Abstract
Müşterilere yapılan anlık kur teklifleri, bankacılık sektöründeki en kritik konular arasında yer almaktadır. Verilen tekliflerin uygun seviyede olması hem banka hem de müşteri açısından oldukça önemlidir. Bu çalışmada, müşteriye verilen kur tekliflerinin tahmini için yaklaşık 8 aylık veri kullanılmış ve tahmin modelleri tasarlanmıştır. Toplamda 18 farklı kur üzerinden çalışma yürütülmüştür. Çalışmada bağımlı değişkenler müşteri segmenti, anlık kur değeri, gün bilgisi, saat bilgisi ve volatilite değeri olarak belirlenmiştir. Bağımsız değişken ise kur marjıdır. Eğitimler günlük verilerle ve Rastgele Ağaçlar (RF), Gradyan Arttırma Makinesi (GBM), Yapay Sinir Ağları (ANN), Derin Sinir Ağları (DNN), Evrişimli Sinir Ağları (CNN) ve Elman Sinir Ağı algoritmaları kullanılarak gerçekleştirilmiştir. Algoritmaların hiper-parametrelerini bulmak için rastgele arama algoritması kullanılmış ve model eğitimlerinin sonuçları karşılaştırılarak en düşük hata değerine sahip modeller tahmin aşamasında kullanılmak üzere seçilmiştir. Başarım ölçümü için Ortalama Kare Hata (MSE) ve Ortalama Mutlak Hata (MAE) hata fonksiyonları kullanılmıştır. Üç farklı model üzerinden gerçekleştirilen eğitimlere göre yapay sinir ağları ve evrişimli sinir ağları algoritmalarının diğer algoritmalara göre daha iyi sonuçlar verdiği gözlemlenmiştir. 18 kur için tahmin süresi yaklaşık 3s'dir.
Keywords
Marj Tahmini Yapay Sinir Ağları Tahmin Modelleri Derin Sinir Ağı Evrişimli Sinir Ağı Elman Sinir Ağı Karar Ağaçları
Supporting Institution
TÜBİTAK
Project Number
7200206
References
- Niyazi TELÇEKEN & Murat KIYILAR & Eyüp KADIOĞLU, “Volatilite Endeksleri: Gelişimi, Türleri, Uygulamaları ve Trvıx Önerisi”, Ekonomi, Politika & Finans Araştırmaları Dergisi, 2019, 4(2): 204-228
- Özkan ŞAHİN & Mehmet Akif ÖNCÜ “Volatilite Alanında Yapılmış Lisansüstü Tezelere Yönelik Bir İçerik Analizi” Muhasebe ve Finansman Dergisi
- Breiman L., Cutler A., Random forest, http://www.stat. berkeley.edu/~breiman/RandomForests/cc_home.html, (2005)
- Alexey Natekin, Alois Knoll, Gradient boosting machines, a tutorial, Neurorobot., 04 December 2013
- Silva F M and Almeida L B 1990, Acceleration techniques for the backpropagation algorithm Neural Networks ed L B Almeida andCJWellekens (Berlin: Springer)
- Ayşe ARI,Murat Erşen BERBERLER, Yapay Sinir Ağları ile Tahmin ve Sınıflandırma Problemlerinin Çözümü İçin Arayüz Tasarımı, Acta Infologıca – 2017
- Y. LeCun et al., "Backpropagation applied to handwritten zip code recognition," Neural computation, vol. 1, no. 4, pp. 541-551, 1989.
- Stephane Lathuili ´ ere, Pablo Mesejo, Xavier Alameda-Pineda, ` Member IEEE, and Radu Horaud “A Comprehensive Analysis of Deep Regression “ https://arxiv.org/abs/1803.08450, v3 [cs.CV] 24 Sep 2020
- Antoni Wysocki and Maciej Ławryńczuk, Two- and Three-Layer Recurrent Elman Neural Networks as Models of Dynamic Processes, February 2016, Challenges in Automation, Robotics and Measurement Techniques (pp.165-175)
- Ercan Öztemel, Yapay Sinir Aglari Paperback – January 1, 2003
- Vidushi Sharma, Sachin Rai, Anurag DevA Comprehensive Study of Artificial Neural Networks, International Journal of Advanced Research in Computer Science and Software Engineering, Volume 2, Issue 10, October 2012, ISSN: 2277 128X
- I. Goodfellow, Y. Bengio, and A. Courville, Deep learning (Adaptive computation and machine learning). Cambridge, Massachusetts: The MIT Press, pp. xxii, 775 pages, 2016.
