Makine Öğrenmesi Yatırımcının Risk İştahını Öngörür mü?

Year 2024, Volume: 6 Issue: 3, 143 - 154, 30.09.2024

Nesrin Özkan , Nurgül Ö. Yalıncaklı

https://doi.org/10.54821/uiecd.1460617

Abstract

Risk iştahı, finansal piyasa katılımcıları tarafından ilgiyle izlenen önemli bir göstergedir. Risk iştahı endekslerinden biri olan "RISE risk iştahı endeksi", genel olarak Türkiye piyasasının risk derecesini ölçmek için hesaplanmaktadır. Literatürde RISE risk iştahıyla ilgili sınırlı sayıda çalışma bulunmakta ve bu çalışmaların çoğu, risk iştahını tahmin etmek için basit ekonometrik yöntemleri kullanmaktadır. Bildiğimiz kadarıyla, makine öğrenmesi algoritmalarını kullanan bir çalışmaya rastlanmamıştır. Bu nedenle, makine öğrenmesi algoritmaları kullanılarak risk iştahının tahminlenmesi merak uyandırmaktadır. Bu çalışmanın amacı, RISE endeksinin tahmin başarısını Uzun Kısa Süreli Hafıza (LSTM) ve Çok Katmanlı Algılayıcı (MLP) kullanarak ölçmektir. Analiz, 2008'den 2023'e kadar olan yılları kapsayan haftalık frekanslı veri setine dayanmaktadır. Sonuçlar, RMSE değerlerine göre karşılaştırılmış olup, LSTM algoritması MLP'ye kıyasla daha yüksek bir tahminleme başarısı sunmaktadır. RISE endeksi üzerinde BIST 100 endeksinin tahmin yeteneği göz önüne alındığında ise BIST 100 endeksinin mevcut ve gecikmiş değerleri karşılaştırılmış ve gecikmeli BIST 100 değerlerinin RISE' ı tahmin etme yeteneğinin, mevcut değerlere göre yaklaşık olarak iki kat daha yüksek olduğu belirlenmiştir. Bu değerli bulgunun, piyasa katılımcılarına ve finansal analistlere, piyasa beklentilerini tahmin etmede derin öğrenme algoritmalarını kullanarak yatırım tercihlerini şekillendirmelerine ve doğru yatırımlar yapmalarına rehberlik edeceği beklenmektedir.

Keywords

Risk İştahı, RISE Endeksi, Tahminleme, LSTM, MLP

Does Machine Learning Forecast Investor’s Risk Appetite?

Abstract

Risk appetite is an important indicator that is monitored with interest by financial market participants. One of the risk appetite indices is nominated “RISE risk appetite index” calculated to measure the riskiness of the Turkey market in general. There are very limited studies in the literature on RISE risk appetite, and most of them use simple econometric methods to predict the risk appetite. To the best of our knowledge, there is no study using machine learning algorithms. Therefore, it creates curiosity on how the success will be in estimating the risk appetite using machine learning algorithms. Thus, the aim of this paper is to measure the estimation success of the RISE index using Long Short-term Memory (LSTM) and Multi-Layer Perceptron (MLP). The analysis is based on a weekly frequency dataset covering the years 2008 to 2023. The results are compared as per RMSE values, and LSTM presents rather high prediction success compared to MLP. Due to the forecasting ability of BIST 100 index on RISE, the current and lagged values of BIST 100 are compared, and lagged values of BIST 100 are found to have a higher ability to estimate RISE, approximately twice as much as current values. It is expected that this valuable finding will be a guide for market participants and financial analysts to shape their investment preferences by using deep learning algorithms in predicting market expectations and to make well-directed investments.

