BIST LİKİDİTE BANKA ENDEKSİ FARKLI VADELİ İŞLEM KONTRATLARI İLE FİYAT KEŞFİ ETKİNLİĞİ: ÇOK KATMANLI ALGILAYICI SİNİR AĞI

Year 2024, Volume: 15 Issue: 2, 1174 - 11191, 07.07.2024

Orhan Özaydın

https://doi.org/10.54688/ayd.1474392

Abstract

Spot ve vadeli işlemlerde fiyat keşfi sürecinin çift yönlü olduğu literatürde sıkça görülmektedir. Bu çalışmanın yeniliği, Türkiye'de nispeten yeni bir endeks olan BIST likit banka endeksinin spot verilerinin farklı vadelerdeki vadeli işlem sözleşmeleri kullanılarak çok katmanlı algılayıcı (MLP) yapay sinir ağı modeli ile analiz edilmesinde yatmaktadır. Modellerin etkinliği, vadeli işlem fiyatlarının spot fiyat keşfini önceleme etkinliği incelenerek değerlendirilmiştir. MLP modellerinin etkinliği, örneklem dışı test serisi sonuçlarına göre düşük ortalama karesel hata (MSE) oranları ile ölçülmüştür. Bulgular, likit banka endeksinin bir ve iki sonraki vadeli işlem sözleşmelerinin spot fiyatları açıklamada en yakın vadeli işlem sözleşmelerinden daha etkili olduğunu göstermektedir. Ayrıca, en yakın vadeli sözleşmelerin diğerlerine göre daha yüksek varyanslara sahip olduğu gözlenmiştir. Hem spot hem de vadeli işlem sözleşmelerinin açıklayıcı değişkenler olarak birlikte kullanılan model, en etkin fiyat keşfi modeli olmuştur. Spot için üç gecikmeli ve iki sonraki vadeli işlem sözleşmesi için iki gecikmeli modeldir. Bu sonuçların, spot ve vadeli işlem yapan bireyler için risk yönetimi stratejileri uygulanırken dikkate alınması önerilmektedir.

Keywords

BIST likit banka endeksi, Çok katmanlı algılayıcı yapay sinir ağları, Vadeli işlem sözleşmeleri, Spot fiyat keşfi, Finansal tahmin

Ethical Statement

yok

Supporting Institution

yok

Thanks

yok

PRICE DISCOVERY EFFICIENCY IN BIST LIQUIDITY BANK INDEX USING DEFERRED FUTURES: A MULTILAYER PERCEPTRON NEURAL NETWORK APPROACH

Abstract

The literature indicates that the process of price discovery in spot and futures can be bidirectional. This study novelty lies in its analysis of the spot data of the BIST liquid bank index, a relatively new index in Turkey, using futures contracts of different maturities with a multi-layer perceptron (MLP) artificial neural network model. The efficacy of the models is evaluated by examining the capacity of futures prices to inform spot price discovery. The effectiveness of the MLP models is measured by low mean squared error (MSE) ratios relative to the out-of-samples test series results. The findings indicate that the one- and two-next futures contracts of the liquid bank index are more effective than the nearest futures contracts in explaining spot prices. Additionally, the nearest expiry contracts are observed to exhibit higher variances than the others. The most efficient pricing model including both spot and futures as explaining variables, is autoregression with three lags for spot and two lags for the two next futures contracts. These results must be considered when implementing risk management strategies for individuals engaged in spot and futures transactions.

Keywords

BIST Liquid Bank Index, Multi-layer Perceptron Artificial Neural Networks, Futures Contracts, Spot Price Discovery, Financial Forecasting

