Bellek Tabanlı LSTM ve GRU Makine Öğrenmesi Algoritmaları Kullanarak BIST100 Endeks Tahmini

Öz

Makine öğrenmesi tabanlı tahmin yaklaşımlarının finansal piyasalarda geliştirilmesi, hızlı ve hassas karar alma, karmaşıklıkla başa çıkma, risk yönetimi, algoritmik ticaret ve duygusal etkilerin azaltılması gibi avantajlar sağlar. Bu yaklaşımlar, sürekli öğrenme ve adaptasyon yetenekleriyle finansal başarı için rekabet avantajı oluşturabilir. Bu makale çalışmasında, Borsa İstanbul (BIST) 100 endeks tahmini için bellek tabanlı makine öğrenmesi modellerine dayalı bir yaklaşım sunulmuştur. Bu amaçla, ardışık veri değerlendirmesinde popüler olan uzun kısa-süreli bellek (LSTM) ve geçitli tekrarlayan birim (GRU) mimarileri kullanılmıştır. Elde edilen model çıktılarına göre bu modellerin, eğitim ve doğrulama aşamalarında düşük kayıplar gösterdiği ve BIST100 endeksinin genel eğilimlerini başarıyla takip ettiği gözlemlenmiştir. Ancak, modeller piyasa dalgalanmaları ve ani değişimlerde gerçek değerlerden sapmalar göstermiş, bu da belirsizlikleri ve genelleme kapasitelerinin sınırlarını ortaya koymuştur. Geleceğe yönelik tahminler, eğitim veri setindeki desenlere dayanarak yapılmış ancak zamanla artan belirsizlik göstermiştir. Çalışma, makine öğrenmesi algoritmalarının finans verileri üzerindeki kullanım alanı konusunda önemli bilgiler sağlayacak potansiyele sahiptir.

Anahtar Kelimeler

• Makine öğrenmesi
• LSTM
• GRU
• BIST100
• finans tahmin.

Predicting the BIST100 Index Using Memory-Based LSTM and GRU Machine Learning Algorithms

Öz

The development of machine learning-based forecasting approaches in financial markets offers advantages such as rapid and precise decision-making, complexity management, risk mitigation, algorithmic trading, and reduction of emotional biases. These methods can create a competitive edge for financial success through their continuous learning and adaptation capabilities. This article presents a memory-based machine learning approach for predicting the Borsa Istanbul (BIST) 100 index, utilizing popular architectures like Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) for sequential data analysis. The models demonstrated low losses in training and validation phases and successfully followed the general trends of the BIST 100 index. However, they showed deviations from actual values during market volatility, highlighting uncertainties and the limits of their generalization abilities. Predictions were based on patterns in the training dataset but indicated increasing uncertainty over time. This study has the potential to provide significant insights into the application of machine learning algorithms on financial data.

Anahtar Kelimeler

• Machine learning
• LSTM
• GRU
• BIST100
• financial forecasting.

Kaynakça

1. Goodfellow I, Bengio Y, Courville A. Deep learning. MIT Press, 2016.
2. Sze V, Chen YH, Yang TJ, Emer JS. Efficient processing of deep neural networks: A tutorial and survey. Proc IEEE, 2017; 105(12): 2295-2329.
3. Ozturk T, Talo M, Yildirim EA, Baloglu UB, Yildirim O, Acharya UR. Automated detection of COVID-19 cases using deep neural networks with X-ray images. Comput Biol Med, 2020; 121: 103792.
4. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proc IEEE Conf Comput Vis Pattern Recognit, 2016; pp. 770-778.
5. Ren S, He K, Girshick R, Sun J. Faster r-cnn: Towards real-time object detection with region proposal networks. Adv Neural Inf Process Syst, 2015; 28.
6. Huang J, Chai J, Cho S. Deep learning in finance and banking: A literature review and classification. Front Bus Res China, 2020; 14(1): 1-24.
7. Singh V, Chen SS, Singhania M, Nanavati B, Gupta A. How are reinforcement learning and deep learning algorithms used for big data based decision making in financial industries–A review and research agenda. Int J Inf Manag Data Insights, 2022; 2(2): 100094.
8. Ahmed S, Alshater MM, El Ammari A, Hammami H. Artificial intelligence and machine learning in finance: A bibliometric review. Res Int Bus Finance, 2022; 61: 101646.

9. Gamboa JCB. Deep learning for time-series analysis, 2017; arXiv preprint arXiv:1701.01887.
10. Sutskever I, Vinyals O, Le QV. Sequence to sequence learning with neural networks. Adv Neural Inf Process Syst, 2014; 27.
11. Amodei D, Ananthanarayanan S, Anubhai R, Bai J, Battenberg E, Case C, Zhu Z. Deep speech 2: End-to-end speech recognition in English and Mandarin. In: Int Conf Mach Learn, 2016; pp. 173-182. PMLR.
12. Cao J, Li Z, Li J. Financial time series forecasting model based on CEEMDAN and LSTM. Physica A, 2019; 519: 127-139.
13. Siami-Namini S, Namin AS. Forecasting economics and financial time series: ARIMA vs. LSTM, 2018; arXiv preprint arXiv:1803.06386.
14. Pirani M, Thakkar P, Jivrani P, Bohara MH, Garg D. A comparative analysis of ARIMA, GRU, LSTM and BiLSTM on financial time series forecasting. In: 2022 IEEE Int Conf Distributed Comput Electr Circuits Electron (ICDCECE), 2022; pp. 1-6. IEEE.
15. Lindemann B, Maschler B, Sahlab N, Weyrich M. A survey on anomaly detection for technical systems using LSTM networks. Comput Ind, 2021; 131: 103498.
16. Chung J, Gulcehre C, Cho K, Bengio Y. Empirical evaluation of gated recurrent neural networks on sequence modeling. 2014; arXiv preprint arXiv:1412.3555.
17. Dey R, Salem FM. Gate-variants of gated recurrent unit (GRU) neural networks. In: 2017 IEEE 60th Int Midwest Symp Circuits Syst (MWSCAS), 2017; pp. 1597-1600. IEEE.
18. Chung J, Gulcehre C, Cho K, Bengio Y. Empirical evaluation of gated recurrent neural networks on sequence modeling. 2014; arXiv preprint arXiv:1412.3555.
19. Yu Y, Si X, Hu C, Zhang J. A review of recurrent neural networks: LSTM cells and network architectures. Neural Comput, 2019; 31(7): 1235-1270.
20. Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput, 1997; 9(8): 1735-1780.
21. Cho K, Van Merriënboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y. Learning phrase representations using RNN encoder-decoder for statistical machine translation, 2014; arXiv preprint arXiv:1406.1078.
22. Merity S, Keskar NS, Socher R. Regularizing and optimizing LSTM language models, 2017; arXiv preprint arXiv:1708.02182.
23. Graves A, Jaitly N, Mohamed AR. Hybrid speech recognition with deep bidirectional LSTM. In: 2013 IEEE Workshop Autom Speech Recognit Understanding, 2013; pp. 273-278. IEEE.
24. Carbune V, Gonnet P, Deselaers T, Rowley HA, Daryin A, Calvo M, Gervais P. Fast multi-language LSTM-based online handwriting recognition. Int J Document Anal Recognit (IJDAR), 2020; 23(2): 89-102.
25. Wikipedia. (2023, Mayıs 5). Borsa İstanbul. https://tr.wikipedia.org/wiki/Borsa_İstanbul