Finansal Zaman Serilerini Tahminlemede Kullanılan Yöntemlere Genel Bir Bakış

Öz

Geçmişte olduğu gibi günümüzde de yatırımcılar için finansal verilerin trendinin tahmin edilebilmesi ve bu bilgi kullanılarak bir finansal strateji oluşturulması oldukça önemlidir. Fakat günümüzde hızlı internet bağlantıları ile finansal verilerin hızlı ulaşması ve bilişim ve bulut sistemlerindeki gelişmeler, finansal tahminlemek için yapay zekâ algoritmalarının kullanılması bu alanda rekabeti artırmaktadır. Fintech içinde portföy yönetimi gibi alanlarda yapay zekâ uygulamalarının kullanım payı gittikçe artmaktadır. Bu çalışmanın amacı finansal zaman serisi verileri tahminlemek için yapılan daha önceki akademik çalışmaları derlemek, zaman serilerinin tahmin etmek için kullanılan yapay zekâ algoritmalarını açıklamak ve tahmin edilen bazı finansal veri tiplerini ve bağımlılıklarını irdelemektir. Çalışma sonunda incelenen makalelerde kullanılan tekniklerin yeterlilikleri ve hangi veri tipi için hangi metodun daha başarılı sonuçlar verebileceği gibi çıkarımlar yapılmıştır.

Anahtar Kelimeler

• Finansal Zaman Serisi
• Öngörü
• Yapay Zekâ
• Veri Madenciliği

A General Review of the Methods Used Financial Time Series Forecasting

Öz

As in the past, it is very important for investors to be able to predict the trend of financial data and to create a financial strategy using this information. However, nowadays, rapid access to financial data with fast Internet connections, developments in informatics, and cloud systems, the use of artificial intelligence algorithms for financial forecasting increase competition in this field. The share of artificial intelligence applications in areas such as portfolio management in Fintech is increasing. The aim of this study is to compile previous academic studies to predict financial time series data, to explain artificial intelligence algorithms used to predict time series, and to examine some predicted financial data types and their dependencies. At the end of the study, inferences were made such as the adequacy of the techniques used in the articles examined and which method could yield more successful results for which data type.

Anahtar Kelimeler

• Financial Time Series
• Forecasting
• Artificial Intelligent
• Data Mining

Kaynakça

1. ‘Fundamental Analysis’ (2012) in The Sector Strategist. John Wiley & Sons, Ltd, 163–184. doi:10.1002/9781119205333.ch9.
2. 'Technical Analysis: Welcome To Technical Analysis’ (2012) in Invest in Penny Stocks. John Wiley & Sons, Ltd,
3. Ponsi (ed.) (2016) ‘The Dow Theory’, in Technical Analysis and Chart Interpretations. Hoboken, NJ, USA: John Wiley & Sons, Inc., 19–26. doi:10.1002/9781119204800.ch4.
4. ‘The Dow Theory’ (2016) in Technical Analysis and Chart Interpretations. John Wiley & Sons, Ltd, 19–26. doi:10.1002/9781119204800.ch4.
5. Bustos, O. & Pomares-Quimbaya, A. (2020) ‘Stock market movement forecast: A Systematic review’, Expert Systems with Applications, 156, 113464–113464. doi:10.1016/j.eswa. 2020.113464.
6. Puschmann, T. (2017) ‘Fintech’, Business & Information Systems Engineering, 59(1), 69–76. doi:10.1007/s12599-017-0464-6.
7. Oleksiuk, A. (2019) ‘Machine Learning Use Cases in Banking and Finance’, Intellias [Preprint]. Available at: https://intellias.com/5-use-cases-of-machine-learning-in-fintech-and-banking/.
8. Ltd, F.M.I.G. and C.P. (2022) AI in Fintech Market to Reach US$ 54 Billion, Globally, by 2032 at 16.5% CAGR: Future Market Insights, Inc., GlobeNewswire News Room. Available at: https://www.globenewswire.com/news-release/2022/06/10/2460623/0/en/AI-in-Fintech-Market-to-Reach-US-54-Billion-Globally-by-2032-at-16-5-CAGR-Future-Market-Insights-Inc.html (Accessed: 12 June 2022).

