Price prediction of dual-listed stocks with RF and LSTM algorithms: NYSE and BIST comparison

Year 2024, Volume: 4 Issue: 5-Special Issue: ICAME'24, 207 - 230, 31.12.2024

Emine Nihan Cici Karaboğa , Gamze Şekeroğlu , Esra Kızıloğlu , Kazım Karaboğa , Ayse Merve Acılar

https://doi.org/10.53391/mmnsa.1577228

Abstract

Companies are looking for ways to access capital from developed markets instead of local markets to find financing. While some companies use debt instruments for this purpose, others use equity financing methods. One of the techniques used in equity financing is the simultaneous registration of shares on national and foreign stock exchanges, also known as the dual-registration method. Investors entering international markets by investing in dual-registered shares is important for companies to gain capital. However, another important issue for those investing in stocks is the ability to gain capital through accurate prediction of price movements. The aim of this study is to predict the prices of Turkcell stocks traded on Borsa Istanbul and the New York Stock Exchange (NYSE) using machine learning and deep learning methodologies. The results of the analyses conducted with the Random Forest Regressor and Long Short-Term Memory algorithms, which are machine learning and deep learning algorithms, respectively, showed that both algorithms exhibited a lower error rate in predicting the closing prices of Turkcell stocks on the NYSE.

