showed the highest performance with an Accuracy of 86.71%, recall of 86.71%, precision of 86.99% and F1 score of 86.59%.

Anahtar Kelimeler

Artificial Intelligence, Bitcoin, Machine Learning, Natural Language Processing, Stock Market, Crypto

Makine Öğrenimi Modelleri Kullanarak Bitcoin Fiyat Yönünü Tahmin Etme

Öz

Finans sektöründe, geçmişte yaşanan ekonomik ve sosyal olaylar güveni sarsarken, internet ve bilgisayar teknolojileri sayesinde bu güven yeniden kazanılıyor. 19. yüzyılda ortaya çıkan finansal teknoloji, dijital para ve özellikle bitcoin ile yeni bir ekonomik anlayışa yol açmıştır. Bitcoin'in merkezi olmayan yapısı ve güvenlik için kullanılan şifreleme sistemleri dolandırıcılığın önlenmesinde önemli rol oynamış ve yatırımcıların ilgi odağı haline gelmiştir. Değeri arttıkça fiyat tahminleri üzerine yapılan çalışmalar da doğal olarak artmıştır. Bu çalışma, dijital ekonomi haber sitelerinden elde edilen verilerin bitcoin fiyatı üzerindeki etkisini doğal dil işleme ve makine öğrenmesi tekniklerini kullanarak tahmin etmeyi amaçlamaktadır. Bu hedef doğrultusunda TF-IDF istatistiksel yöntemi ile metin vektörleştirmesi yapılmıştır. Vektörleştirilen veri setindeki dengesizliği gidermek için Sentetik Azınlık Aşırı Örnekleme Tekniği (SMOTE) uygulandı. Elde edilen çıktılara Lojistik Regresyon, Karar Ağaçları, Rastgele Orman, Destek Vektör Makineleri, K-En Yakın Komşu, Ekstra Ağaçlar, Bernoulli Naive Bayes ve Çok Katmanlı Perceptron gibi sınıflandırma modelleri uygulanmıştır.
Farklı makine öğrenimi modellerinin bitcoin fiyat dalgalanmasının yönünü tahmin etmedeki performans sonuçlarına göre, Ekstra Ağaçlar Sınıflandırıcı modeli %86,71 Doğruluk, %86,71 hatırlama, %86,99 kesinlik ve %86,59 F1 puanı ile en yüksek performansı göstermiştir.