9. Harvey, A. (2016) ‘Trend Analysis’, in Wiley StatsRef: Statistics Reference Online. John Wiley & Sons, Ltd, 1–21. doi:10.1002/9781118445112.stat07817.pub2.
10. Gulve, A. (2020) ‘Everything about Components of Time Series: Part-1’, Medium, 10 April. Available at: https://aishwaryagulve97.medium.com/everything-about-components-of-time-series-part-1-7476fb521477 (Accessed: 7 January 2022).
11. Fig. 3 Time series graphs with random, seasonal and trend components in... (no date) ResearchGate. Available at: https://www.researchgate.net/figure/Time-series-graphs-with-random-seasonal-and-trend-components-in-cluster-1_fig1_268153169 (Accessed: 19 January 2022).
12. Selvin, S. et al. (2017) ‘Stock price prediction using LSTM, RNN and CNN-sliding window model’, 2017 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2017, 2017-January, 1643–1647. doi:10.1109/ICACCI.2017.8126078.
13. Stocks | Investor.gov (no date). Available at: https://www.investor.gov/introduction-investing/investing-basics/investment-products/stocks (Accessed: 13 June 2022).
14. Marquit, M. (2021a) Investing Basics: What Are Dividends?, Forbes Advisor. Available at: https://www.forbes.com/advisor/investing/what-is-dividend/ (Accessed: 13 June 2022).
15. Ögel, S. & Fındık, M. (2020) ‘Farkli Kitalarda Yer Alan Borsa Endekslerinin Vix(Korku) Endeksi İle İlişkisi’, Kocatepeiibf Journal, 22(1), 127–140.
16. Schich, S. (2004) ‘European stock market dependencies when price changes are unusually large’, Applied Financial Economics, 14(3), 165–177. doi:10.1080/0960310042000187360.
17. Sezer, O.B., Gudelek, M.U. and Ozbayoglu, A.M. (2020) ‘Financial time series forecasting with deep learning: A systematic literature review: 2005–2019’, Applied Soft Computing Journal, 90, 106181–106181. doi:10.1016/j.asoc.2020.106181.
18. Kumar, R. (2014) ‘Chapter 5 - Stock Markets, Derivatives Markets, and Foreign Exchange Markets’, in Kumar, R. (ed.) Strategies of Banks and Other Financial Institutions. San Diego: Academic Press, 125–164. doi:10.1016/B978-0-12-416997-5.00005-1.
19. ‘What Is A Stock Market Index? – Forbes Advisor’ (no date). Available at: https://www.forbes.com/advisor/investing/stock-market-index/ (Accessed: 13 June 2022).
20. Tretina, K. (2021) Investing Basics: What Is A Market Index?, Forbes Advisor. Available at: https://www.forbes.com/advisor/investing/stock-market-index/ (Accessed: 13 June 2022).
21. Marquit, M. (2021b) What Is The VIX Volatility Index?, Forbes Advisor. Available at: https://www.forbes.com/advisor/investing/vix-volatility-index/ (Accessed: 13 June 2022).
22. ARIMA Models - Demand‐Driven Forecasting - Wiley Online Library (no date). Available at: https://onlinelibrary.wiley.com/doi/10.1002/9781118691861.ch7 (Accessed: 13 June 2022).
23. Miller, D.M. & Williams, D. (2003) ‘Shrinkage estimators of time series seasonal factors and their effect on forecasting accuracy’, International Journal of Forecasting, 19(4), 669–684. doi:10.1016/S0169-2070(02)00077-8.
24. Hyndman, R.J., Hyndman, & Rob (2004) ‘The interaction between trend and seasonality’, International Journal of Forecasting, 20(4), 561–563.
25. Time Series: Understanding Changes Over Time - Science Direct (no date). Available at: https://www.sciencedirect.com/science/article/pii/B9780128200254000142 (Accessed: 13 June 2022).
26. Newbold, P. & Bos, T. (1989) ‘On exponential smoothing and the assumption of deterministic trend plus white noise data-generating models’, International Journal of Forecasting, 5(4), 523–527. doi:10.1016/0169-2070(89)90007-1.
27. Karakaş, E. (2019) ‘Çocuk Yoğun Bakım Ünitesine Olan Talebin Zaman Serisi Yöntemleri ile Tahmin Edilmesi’, European Journal of Science and Technology, 454–462. doi:10.31590/ejosat.624407.
28. Johannet, A. (2010) ‘Artificial Neural Network Models’, in Mathematical Models. John Wiley & Sons, Ltd, 419–443. doi:10.1002/9781118557853.ch14.