References

• Bohl, M. T., Salm, C. A. & Schuppli, M. (2011). Price discovery and investor structure in stock index futures. The Journal of Futures Markets, 31 (3), 282–306. https://doi.org/10.1002/fut.20469.
• Borsa İstanbul (2024). Bist likit pay endeksleri. Retrieved from https://borsaistanbul.com/tr/endeks/1/6/likit at 05.03.2024.
• Chan, L. & Lien, D. (2001). Cash settlement and price discovery in futures markets. Quarterly Journal of Business and Economics, 40 (3/4), 65-77. https://www.jstor.org/stable/40473334.
• Chen, Y.-J., Duan, J.-C. & Hung, M.-W. (1999). Volatility and maturity effects in the Nikkei index futures. Journal Of Futures Markets, 19 (8), 895–895.
• Chen, X., & Tongurai, J. (2023). Informational linkage and price discovery between China's futures and spot markets: Evidence from the US–China trade dispute. Global Finance Journal, 55, 100750. https://doi.org/10.1016/j.gfj.2022.100750.
• Fassas, A., Papadamou, S. & Koulis, A. (2020). Price discovery in bitcoin futures. Research In International Business and Finance, 52. https://doi.org/10.1016/j.ribaf.2019.101116.
• Gök, İ. Y. & Kalaycı, Ş. (2014). Intraday price discovery and volatility spillover in Bist 30 spot and futures markets. Süleyman Demirel University Economics and Administrative Faculty Journal, 19 (3), 109-133.
• Güzel, F. (2020). Analysis of price discovery and volatility interactions in spot and derivative markets: an empirical application on Borsa Istanbul. PhD Thesis. Selçuk University, Konya.
• Hsu, C.-M. (2011). Forecasting stock/futures prices by using neural networks with feature selection. Paper presented at the 2011 6th IEEE Joint International Information Technology and Artificial Intelligence Conference. Chongqing, China. doi:10.1109/ITAIC.2011.6030137.
• Hu, Z., Mallory, M., Serra, T. & Garcia, P. (2020). Measuring price discovery between nearby and deferred contracts in storable and nonstorable commodity futures markets. Agricultural Economics (United Kingdom), 51 (6), 825-840. https://doi.org/10.1111/agec.12594.
• Kalaycı, Ş. & Gök, İ. Y. (2013). Price discovery in index futures and spot markets: a literature review from 1982 to present. International Journal of Alanya Faculty of Business, 5 (2), 37-50.
• Katoch, R., & Batra, S. (2023). Co-movement Between NIFTY Spot and Futures Indices: A Time–Frequency Analysis Using Wavelet. Studies in Microeconomics, 0(0) (Published online). https://doi.org/10.1177/23210222231194860.
• Kaur, K. (2019). Price discovery in spot and futures market: Evidence from selected Sensex companies. International Journal of Management Studies. DOI:10.18843/ijms/v6i1(2)/07.
• Kulkarni, S. & Haidar, I. (2009). Forecasting model for crude oil price using artificial neural networks and commodity futures prices. International Journal of Computer Science and Information Security, 2 (1).
• Kumar, B. & Pandey, A. (2011). Price discovery in emerging commodity markets: spot and futures relationship in Indian commodity futures market. Boğaziçi Journal, 25 (1), 79-121. DOI:10.21773/BOUN.25.1.4.
• Nicolau, M. (2012). Do spot prices move towards futures prices? A study on crude oil market. Acta Universitatis Danubius OEconomica, Danubius University of Galati, issue 5 (5), 166-176.
• Refenes, A. (1995). Neural networks in the capital markets. John Wiley & Sons, New York.
• Sánchez Lasheras, F., de Cos Juez, F. J., Suárez Sánchez, A., Krzemień, A. & Riesgo Fernández, P. (2015). Forecasting the Comex copper spot price by means of neural networks and arima models. Resources Policy, 45, 37-43. https://doi.org/10.1016/j.resourpol.2015.03.004.
• Szczepańska-Przekota, A. (2022). Causality in relation to futures and cash prices in the wheat market. Agriculture, 12 (6), 872. https://doi.org/10.3390/agriculture12060872.
• Wang, J. & Li, X. (2018). A combined neural network model for commodity price forecasting with SSA. Soft Computing, 22, 5323–5333. https://doi.org/10.1007/s00500-018-3023-2.
• Xie, S., Zhou, S., & Zhang, Y. (2023). Should dominant contracts move to nearby months? Evidence from Chinese agricultural futures markets. Global Finance Journal. Advance online publication. https://doi.org/10.1016/j.gfj.2023.100929.
• Xu, X. & Zhang, Y. (2021). Corn cash price forecasting with neural networks. Computers and Electronics in Agriculture, 184, 106120. https://doi.org/10.1016/j.compag.2021.106120.
• Yağcılar, G., G. (2022). Information efficiency and interactions between spot and futures markets: Lead-lag relationship and volatility transmission. International Journal of Management Economics and Business, 18 (2), 470-491. http://dx.doi.org/10.17130/ijmeb.969177.