Anahtar Kelimeler

Yapay Zela, Bitcoin, Makine Öğrenmesi, Doğal Dil İşleme, Borsa, Kripto

Kaynakça

• [1] D. YILDIZ, ‘Bilgi Sistemi Yazılım Geliştirme Yaşam Döngüsü Safhalarından Gereksinim Belirleme ve Sistem Tasarımında Kalite Odaklılık: Üç Proje İncelemesi’, Bilişim Teknol. Derg., vol. 15, no. 1, pp. 55–64, 2022, doi: 10.17671/gazibtd.871411.
• [2] J. P. Miguel, D. Mauricio, and G. Rodríguez, ‘A Review of Software Quality Models for the Evaluation of Software Products’, Int. J. Softw. Eng. Appl., vol. 5, no. 6, pp. 31–53, 2014, doi: 10.5121/ijsea.2014.5603.
• [3] M. D. Mulyawan, I. N. S. Kumara, I. B. A. Swamardika, and K. O. Saputra, ‘Kualitas Sistem Informasi Berdasarkan ISO/IEC 25010: Literature Review’, Maj. Ilm. Teknol. Elektro, vol. 20, no. 1, p. 15, Mar. 2021, doi: 10.24843/mite.2021.v20i01.p02.
• [4] A. Hussain and E. O. C. Mkpojiogu, ‘An application of the ISO/IEC 25010 standard in the quality-in-use assessment of an online health awareness system’, J. Teknol., vol. 77, no. 5, pp. 9–13, 2015, doi: 10.11113/jt.v77.6107.
• [5] R. D. Jayanto, ‘EVALUASI KUALITAS APLIKASI MOBILE KAMUS ISTILAH JARINGAN PADA PLATFORM ANDROID DENGAN STANDAR ISO/IEC 25010’, Elinvo (Electronics, Informatics, Vocat. Educ., vol. 2, no. 2, pp. 178–182, Dec. 2017, doi: 10.21831/elinvo.v2i2.17311.
• [6] N. YALÇIN and B. ŞİMŞEK YAĞLI, ‘TEKNOLOJİ MAĞAZALARININ ISO 25010 KALİTE MODELİNE DAYALI WEBSİTESİ KALİTE DEĞERLENDİRMESİNİN ÇOK KRİTERLİ ANALİZİ: TÜRKİYE ÖRNEĞİ’, Uluslararası İktisadi ve İdari İncelemeler Derg., pp. 57–76, Feb. 2020, doi: 10.18092/ulikidince.557263.
• [7] K. Moumane, A. Idri, F. El Aouni, J. Laghnimi, N. C. Benabdellah, and O. Hamal, ‘ISO/IEC 25010-based Quality Evaluation of Three Mobile Applications for Reproductive Health Services in Morocco’, Clin. Exp. Obstet. Gynecol., vol. 51, no. 4, 2024, doi: 10.31083/j.ceog5104088.
• [8] L. Carlos Belezia, M. Fatima Ludovico de Almeida, M. Falco, and G. Robiolo, ‘Building a Catalogue of ISO/IEC 25010 Quality Measures Applied in an Industrial Context’, J. Phys. Conf. Ser., vol. 1828, no. 1, p. 012077, Feb. 2021, doi: 10.1088/1742- 6596/1828/1/012077.
• [9] A. Di Sorbo, G. Grano, C. Aaron Visaggio, and S. Panichella, ‘Investigating the criticality of user-reported issues through their relations with app rating’, J. Softw. Evol. Process, vol. 33, no. 3, pp. 1–21, 2021, doi: 10.1002/smr.2316.
• [10] T. EREN, ‘Mobil Uygulama Seçiminde Etkili Olan Kriterlerin Belirlenmesi ve Örnek Uygulama’, Istanbul J. Econ. / İstanbul İktisat Derg., vol. 70, no. 1, pp. 113–139, Jun. 2020, doi: 10.26650/istjecon2019-0022.
• [11] I. Atoum and C. H. Bong, ‘Measuring Software Quality in Use: State-of-the-Art and Research Challenges’, vol. 17, pp. 4– 15, 2015, [Online]. Available: http://arxiv.org/abs/1503.06934
• [12] R. dos Santos, K. Villela, D. T. Avila, and L. H. Thom, ‘A practical user feedback classifier for software quality characteristics’, Proc. Int. Conf. Softw. Eng. Knowl. Eng. SEKE, vol. 2021-July, pp. 340–345, 2021, doi: 10.18293/SEKE2021-055.
• [13] B. El Fhel and A. Idri, ‘Quality In-Use of Mobile Geographic Information Systems for Data Collection’, Int. J. Adv. Comput. Sci. Appl., vol. 14, no. 11, pp. 903–913, 2023, doi: 10.14569/IJACSA.2023.0141192.