Keywords

Risk Appetite, RISE Index, Forecasting, LSTM, MLP

References

• Adrian, T., Etula, E., & Shin, H. S. (2010). Risk appetite and exchange rates (361). FRB of New York Staff Report.
• Alpay, Ö. (2020). USD / TRY price prediction using LSTM architecture. European Journal of Science and Technology, Special Issue: 452-456.
• Baek, I. M. (2006). Portfolio investment flows to Asia and Latin America: Pull, push or market sentiment?,Journal of Asian Economics, 17(2), 363-373.
• Çelik S., Dönmez, E., & Burcu, A. (2017). The Determinants of risk appetite: Evidence from Turkey. Usak University Journal of Social Sciences, IASOS Special Issue, 153-162.
• Central Securities Depository & Trade Repository of Türkiye (2021). Storage Services.
• Doğan, F., & Türkoğlu, İ. (2019) Deep learning and application areas. DUMF Engineering Journal, 10(2), 409-445.
• Financial Stability Review (2007). ECB European Central Bank, 167.
• Gai, P., & Vause, N. (2006). Measuring investors’ risk appetite. International Journal of Central Banking, 2(1), 167-188.
• Gemici, E., Gök, R., & Bouri, E. (2023). Predictability of risk appetite in Turkey: Local versus global factors. Emerging Markets Review, 55, 101018.
• Global Strategy Research, (2004) Market focus, Credit Suisse Research Institute.
• Haugen, P. (2006). Financial risk, risk appetite and the macroeconomic environment. (Master Thesis of Science in Physics and Mathematics. Norwegian University)
• Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780.
• Illing, M., & Aaron, M. (2005). A brief survey of risk-appetite indexes. Financial System Review. Bank of Canada.
• İskenderoğlu, Ö., & Akdağ, S. (2019). Causality analysis between risk appetite with oil prices, currency rates, gold prices, and interest rates: The case of Turkey. Dogus University Journal, 20(1), 1-14.
• Köycü, E. (2022). The relationship between risk appetite index and BIST100 index: A study of the pre and post Covid-19 period, Research of Financial Economic and Social Studies, 7(1), 1-11.
• Kumar, M. S., & Persaud, A. (2002). Pure contagion and investors’ shifting risk appetite: Analytical issues and empirical evidence. International Finance, 5(3), 401-436.
• Misina, M. (2005). Benchmark index of risk appetite, Monetary and Financial Analysis (Vol 15). Bank of Canada.
• Özkan, N. (2022). Analysis of the relationship between investors’ risk appetite, BIST 100, dollar exchange rate and gold prices: An investigation on Covid-19 pandemic period. In Handbook of İşletme ve İktisadi Bilimler Metodoloji, Araştırma ve Uygulama, (pp. 353-368). Livre de Lyon.
• Pericoli, M., & Sbracia, M. (2009). Capital asset pricing model and the risk appetite index: Theoretical differences, empirical similarities and implementation problems. International Finance, 12(2), 123-150.
• Saraç, T. B., İskenderoğlu, Ö., & Akdağ, S. (2016). Investigation of domestic and foreign investors’ risk appetite: The case of Turkey. Sosyoekonomi, 24(30), 29-44.
• Sarı, S., & Başakın, E. (2021). Analysis of BIST Bank index with data-based models. Journal of Productivity, (3), 147-163.
• Sarwar, G. (2012). Is VIX an investor fear gauge in BRIC equity markets?, Journal of Multinational Financial Management, 22(3), 55-65.
• Shen, D.B., & Hu, K.H. (2007). Bank risk appetite measurement and the relationship with macroeconomic factors: Case of Taiwan’s banks. International Journal of Information Systems for Logistics and Management, 3(1), 25-39.
• Ting, F.F., & Sim, K.S. (2017). Self-regulated multilayer perceptron neural network for breast cancer classification. In 2017 International Conference on Robotics, Automation and Sciences (ICORAS) (pp. 1-5). IEEE.
• Yılmaz, T., & Yıldız, B. (2022). The relationship between investors’ risk appetite index and fear indices: An empirical application with ARDL in Turkey. Journal of Research in Economics, Politics & Finance, 7(3), 646-676.