- C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, "Rethinking the inception architecture for computer vision," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818-2826, 2016.
- V. Dumoulin and F. Visin, "A guide to convolution arithmetic for deep learning," CoRR, vol. abs/1603.07285, 2016.
- Evrişimli Sinir Ağları el kitabı, CS 230 - Derin Öğrenme https://stanford.edu/~shervine/l/tr/teaching/cs-230/cheatsheet-convolutional-neural-networks
- Ren, G., Cao, Y., Wen, S., Huang, T., & Zeng, Z. (2018). A modified Elman neural network with a new learning rate scheme. Neurocomputing, 286, 11–18. doi: 10.1016/j.neucom.2018.01.046
- Wysocki, A., & Ławryńczuk, M. (2016). Two- and Three-Layer Recurrent Elman Neural Networks as Models of Dynamic Processes. Advances in Intelligent Systems and Computing, 165–175. doi:10.1007/978-3-319-29357-8_15
- Shuaiqiang Liu, Cornelis W. Oosterlee and Sander M. Bohte Pricing Options and Computing Implied Volatilities using Neural Networks, Modern Numerical Techniques and Machine-Learning in Pricing and Risk Management, https://doi.org/10.3390/risks7010016, 2019
- Chuong Luong and Nikolai Dokuchaev, Forecasting of Realised Volatility with the Random Forests Algorithm, Journal of Risk and Financial Management, 2018
- Winky K.O. Ho, Bo-Sin Tang Predicting property prices with machine learning algorithms, Journal of Property Research, 2020
- Wenjie Lu, Jiazheng Li, Jingyang Wang, Lele Qin, A CNN-BiLSTM-AM method for stock price prediction, Neural Computing and Applications, 2020
- Bo Liu , Qilin Wu, and Qian Cao, An Improved Elman Network for Stock Price Prediction Service, Volume 2020, Article ID 8824430, 9 pages
- Fang Wang, Sai Tang and Menggang Li, Advantages of Combining Factorization Machine with Elman Neural Network for Volatility Forecasting of Stock Market, Volume 2021 |Article ID 6641298
- Simon S. Du, Jason D. Lee, Haochuan Li, Liwei Wang, Xiyu Zhai ¸Gradient Descent Finds Global Minima of Deep Neural Networks, arXiv:1811.03804, 2019
- Yuanzhi Li, Yingyu Liang, Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data, arXiv:1808.01204, 2018
Abstract
Project Number
7200206
References
- Niyazi TELÇEKEN & Murat KIYILAR & Eyüp KADIOĞLU, “Volatilite Endeksleri: Gelişimi, Türleri, Uygulamaları ve Trvıx Önerisi”, Ekonomi, Politika & Finans Araştırmaları Dergisi, 2019, 4(2): 204-228
- Özkan ŞAHİN & Mehmet Akif ÖNCÜ “Volatilite Alanında Yapılmış Lisansüstü Tezelere Yönelik Bir İçerik Analizi” Muhasebe ve Finansman Dergisi
- Breiman L., Cutler A., Random forest, http://www.stat. berkeley.edu/~breiman/RandomForests/cc_home.html, (2005)
- Alexey Natekin, Alois Knoll, Gradient boosting machines, a tutorial, Neurorobot., 04 December 2013
- Silva F M and Almeida L B 1990, Acceleration techniques for the backpropagation algorithm Neural Networks ed L B Almeida andCJWellekens (Berlin: Springer)
- Ayşe ARI,Murat Erşen BERBERLER, Yapay Sinir Ağları ile Tahmin ve Sınıflandırma Problemlerinin Çözümü İçin Arayüz Tasarımı, Acta Infologıca – 2017
- Y. LeCun et al., "Backpropagation applied to handwritten zip code recognition," Neural computation, vol. 1, no. 4, pp. 541-551, 1989.