• [14] M. Haoues, R. Mokni, and A. Sellami, ‘Machine learning for mHealth apps quality evaluation: An approach based on user feedback analysis’, Softw. Qual. J., vol. 31, no. 4, pp. 1179–1209, Dec. 2023, doi: 10.1007/s11219-023-09630-8.
• [15] M. N. Zahra and K. Kraugusteeliana, ‘Analisis Kualitas Performa Aplikasi Digital Banking X Menggunakan Framework ISO 25010’, J. Teknol. Inf. dan Ilmu Komput., vol. 10, no. 3, pp. 483–490, Jul. 2023, doi: 10.25126/JTIIK.20231036326.
• [16] ‘Türkiye Bilişim Vakfı Bilgisayar Bilimleri ve Mühendisliği Dergisi » Makale » DevOps İşletim Hattının Kalite Bakış Açısı ile İrdelenmesi ve ISO/IEC 25010 Boşluk Analizinin Gerçekleştirilmesi’. Accessed: Oct. 20, 2024. [Online]. Available: https://dergipark.org.tr/tr/pub/tbbmd/issue/78526/1118200
• [17] A. KAHVECİ YETİŞ and R. DAŞ, ‘Yazılım Ürün Ölçütlerinin Uygulamalı İncelenmesi’, Fırat Üniversitesi Mühendislik Bilim. Derg., vol. 34, no. 2, pp. 635–645, 2022, doi: 10.35234/fumbd.1114056.
• [18] M. F. TUNA, ‘MOBİL UYGULAMA MÜŞTERİ GERİ BİLDİRİMİNDEKİ DUYGULARIN MAKİNE ÖĞRENMESİ YÖNTEMLERİYLE SINIFLANDIRILMASI’, J. Bus. Commun. Stud., vol. 1, no. 1, pp. 83–103, 2022, doi: 10.29228/JOBACS.63080.
• [19] M. R. Ramadhan and K. D. Hartomo, ‘Evaluasi Kualitas Website Menggunakan Webqual 4.0 (Studi Kasus: Sistem Informasi Kebencanaan Kabupaten Boyolali)’, J. Transform., vol. 19, no. 2, p. 138, Jan. 2022, doi: 10.26623/TRANSFORMATIKA.V19I2.4195.
• [20] B. ONARAN and K. K. GENÇTÜRK, ‘Mobil Belediye Aplikasyonlarında Hizmet Kalitesi: İzmir Örneği’, Uluslararası Yönetim Akad. Derg., vol. 5, no. 1, pp. 16–31, 2022, doi: 10.33712/mana.1039540.
• [21] N. YALÇIN and B. ŞİMŞEK YAĞLI, ‘TEKNOLOJİ MAĞAZALARININ ISO 25010 KALİTE MODELİNE DAYALI WEBSİTESİ KALİTE DEĞERLENDİRMESİNİN ÇOK KRİTERLİ ANALİZİ: TÜRKİYE ÖRNEĞİ’, Uluslararası İktisadi ve İdari İncelemeler Derg., pp. 57–76, Feb. 2020, doi: 10.18092/ulikidince.557263.
• [22] E. Keibach and H. Shayesteh, ‘BIM for Landscape Design Improving Climate Adaptation Planning: The Evaluation of Software Tools Based on the ISO 25010 Standard’, Appl. Sci., vol. 12, no. 2, Jan. 2022, doi: 10.3390/APP12020739.
• [23] S. Majumdar, A. Bansal, P. P. Das, P. D. Clough, K. Datta, and S. K. Ghosh, ‘Automated evaluation of comments to aid software maintenance’, J. Softw. Evol. Process, vol. 34, no. 7, Jul. 2022, doi: 10.1002/SMR.2463.
• [24] A. E. Yahya, A. Gharbi, W. M. S. Yafooz, and A. Al- Dhaqm, ‘A Novel Hybrid Deep Learning Model for Detecting and Classifying Non-Functional Requirements of Mobile Apps Issues’, Electronics, vol. 12, no. 5, Mar. 2023, doi: 10.3390/ELECTRONICS12051258.
• [25] N. D. Khan, J. A. Khan, J. Li, T. Ullah, and Q. Zhao, ‘Mining software insights: uncovering the frequently occurring issues in low-rating software applications’, PeerJ Comput. Sci., vol. 10, p. e2115, Jul. 2024, doi: 10.7717/PEERJ-CS.2115/SUPP-1.
• [26] B. I. Belinda, A. A. Emmanuel, N. Solomon, and A. B. Kayode, ‘Evaluating Software Quality Attributes using Analytic Hierarchy Process (AHP)’, Int. J. Adv. Comput. Sci. Appl., vol. 12, no. 3, pp. 165–173, 2021, doi: 10.14569/IJACSA.2021.0120321.
• [27] G. A. Pradipta, R. Wardoyo, A. Musdholifah, I. N. H. Sanjaya, and M. Ismail, ‘SMOTE for Handling Imbalanced Data Problem : A Review’, in 2021 6th International Conference on Informatics and Computing, ICIC 2021, Institute of Electrical and Electronics Engineers Inc., 2021. doi: 10.1109/ICIC54025.2021.9632912.
