LIBOR KAVRAMI VE LIBOR’UN MULTİ-LAYER PERCEPTRON İLE TAHMİNİ

Abstract

1970'lerden beri yaşanan ekonomik gelişmeler ve faiz oranlarındaki aşırı oynaklık, uzun vadeli borçlanmalarda yeni çözümler gerektirmiştir. Bu kapsamda, değişken faiz oranları için bir karşılaştırma aracı olan Londra Bankalararası Teklif Faizi (LIBOR) önemli bir çözüm olmuştur. 1986’da BBA tarafından referans faiz oranı olarak hesaplanan LIBOR’un kullanımı 2008 Küresel Finans Krizi’ne kadar artmış, ancak kriz sonrası manipülasyon iddialarıyla sorgulanarak 2020’lerde ABD’de SOFR, Birleşik Krallık’ta SONIA ve AB’de ESTR ile değiştirilmiştir. Uzun yıllar bankalararası borçlanma maliyetlerini belirleyen LIBOR'un gelecekteki değerinin tahmini, şirketler ve ülkeler için büyük önem taşımaktadır. Faiz oranı modellemesi Louis Bachelier’in 1900’deki Aritmetik Brown Hareketi (ABM) çalışmasıyla başlamıştır. Günümüzde LIBOR Piyasa Modeli (LMM) yaygın olsa da karmaşıklığı, kalibrasyon sorunları, simülasyon gerekliliği ve LIBOR'un sona ermesiyle kullanımı sınırlıdır. Bu çalışmada, faiz hareketlerinin doğrusal ve parametrik olmaması nedeniyle geleneksel ekonometrik yöntemler yetersiz kalmıştır. Bu nedenle yapay zeka uygulaması olan Çok Katmanlı Algılayıcı (MLP) yöntemi kullanılmıştır. Yeterli SOFR verisi olmaması gibi nedenlerle, bir aylık LIBOR bağımlı, FED politika faizi ise bağımsız değişken olarak ele alınmıştır. Hem eşbütünleşme hem de MLP analizleri, LIBOR'un FED politika faizi ile birebir hareket ettiğini ortaya koymaktadır. FED Politika Faiz Oranının doğru tahmini, gelecekteki LIBOR oranının da isabetli tahminini mümkün kılacaktır.

Keywords

• Londra Bankalararası Teklif Faizi (LIBOR)
• LIBOR Piyasa Modeli (LMM)
• Çok Katmanlı Algılayıcı (MLP)

Libor Concept and Libor’s Estimation With Multi-Layer Perceptron

Abstract

Economic developments since the 1970s and excessive volatility in interest rates have necessitated new solutions for long-term borrowing. In this context, the London Interbank Offered Rate (LIBOR), a comparison tool for variable interest rates, has been an important solution. The use of LIBOR, calculated as a reference interest rate by the BBA in 1986, increased until the 2008 Global Financial Crisis but was subsequently questioned due to post-crisis manipulation allegations and replaced in the 2020s by SOFR in the US, SONIA in the UK, and ESTR in the EU. The estimation of the future value of LIBOR, which determined interbank borrowing costs for many years, is of great importance for companies and countries. Interest rate modeling began with Louis Bachelier's 1900 work on Arithmetic Brownian Motion (ABM). Although the LIBOR Market Model (LMM) is widely used today, its application is limited due to its complexity, calibration problems, simulation requirements, and the discontinuation of LIBOR. In this study, traditional econometric methods were insufficient as interest rate movements were not linear and parametric. Therefore, the Multi-Layer Perceptron (MLP) method, an artificial intelligence application, was used. Due to reasons such as the lack of sufficient SOFR data, one-month LIBOR was taken as the dependent variable and the FED policy rate as the independent variable. Both cointegration and MLP analyses reveal that LIBOR moves one-to-one with the FED policy rate. The correct estimation of the FED Policy Rate will enable an accurate estimation of the future LIBOR rate.

Keywords

• The London Inter-Bank Offered Rate (LIBOR)
• LIBOR Market Model (LMM)
• Multi-Layer Perceptron (MLP)

