Forecasting the yield curve for Poland with the PCA and machine learning

Tomasz Piotr Kostyra ()
Additional contact information
Tomasz Piotr Kostyra: Warsaw School of Economics

Bank i Kredyt, 2024, vol. 55, issue 4, 459-478

Abstract: The article examines the application of the Principal Component Analysis (PCA) and machine learning method, the Long Short-Term Memory (LSTM), in the prediction of the yield curve for Poland. The PCA was applied to decompose the yield curve, forecast its components using the LSTM, and obtain the yield curve predictions upon recomposition. The results from the PCA-LSTM model were compared to predictions generated directly by the LSTM model, simple autoregression and random walk, which serves as a benchmark. Overall, LSTM predictions are the most accurate with PCA-LSTM being a close second, nonetheless PCA-LSTM is more accurate in short-term forecasting of interest rates at long maturities. Both methods outperform the benchmark, while autoregression usually underperforms. For these reasons, the PCA-LSTM as well as the LSTM can be useful in interest rate management or building trading strategies. The PCA-LSTM has the advantage that it can focus on particular components of the yield curve, such as variability of the yield curve’s level or steepness.

Keywords: forecasting; LSTM; machine learning; PCA; yield curve (search for similar items in EconPapers)
JEL-codes: C53 G12 G17 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://bankikredyt.nbp.pl/content/2024/04/bik_04_2024_03.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nbp:nbpbik:v:56:y:2024:i:4:p:459-478

Access Statistics for this article

More articles in Bank i Kredyt from Narodowy Bank Polski Contact information at EDIRC.
Bibliographic data for series maintained by Wojciech Burjanek ().