29. Yildiran, A. & Kandemı̇r, S.Y. (2018) ‘Yağış Miktarının Yapay Sinir Ağları ile Tahmini’, Bilecik Şeyh Edebali Üniversitesi Fen Bilimleri Dergisi, 5(2), 97–104.
30. Dayhoff, J.E. & Deleo, J.M. (1999) ‘Conference on Prognostic Factors and Staging in Cancer Management: Contributions of Artificial Neural Networks and Other Statistical Methods Artificial Neural Networks Opening the Black Box’. doi:10.1002/1097-0142(20010415)91:8.
31. ‘Multilayer Neural Networks and Backpropagation’ (2016) in Fundamentals of Computational Intelligence. John Wiley & Sons, Ltd, 35–60. doi:10.1002/9781119214403.ch3.
32. Broussard, R. et al. (2008) ‘An artificial neural network based matching metric for iris identification’, in, 68120. doi:10.1117/12.766725.
33. Wythoff, B.J. (1993) ‘Backpropagation neural networks: A tutorial’, Chemometrics and Intelligent Laboratory Systems, 18(2), 115–155. doi:10.1016/0169-7439(93)80052-J.
34. Yazan, E. and Talu, M.F. (2022) ‘Yönsel Türev Tabanlı Yakınsama Yaklaşımlarının Karşılaştırmalı Analizi’, 10.
35. Kızrak, A. (2020) ‘Comparison of Activation Functions for Deep Neural Networks’, Medium [Preprint]. Available at: https://towardsdatascience.com/comparison-of-activation-functions-for-deep-neural-networks-706ac4284c8a.
36. Rhanoui, M. et al. (2019) ‘Forecasting Financial Budget Time Series: ARIMA Random Walk vs LSTM Neural Network’, IAES International Journal of Artificial Intelligence (IJ-AI), 8, 317–317. doi:10.11591/ijai.v8.i4.pp317-327.
37. ‘Recurrent Neural Net’ (2019) nerdcoder, 3 February. Available at: https://nerdthecoder.wordpress.com/2019/02/03/recurrent-neural-net/ (Accessed: 8 December 2021).
38. Hughes, D. & Correll, N. (2016) ‘Distributed Machine Learning in Materials that Couple Sensing, Actuation, Computation and Communication’.
39. (PDF) Deep Learning for Daily Peak Load Forecasting-A Novel Gated Recurrent Neural Network Combining Dynamic Time Warping (no date). Available at: https://www.researchgate.net/publication/330723201_Deep_Learning_for_Daily_Peak_Load_Forecasting-A_Novel_Gated_Recurrent_Neural_Network_Combining_Dynamic_Time_Warping (Accessed: 10 December 2021).
40. CS 230 - Recurrent Neural Networks Cheatsheet (no date). Available at: https://stanford.edu/~shervine/teaching/cs-230/cheatsheet-recurrent-neural-networks (Accessed: 13 June 2022).
41. Van Houdt, G., Mosquera, C. & Nápoles, G. (2020) ‘A Review on the Long Short-Term Memory Model’, Artificial Intelligence Review, 53. doi:10.1007/s10462-020-09838-1.
42. Hochreiter, S. & Schmidhuber, J. (1997) ‘Long Short-Term Memory’, Neural Computation, 9(8), 1735–1780. doi:10.1162/neco.1997.9.8.1735.
43. Fang, H. et al. (2020) ‘A LSTM Algorithm Estimating Pseudo Measurements for Aiding INS during GNSS Signal Outages’, Remote Sensing, 12, p. 256. doi:10.3390/rs12020256.
44. Savaş, S. et al. (2022) ‘Comparison of Deep Learning Models in Carotid Artery Intima-Media Thickness Ultrasound Images: CAIMTUSNet’, Bilişim Teknolojileri Dergisi, 15(1), 1–12. doi:10.17671/gazibtd.804617.
45. Firildak, K. & Talu, M.F. (no date) ‘Evrişimsel Sinir Ağlarında Kullanılan Transfer Öğrenme Yaklaşımlarının İncelenmesi’, 8.
46. Convolutional neural networks for time series forecasting | Python for Finance Cookbook (no date). Available at: https://subscription.packtpub.com/book/data/9781789618518/10/ch10lvl1sec63/convolutional-neural-networks-for-time-series-forecasting (Accessed: 19 January 2022).
47. Alfarzaeai, M.S. et al. (2020) ‘Coal/Gangue Recognition Using Convolutional Neural Networks and Thermal Images’, IEEE Access, 8, pp. 76780–76789. doi:10.1109/ACCESS.2020.2990200.
48. Bhatnagar, S., Ghosal, D. & Kolekar, M.H. (2017) ‘Classification of fashion article images using convolutional neural networks’, in 2017 Fourth International Conference on Image Information Processing (ICIIP). 2017 Fourth International Conference on Image Information Processing (ICIIP), 1–6. doi:10.1109/ICIIP.2017.8313740.