References

1. Alexander, C., & Lvov, D. (2003). Statistical properties of forward Libor rates (ISMA Discussion Papers in Finance 2003-03). ICMA Centre. http://www.icmacentre.ac.uk/pdf/discussion/DP2003-03.pdf
2. Alternative Reference Rates Committee. (2017, June 22). The ARRC selects a broad repo rate as its preferred alternative reference rate. Federal Reserve Bank of New York. https://www.newyorkfed.org/medialibrary/microsites/arrc/files/2017/ARRC-press-release-Jun-22-2017.pdf
3. Alternative Reference Rates Committee. (2018, March). Second report. Federal Reserve Bank of New York. https://www.sec.gov/spotlight/fixed-income-advisory-committee/arrc-second-report-041519.pdf
4. Alternative Reference Rates Committee. (2019, January 31). Frequently asked questions. Federal Reserve Bank of New York. https://assets.ey.com/content/dam/ey-sites/ey-com/en_gl/topics/banking-and-capital-markets/ey-arrc-faq.pdf
5. Andersen, L., & Andersen, J. (2000). Volatility skews and extensions of the Libor market model. Applied Mathematical Finance, 7(1), 1–32. https://doi.org/10.1080/13504860050036110
6. Andrés, J. A., & Scudiero, F. E. (2023). Futures contracts as a means of hedging market risks. Aibi Research, Management and Engineering Journal, 11(3), 42–51. https://doi.org/10.15649/2346030X.3185
7. Arteta, C., Kamin, S., & Ruch, F. U. (2022). How do rising U.S. interest rates affect emerging and developing economies? (World Bank Policy Research Working Paper, 10258). World Bank. https://documents1.worldbank.org/curated/en/099036212082239238/pdf/IDU032d1feef0db0d0480e0b3190f92d87c50de8.pdf
8. Astray, G. F. J., Rodriguez-Rajo, A., Ferreiro-Lage, M., Fernandez-Gonzalez, D., Jato, V., & Mejutoa, J. C. (2010). The use of artificial neural networks to forecast biological atmospheric allergens or pathogens only as Alternaria spores. Journal of Environmental Monitoring, 12(11), 2145–2152. https://doi.org/10.1039/c0em00248h