- Stephane Lathuili ´ ere, Pablo Mesejo, Xavier Alameda-Pineda, ` Member IEEE, and Radu Horaud “A Comprehensive Analysis of Deep Regression “ https://arxiv.org/abs/1803.08450, v3 [cs.CV] 24 Sep 2020
- Antoni Wysocki and Maciej Ławryńczuk, Two- and Three-Layer Recurrent Elman Neural Networks as Models of Dynamic Processes, February 2016, Challenges in Automation, Robotics and Measurement Techniques (pp.165-175)
- Ercan Öztemel, Yapay Sinir Aglari Paperback – January 1, 2003
- Vidushi Sharma, Sachin Rai, Anurag DevA Comprehensive Study of Artificial Neural Networks, International Journal of Advanced Research in Computer Science and Software Engineering, Volume 2, Issue 10, October 2012, ISSN: 2277 128X
- I. Goodfellow, Y. Bengio, and A. Courville, Deep learning (Adaptive computation and machine learning). Cambridge, Massachusetts: The MIT Press, pp. xxii, 775 pages, 2016.
- C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, "Rethinking the inception architecture for computer vision," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818-2826, 2016.
- V. Dumoulin and F. Visin, "A guide to convolution arithmetic for deep learning," CoRR, vol. abs/1603.07285, 2016.
- Evrişimli Sinir Ağları el kitabı, CS 230 - Derin Öğrenme https://stanford.edu/~shervine/l/tr/teaching/cs-230/cheatsheet-convolutional-neural-networks
- Ren, G., Cao, Y., Wen, S., Huang, T., & Zeng, Z. (2018). A modified Elman neural network with a new learning rate scheme. Neurocomputing, 286, 11–18. doi: 10.1016/j.neucom.2018.01.046
- Wysocki, A., & Ławryńczuk, M. (2016). Two- and Three-Layer Recurrent Elman Neural Networks as Models of Dynamic Processes. Advances in Intelligent Systems and Computing, 165–175. doi:10.1007/978-3-319-29357-8_15
- Shuaiqiang Liu, Cornelis W. Oosterlee and Sander M. Bohte Pricing Options and Computing Implied Volatilities using Neural Networks, Modern Numerical Techniques and Machine-Learning in Pricing and Risk Management, https://doi.org/10.3390/risks7010016, 2019
- Chuong Luong and Nikolai Dokuchaev, Forecasting of Realised Volatility with the Random Forests Algorithm, Journal of Risk and Financial Management, 2018
- Winky K.O. Ho, Bo-Sin Tang Predicting property prices with machine learning algorithms, Journal of Property Research, 2020
- Wenjie Lu, Jiazheng Li, Jingyang Wang, Lele Qin, A CNN-BiLSTM-AM method for stock price prediction, Neural Computing and Applications, 2020
- Bo Liu , Qilin Wu, and Qian Cao, An Improved Elman Network for Stock Price Prediction Service, Volume 2020, Article ID 8824430, 9 pages
- Fang Wang, Sai Tang and Menggang Li, Advantages of Combining Factorization Machine with Elman Neural Network for Volatility Forecasting of Stock Market, Volume 2021 |Article ID 6641298
- Simon S. Du, Jason D. Lee, Haochuan Li, Liwei Wang, Xiyu Zhai ¸Gradient Descent Finds Global Minima of Deep Neural Networks, arXiv:1811.03804, 2019
- Yuanzhi Li, Yingyu Liang, Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data, arXiv:1808.01204, 2018
Details
| Primary Language | Turkish |
|---|---|
| Subjects | Engineering |
| Journal Section | Makaleler(Araştırma) |
| Authors | |
| Project Number | 7200206 |
| Publication Date | December 22, 2021 |
| Published in Issue | Year 2021 Volume: 14 Issue: 2 |
Cite
Article Acceptance
Use user registration/login to upload articles online.
The acceptance process of the articles sent to the journal consists of the following stages:
1. Each submitted article is sent to at least two referees at the first stage.
2. Referee appointments are made by the journal editors. There are approximately 200 referees in the referee pool of the journal and these referees are classified according to their areas of interest. Each referee is sent an article on the subject he is interested in. The selection of the arbitrator is done in a way that does not cause any conflict of interest.
3. In the articles sent to the referees, the names of the authors are closed.
4. Referees are explained how to evaluate an article and are asked to fill in the evaluation form shown below.
5. The articles in which two referees give positive opinion are subjected to similarity review by the editors. The similarity in the articles is expected to be less than 25%.
6. A paper that has passed all stages is reviewed by the editor in terms of language and presentation, and necessary corrections and improvements are made. If necessary, the authors are notified of the situation.
.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.