49. Savaş, S. (2022) ‘Detecting the Stages of Alzheimer’s Disease with Pre-trained Deep Learning Architectures’, Arabian Journal for Science and Engineering, 47(2), 2201–2218. doi:10.1007/s13369-021-06131-3.
50. Iqbal, S. et al. (2018) ‘Brain tumor segmentation in multi-spectral MRI using convolutional neural networks (CNN)’, Microscopy Research and Technique, 81(4), 419–427. doi:10.1002/jemt.22994.
51. Ibrahim, A., Kashef, R. and Corrigan, L. (2021) ‘Predicting market movement direction for bitcoin: A comparison of time series modeling methods’, Computers & Electrical Engineering, 89, 106905. doi:10.1016/j.compeleceng.2020.106905.
52. Prophet: forecasting at scale - Meta Research (no date) Meta Research. Available at: https://research.facebook.com/blog/2017/02/prophet-forecasting-at-scale/ (Accessed: 21 December 2021).
53. Mondal, P., Shit, L. & Goswami, S. (2014) ‘Study of Effectiveness of Time Series Modeling (Arima) in Forecasting Stock Prices’, International Journal of Computer Science, Engineering and Applications, 4(2), 13–29. doi:10.5121/ijcsea.2014.4202.
54. Yamak, P.T., Yujian, L. & Gadosey, P.K. (2019) ‘A Comparison between ARIMA, LSTM, and GRU for Time Series Forecasting’, in Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence. New York, NY, USA: Association for Computing Machinery (ACAI 2019), 49–55. doi:10.1145/3377713.3377722.
55. Lai, K.K. et al. (2006) ‘Hybridizing Exponential Smoothing and Neural Network for Financial Time Series Predication’, in Alexandrov, V.N. et al. (eds) Computational Science – ICCS 2006. Berlin, Heidelberg: Springer Berlin Heidelberg (Lecture Notes in Computer Science), 493–500. doi:10.1007/11758549_69.
56. Khashei, M. & Bijari, M. (2010) ‘An artificial neural network (p, d, q) model for timeseries forecasting’, Expert Syst. Appl., 37, 479–489. doi:10.1016/j.eswa.2009.05.044.
57. Zhang, G.P. (2003) ‘Time series forecasting using a hybrid ARIMA and neural network model’, Neurocomputing, 50, 159–175. doi:10.1016/S0925-2312(01)00702-0.
58. Babu, C.N. & Reddy, B.E. (2014) ‘A moving-average filter based hybrid ARIMA–ANN model for forecasting time series data’, Applied Soft Computing, 23, 27–38. doi:10.1016/j.asoc.2014.05.028.
59. Adhikari, R. & Agrawal, R.K. (2014) ‘A combination of artificial neural network and random walk models for financial time series forecasting’, Neural Computing and Applications, 24(6), 1441–1449. doi:10.1007/s00521-013-1386-y.
60. Akbar & Sima, S.N. (2018) ‘Forecasting Economics and Financial Time Series: ARIMA vs. LSTM’, arXiv:1803.06386 [cs, q-fin, stat] [Preprint]. Available at: http://arxiv.org/abs/1803.06386 (Accessed: 9 December 2021).
61. Sagheer, A. & Kotb, M. (2019) ‘Time series forecasting of petroleum production using deep LSTM recurrent networks’, Neurocomputing, 323, 203–213. doi:10.1016/j.neucom. 2018.09.082.
62. Fang, W.-X. et al. (2019) ‘Combine Facebook Prophet and LSTM with BPNN Forecasting financial markets: the Morgan Taiwan Index’, in 2019 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS). 2019 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), 1–2. doi:10.1109/ISPACS48206.2019.8986377.
63. Livieris, I.E., Pintelas, E. & Pintelas, P. (2020) ‘A CNN–LSTM model for gold price time-series forecasting’, Neural Computing and Applications, 32(23), 17351–17360. doi:10.1007/s00521-020-04867-x.
64. Li, J. (2021) ‘Research on Market Stock Index Prediction Based on Network Security and Deep Learning’, Security and Communication Networks. Edited by C.-H. Chen, 2021, 1–8. doi:10.1155/2021/5522375.
65. Yusof, U.K. et al. (2021) ‘Financial Time Series Forecasting Using Prophet’, in Saeed, F., Mohammed, F., and Al-Nahari, A. (eds) Innovative Systems for Intelligent Health Informatics. Cham: Springer International Publishing (Lecture Notes on Data Engineering and Communications Technologies), 485–495. doi:10.1007/978-3-030-70713-2_45.