9. Bachelier, L. (1900). Théorie de la spéculation [Theory of speculation]. Gauthier-Villars.
10. Belomestny, D., & Schoenmakers, J. (2009). A jump-diffusion Libor model and its robust calibration. The Weierstrass Institute. https://www.wias-berlin.de/people/schoenma/RQUF-2008-0135_Final.pdf
11. Brace, A., Gatarek, D., & Musiela, M. (1997). The market model of interest rate dynamics. Mathematical Finance, 7(2), 127–154. https://doi.org/10.1111/1467-9965.00028
12. Cheng, L. (2016). On the calibration of the SABR model and its extensions (Master's thesis, Imperial College London). https://www.imperial.ac.uk/media/imperial-college/faculty-of-natural-sciences/department-of-mathematics/math-finance/Cheng_Luo-thesis.pdf
13. Congressional Budget Office. (2024, February). The budget and economic outlook: 2024 to 2034. https://www.cbo.gov/publication/59946
14. Devineau, L., Arrouy, P.-E., Bonnefoy, P., & Boumezoued, A. (2017). Fast calibration of the Libor market model with stochastic volatility and displaced diffusion. arXiv:1706.00263. https://arxiv.org/pdf/1706.00263.pdf
15. Durré, A., Evjen, S., & Pialgaard, R. (2003). Estimating risk premia in money markets (ECB Working Paper No. 221). European Central Bank. https://www.ecb.europa.eu/pub/pdf/scpwps/ecbwp221.pdf
16. Federal Reserve Bank of St. Louis. (2024). Federal Reserve Economic Data (FRED). https://fred.stlouisfed.org
17. Financial Conduct Authority. (2023, April 3). FCA announces decision on synthetic US dollar LIBOR. https://www.fca.org.uk/news/news-stories/fca-announces-decision-synthetic-us-dollar-libor
18. Gatarek, D., Bachert, P., & Maksymiuk, R. (2006). The LIBOR market model in practice. John Wiley & Sons. global-rates.com. (2024). Historical LIBOR rates. https://www.global-rates.com/en/interest-rates/libor/
19. Greene, W. H. (2012). Econometric analysis (7th ed.). Prentice Hall.
20. Haugh, M. (2010). Market models, term structure models: IEOR E4710. Columbia University. http://www.columbia.edu/~mh2078/market_models.pdf
21. Haykin, S. (2008). Neural networks and learning machines (3rd ed.). Pearson Education.
22. Heath, D., Jarrow, R., & Morton, A. (1992). Bond pricing and the term structure of interest rates: A new methodology for contingent claims valuation. Econometrica, 60(1), 77–105. https://doi.org/10.2307/2951677
23. Ho, T. S. Y., & Lee, S.-B. (1986). Term structure movements and pricing interest rate contingent claims. The Journal of Finance, 41(5), 1011–1029. https://doi.org/10.1111/j.1540-6261.1986.tb04524.x
24. Hou, D., & Skeie, D. (2014, March). LIBOR: Origins, economics, crisis, scandal, and reform (Federal Reserve Bank of New York Staff Reports, No. 667). http://hdl.handle.net/10419/120778
25. Huang, W., & Todorov, K. (2022, December). The post-Libor world: A global view from the BIS derivatives statistics. BIS Quarterly Review. https://www.bis.org/publ/qtrpdf/r_qt2212e.pdf
26. Hull, J. C. (2012). Options, futures, and other derivatives (8th ed.). Prentice Hall.
27. IBM. (2023, June 27). What is machine learning? IBM. https://www.ibm.com/topics/machine-learning Intercontinental Exchange. (2018, April 25). ICE LIBOR evolution. https://www.theice.com/publicdocs/ICE_LIBOR_Evolution_Report_25_April_2018.pdf
28. Izgi, B., & Bakkaloglu, A. (2017). Fundamental solution of bond pricing in the Ho-Lee stochastic interest rate model under the invariant criteria. New Trends in Mathematical Sciences, 5(1), 196–203. http://dx.doi.org/10.20852/ntmsci.2017.138
29. Jackel, P. (2001). Monte Carlo methods in finance. John Wiley & Sons.
30. Jamshidian, F. (1997). Libor and swap market models and measures. Finance and Stochastics, 1(4), 293–330. https://doi.org/10.1007/s007800050026
31. Jarrow, R., & Protter, P. (2003). A short history of stochastic integration and mathematical finance: The early years, 1880–1970. Cornell University. https://www.ma.imperial.ac.uk/~ajacquie/IC_AMDP/IC_AMDP_Docs/Literature/Jarrow_Protter_History_Stochastic_Integration.pdf
32. Kiff, J. (2012, December). Back to basics: What is LIBOR? Finance & Development, 49(4). https://www.imf.org/external/pubs/ft/fandd/2012/12/basics.htm
33. LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521, 436–444. https://doi.org/10.1038/nature14539
34. Leippold, M., & Strömberg, J. (2013). Time-changed Levy LIBOR market model: Pricing and joint estimation of the cap surface and swaption cube (Swiss Finance Institute Research Paper Series, No. 12–23). https://ssrn.com/abstract=2065375
35. Martinez Peria, S. M., & Schmukler, S. (2017). Understanding the use of long-term finance in developing economies (IMF Working Paper WP/17/96). International Monetary Fund. https://www.elibrary.imf.org/view/journals/001/2017/096/001.2017.issue-096-en.xml
36. Merton, R. C. (1973). Theory of rational option pricing. The Bell Journal of Economics and Management Science, 4(1), 141–183. https://doi.org/10.2307/3003143
37. Miltersen, K., Sandmann, K., & Sondermann, D. (1997). Closed form solutions for term structure derivates with log-normal interest rates. Journal of Finance, 52(1), 409–430. ttps://doi.org/10.1111/j.1540-6261.1997.tb02710.x
38. Nawalkha, S. K. (2009). The LIBOR market model: A critical review. SSRN. https://papers.ssrn.com/sol3/papers.cfm?abstract_id=1396777
39. Nekrasov, V. (2013). An accompaniment to a course on interest rate modeling: With discussion of Black-76, Vasicek and HJM models and a gentle introduction to the multivariate LIBOR market model. SSRN. https://ssrn.com/abstract=2001007
40. Papapantoleon, A., Schoenmakers, J., & Skovmand, D. (2011). Efficient and accurate log-Lévy approximations to Lévy driven LIBOR models (CREATES Research Paper, 2011-22). https://www.wias-berlin.de/people/schoenma/papapan_schoen_skov.pdf
41. Papapantoleon, A., & Skovmand, D. (2011, July). Numerical methods for the Lévy LIBOR model [Paper presentation]. Conference Name, Location. arXiv:1006.3340. https://arxiv.org/pdf/1006.3340.pdf
42. Peters, O., & Adamou, A. (2018). The sum of log-normal variates in geometric Brownian motion. arXiv:1802.02939. https://arxiv.org/abs/1802.02939
43. Popescu, M.-C., Balas, V. E., Perescu-Popescu, L., & Mastorakis, N. (2009). Multilayer perceptron and neural networks. WSEAS Transactions on Circuits and Systems, 8(7), 579-588. https://www.researchgate.net/publication/228340819
44. Samuelson, P. A. (1965). Rational theory of warrant pricing. Industrial Management Review, 6(2), 13–39.
45. Tomar, A., & Laxkar, P. (2022). Differences of Tanh, sigmoid and ReLu activation function in neural network. International Journal of Scientific Progress and Research, 80(6), 18-22.
46. The World Bank. (2015). Global financial development report 2015-2016: Long-term finance. https://documents1.worldbank.org/curated/en/955811467986333727/pdf/99100-PUB-REVISED-Box393195B-OUO-9-PUBLIC.pdf
47. Vasicek, O. (1977). An equilibrium characterization of the term structure. Journal of Financial Economics, 5(2), 177–188. https://doi.org/10.1016/0304-405X(77)90016-2
48. Verschuren, R. M. (2020). Stochastic interest rate modelling using a single or multiple curves: An empirical performance analysis of the Lévy forward price model. Quantitative Finance, 20(7), 1123–1148. https://doi.org/10.1080/14697688.2020.1722318
49. Wang, L., Zhang, M., & Liu, Z. (2023). The progress of Black-Scholes model and Black-Scholes-Merton model. BCP Business & Management, 38, 3405–3410. https://doi.org/10.54691/bcpbm.v38i.3980
50. West, G. (2010). Interest rate derivatives: Lecture notes. finmod. https://web.archive.org/web/20120417044831/http://www.finmod.co.za/ird.pdf Westfälische Wilhelms-Universität Münster. (2021). Advanced financial mathematics, lecture notes summer term 2021. https://www.uni-muenster.de/imperia/md/content/Stochastik/financial_mathematics.pdf
51. Wu, L., & Zhang, F. (2006). LIBOR market model with stochastic volatility. Journal of Industrial and Management Optimization, 2(2), 199–227. https://doi.org/10.3934/jimo.2006.2.199