Keywords

Dual-listed stocks, LSTM, price prediction, artificial intelligence algorithms

References

• [1] Aksoy, A. and Dayı, F. Birden fazla borsada işlem gören hisse senetlerinin değerlemesi: Teorik bir inceleme. Kastamonu Üniversitesi Iktisadi ve Idari Bilimler Fakültesi Dergisi, 5(17), 33-43, (2017).
• [2] BorsaMatik, Turkcell 2024/9 Finansal Raporu, (2024). https://www.borsamatik.com.tr
• [3] InvestingPro, Turkcell (TCELL) Piyasa Değeri ve Analizleri, (2024). https://tr.investing. com
• [4] Stock Analysis, Turkcell Iletisim Hizmetleri Market Cap. Retrieved December 16, 2024, from (2024). https://stockanalysis.com
• [5] Companies Market Cap, Turkcell (TKC) Market capitalization. Retrieved December 16, 2024, from, (2024). https://companiesmarketcap.com
• [6] YCharts, Turkcell Iletisim Hizmetleri AS (TKC) Market Cap: 5.874B for Dec. 13, 2024. Retrieved December 16, 2024, from, (2024). https://ycharts.com
• [7] Civan, M. Sermaye Piyasası Analizleri ve Portföy Yönetimi. Gazi Kitabevi: Ankara, (2007).
• [8] Hamurcu, Ç. and Aslanoğlu, S. New York menkul kıymetler borsası (NYSE) ile Istanbul menkul kıymetler borsası (İMKB) arasındaki etkileşim ve her iki borsada işlem gören Turkcell hisse senetleri arasındaki ilişki. Manas Sosyal Araştırmalar Dergisi, 2(3), 27-48, (2013).
• [9] Anto, R. and Pangestuti, I.R.D. Transmission of information of the Indonesian dual listed shares. International Journal of Financial Research, 11(2), 255-261, (2020).
• [10] Rath, S. Execution costs of dual listed Australian stocks. Applied Financial Economics, 17(5), 379-389, (2007).
• [11] Duppati, G., Hou, Y. and Scrimgeour, F. The dynamics of price discovery for cross-listed stocks evidence from US and Chinese markets. Cogent Economics & Finance, 5(1), 1389675, (2017).
• [12] Liu, J., Chao, F., Chen Lin, Y.C. and Lin, C.M. Stock prices prediction using deep learning models. ArXiv Preprint:1909.12227, (2019).
• [13] Sarkissian, S. and Schill, M.J. Cross-listing waves. Journal of Financial and Quantitative Analysis, 51(1), 259-306, (2016).
• [14] Spitzer, J. The Persistence of Pricing Differentials in Dual-listed Companies in Hong Kong and China. Claremont McKenna College, Senior Thesis, (2011). [https://scholarship.claremont.edu/cmc_theses/272/]
• [15] Akusta, A. Time series analysis of long-term stock performance of airlines: The case of Turkish Airlines. Politik Ekonomik Kuram, 8(1), 160-173, (2024).
• [16] Bessembinder, H. and Kaufman, H.M. A comparison of trade execution costs for NYSE and NASDAQ-listed stocks. Journal of Financial and Quantitative Analysis, 32(3), 287-310, (1997).
• [17] Glosten, L.R. and Harris, L.E. Estimating the components of the bid/ask spread. Journal of Financial Economics, 21(1), 123-142, (1988).
• [18] Glosten, L.R. and Milgrom, P.R. Bid, ask and transaction prices in a specialist market with heterogeneously informed traders. Journal of Financial Economics, 14(1), 71-100, (1985).
• [19] Stoll, H.R. Inferring the components of the bid-ask spread: Theory and empirical tests. The Journal of Finance, 44(1), 115-134, (1989).
• [20] Lieberman, O., Ben-Zion, U. and Hauser, S. A characterization of the price behavior of international dual stocks: an error correction approach. Journal of International Money and Finance, 18(2), 289-304, (1999).
• [21] Janiesch, C., Zschech, P. and Heinrich, K. Machine learning and deep learning. Electronic Markets, 31, 685-695, (2021).
• [22] Bishop, C.M. and Nasrabadi, N.M. Pattern recognition and machine learning. New York: Springer, (2006).
• [23] Mahesh, B. Machine learning algorithms-a review. International Journal of Science and Research (IJSR), 9(1), 381-386, (2020).
• [24] Karaboğa, K. Big data and data mining. In Data, Information and Knowledge Management pp. (21-43). Istanbul, Turkey: Nobel Publishing Group, (2020).
• [25] Akusta, A. Analysis of the relationship between cross capital flows and stock exchange index with machine learning. Abant Sosyal Bilimler Dergisi, 24(1), 244-263, (2024).
• [26] Goodfellow, I., Bengio, Y. and Courville, A. Deep Learning. MIT Press: Cambridge, Massachusetts, (2016).
• [27] Kazan, S. and Karakoca, H. Makine öğrenmesi ile ürün kategorisi sınıflandırma. Sakarya University Journal of Computer and Information Sciences, 2(1), 18-27, (2019).
• [28] Schmidhuber, J. Deep learning in neural networks: An overview. Neural Networks, 61, 85-117, (2015).
• [29] Leijnen, S. and Veen, F.V. The neural network zoo. Proceedings, 47(1), 9, (2020).
• [30] Güdelek, M.U. Zaman Serisi Analiz ve Tahmini: Derin Öğrenme Yaklaşımı. Master’s Thesis, Graduate School of Engineering and Science, TOBB University of Economics and Technology, (2019).[http://193.140.108.196:8080/handle/20.500.11851/2285]
• [31] Dawani, J. Hands-On Mathematics for Deep Learning: Build a solid mathematical foundation for training efficient deep neural networks. Packt Publishing Ltd. (2020).
• [32] Miao, Y., Liu, F., Hou, T. and Liu, Y. Virtifier: a deep learning-based identifier for viral sequences from metagenomes. Bioinformatics, 38(5), 1216-1222, (2022).
• [33] Chollet, F. (2019). Deep learning with Python. Manning Publications.
• [34] Beysolow, T. Applied natural language processing with Python: Implementing Machine Learning and Deep Learning Algorithms for Natural Language Processing. Apress: Berkeley, CA, (2018).
• [35] Graves, A. and Schmidhuber, J. Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Networks, 18(5-6), 602-610, (2005).
• [36] Graves, A., Mohamed, A.R. and Hinton, G. Speech recognition with deep recurrent neural networks. In Proceedings, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6645-6649, Vancouver, BC, Canada, (2013, May).