• [28] P. Soltanzadeh and M. Hashemzadeh, ‘RCSMOTE: Range-Controlled synthetic minority over-sampling technique for handling the class imbalance problem’, Inf. Sci. (Ny)., vol. 542, pp. 92–111, Jan. 2021, doi: 10.1016/j.ins.2020.07.014.
• [29] E. Sugawara and H. Nikaido, ‘Properties of AdeABC and AdeIJK efflux systems of Acinetobacter baumannii compared with those of the AcrAB-TolC system of Escherichia coli’, Antimicrob. Agents Chemother., vol. 58, no. 12, pp. 7250–7257, 2014, doi: 10.1128/AAC.03728-14.
• [30] A. A. Arifiyanti, A. A. Arifiyanti, and E. D. Wahyuni, ‘SMOTE: METODE PENYEIMBANG KELAS PADA KLASIFIKASI DATA MINING’, Scan J. Teknol. Inf. dan Komun., vol. 15, no. 1, pp. 34– 39, Feb. 2020, doi: 10.33005/scan.v15i1.1850.
• [31] P. A. Manilal and A. C. Suthar, ‘Object Based Image Classification of Satellite Images for Urban Areas’, 2023. Accessed: Oct. 17, 2024. [Online]. Available: http://gtusitecirculars.s3.amazonaws.com/uploads/Final Synopsis_465548.pdf
• [32] A. Pagliaro, ‘Forecasting Significant Stock Market Price Changes Using Machine Learning: Extra Trees Classifier Leads’, Electron., vol. 12, no. 21, p. 4551, Nov. 2023, doi: 10.3390/electronics12214551.
• [33] D. Baby, S. J. Devaraj, J. Hemanth, and M. M. Anishin Raj, ‘Leukocyte classification based on feature selection using extra trees classifier: A transfer learning approach’, Turkish J. Electr. Eng. Comput. Sci., vol. 29, pp. 2742–2757, 2021, doi: 10.3906/elk-2104-183.
• [34] N. Bhandari, ‘How does ExtraTreesClassifier reduce the risk of overfitting?’ [Online]. Available: https://medium.com/@namanbhandari/extratreesclassifier- 8e7fc0502c7
• [35] ‘Extra Trees Classifier’, scikit-learn Machine Learning in Python. [Online]. Available: https://scikit- learn.org/dev/modules/generated/sklearn.ensemble.ExtraTree sClassifier.html
• [36] O. O. Petinrin, X. Li, and K. C. Wong, ‘Particle Swarm Optimized Gaussian Process Classifier for Treatment Discontinuation Prediction in Multicohort Metastatic Castration- Resistant Prostate Cancer Patients’, IEEE J. Biomed. Heal. Informatics, vol. 26, no. 3, pp. 1309–1317, 2022, doi: 10.1109/JBHI.2021.3103989.
• [37] I. Achituve, A. Navon, Y. Yemini, G. Chechik, and E. Fetaya, ‘GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning’, Proc. Mach. Learn. Res., vol. 139, pp. 54– 65, Feb. 2021, Accessed: Oct. 17, 2024. [Online]. Available: https://arxiv.org/abs/2102.07868v4
• [38] ‘Gaussian Process Classification’. [Online]. Available: https://scikit- learn.org/1.5/modules/gaussian_process.html#gaussian- processes
• [39] ‘MLP Classifier’. [Online]. Available: https://scikit- learn.org/dev/modules/generated/sklearn.neural_network.ML PClassifier.html
• [40] O. Iparraguirre-Villanueva, K. Espinola-Linares, R. O. Flores Castañeda, and M. Cabanillas-Carbonell, ‘Application of Machine Learning Models for Early Detection and Accurate Classification of Type 2 Diabetes’, Diagnostics, vol. 13, no. 14, 2023, doi: 10.3390/diagnostics13142383.
• [41] M. M. Nishat, F. Faisal, T. Hasan, M. F. Bin Karim, Z. Islam, and M. R. K. Shagor, ‘An Investigative Approach to Employ Support Vector Classifier as a Potential Detector of Brain Cancer from MRI Dataset’, Proc. Int. Conf. Electron. Commun. Inf. Technol. ICECIT 2021, pp. 1–4, 2021, doi: 10.1109/ICECIT54077.2021.9641168.