• [37] Fernández, S., Graves, A. and Schmidhuber, J. An application of recurrent neural networks to discriminative keyword spotting. In Proceedings, Artificial Neural Networks-ICANN, pp. 220-229, Berlin, Heidelberg, (2007, September).
• [38] Samui, S., Chakrabarti, I. and Ghosh, S.K. Tensor-train long short-term memory for monaural speech enhancement. arXiv preprint arXiv:1812.10095, (2018).
• [39] Raj, A., Varma, T. and Banerjee, S. LSTM-based image and video classification: An exploration. Multimedia Tools and Applications, 77, 17097-17116, (2018).
• [40] Chatterjee, A., Bhowmick, H. and Sen, J. Stock price prediction using time series, econometric, machine learning, and deep learning models. In Proceedings, 2021 IEEE Mysore Sub Section International Conference (MysuruCon), pp. 289-296, Hassan, India, (2021, October).
• [41] Mehtab, S., Sen, J. and Dutta, A. Stock price prediction using machine learning and LSTM-based deep learning models. In Proceedings, Machine Learning and Metaheuristics Algorithms, and Applications, pp. 88-106, Singapore, (2021).
• [42] Nikou, M., Mansourfar, G. and Bagherzadeh, J. Stock price prediction using DEEP learning algorithm and its comparison with machine learning algorithms. Intelligent Systems in Accounting, Finance and Management, 26(4), 164-174, (2019).
• [43] Ozan, M. Derin Öğrenme Teknikleri Kullanılarak Borsadaki Hisse Değerlerinin Tahmin Edilmesi. Master’s Thesis, Department of Electrical and Electronics Engineering, Erciyes University, (2021).
• [44] Sheth, D. and Shah, M. Predicting stock market using machine learning: best and accurate way to know future stock prices. International Journal of System Assurance Engineering and Management, 14, 1-18, (2023).
• [45] Saracık, Ö. Derin Öğrenme Teknikleri Kullanılarak Hisse Senedi Fiyatlarının Tahmin Edilmesi: BIST’te Bir Uygulama. Master’s Thesis, Manisa Celal Bayar University, (2023).
• [46] Nabipour, M., Nayyeri, P., Jabani, H., Shahab, S. and Mosavi, A. Predicting stock market trends using machine learning and deep learning algorithms via continuous and binary data; a comparative analysis. IEEE Access, 8, 150199-150212, (2020).
• [47] Demirel, U., Çam, H. and Ünlü, R. Predicting stock prices using machine learning methods and deep learning algorithms: The sample of the Istanbul Stock Exchange. Gazi University Journal of Science, 34(1), 63-82, (2021).
• [48] Akita, R., Yoshihara, A., Matsubara, T. and Uehara, K. Deep learning for stock prediction using numerical and textual information. In Proceedings, 2016 IEEE/ACIS 15th International Conference on Computer and Information Science (ICIS), pp. 1-6, Okayama, Japan, (2016, June).
• [49] Yan, H. and Ouyang, H. Financial time series prediction based on deep learning. Wireless Personal Communications, 102, 683-700, (2018).
• [50] Fischer, T. and Krauss, C. Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654-669, (2018).
• [51] Van Houdt, G., Mosquera, C. and Nápoles, G. A review on the long short-term memory model. Artificial Intelligence Review, 53, 5929-5955, (2020).
• [52] Bao, W., Yue, J. and Rao, Y. A deep learning framework for financial time series using stacked autoencoders and long short-term memory. Neurocomputing, 356, 74-85, (2017).
• [53] Zhong, X. and Enke, D. Predicting the daily return direction of the stock market using hybrid machine learning algorithms. Financial Innovation, 5, 24, (2019).
• [54] Hochreiter, S. and Schmidhuber, J. Long short-term memory. Neural Computation, 9(8), 1735- 1780, (1997).
• [55] Gers, F.A., Schmidhuber, J. and Cummins, F. Learning to forget: Continual prediction with LSTM. Neural Computation, 12(10), 2451-2471, (2000).
• [56] Patel, J., Shah, S., Thakkar, P. and Kotecha, K. Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques. Expert Systems with Applications, 42(1), 259-268, (2015).
• [57] Breiman, L. Random forests. Machine Learning, 45, 5-32, (2001).
• [58] Alhnaity, B. and Abbod, M. A new hybrid financial time series prediction model. Engineering Applications of Artificial Intelligence, 95, 103873, (2020).
• [59] Box, G.E., Jenkins, G.M., Reinsel, G.C. and Ljung, G.M. Time Series Analysis: Forecasting and Control. John Wiley & Sons, (2015).
• [60] Hyndman, R.J. and Athanasopoulos, G. Forecasting: Principles and Practice. OTexts: Melbourne, (2018).
• [61] Bergmeir, C., Hyndman, R.J. and Koo, B. A note on the validity of cross-validation for evaluating autoregressive time series prediction. Computational Statistics & Data Analysis, 120, 70-83, (2018).
• [62] Siami-Namini, S., Tavakoli, N. and Namin, A.S. A comparison of ARIMA and LSTM in forecasting time series. In Proceedings, 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 1394-1401, Orlando, FL, USA, (2018, December).
• [63] Biau, G. and Scornet, E. A random forest-guided tour. Test, 25, 197-227, (2016).
• [64] NYSE, Trading & Data Better Trading, (2024). https://www.nyse.com/trading-data#: ~:text=Meeting%20the%20volatility%20challenge,the%20opening%20and%20closing% 20auctions
• [65] Lu, Z. Comparison of stock price prediction models for linear models, random forest and LSTM. In Proceedings, 4th International Conference on Signal Processing and Machine Learning, pp. 226-233, (2024).
• [66] Omar, A.B., Huang, S., Salameh, A.A., Khurram, H. and Fareed, M. Stock market forecasting using the random forest and deep neural network models before and during the COVID-19 period. Frontiers in Environmental Science, 10, 917047, (2022).