Modelling and forecasting interest rates during stages of the economic cycle: A knowledge-discovery approach

Díaz, David; Theodoulidis, Babis; Dupouy, Carlos

doi:10.1016/j.eswa.2015.09.010

Cited by 17 publications

(7 citation statements)

References 54 publications

(100 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These techniques include support vector machines (Gogas et al, 2015), fuzzy logic and genetic algorithms (Ju et al, 1997), neural networks (Kim & Noh, 1997;Oh & Han, 2000;Hong & Han, 2002;Bianchi et al 2020b, a) and case-based reasoning (Kim & Noh 1997). However, the financial literature has been slow to adapt such methods (Bianchi et al 2020b), possibly because it is not necessary straightforward to understand their abundant non-linear patterns (Diaz et al, 2016) and it is claimed that they are not suitable for parameter inference (see Mullainathan & Spiess, 2017). Finally, data-driven yield curve models fit mathematical functions, including spline-based and parsimonious functions, to discount factors, spot rates, forward rates or par yields (Müller, 2002;BIS, 2005).…”

Section: Models For Estimating the Term Structurementioning

confidence: 99%

“…We refer to Duffee (2013) for a profound examination of yield curve models used for forecasting and to Carriero et al (2012) for an extensive comparison of different modelling approaches that are estimated with Bayesian vector autoregression. It should be emphasized that parsimonious yield curve models were originally not intended for forecasting since they do not contain information on the dynamics of the yield curve (Lengwiler & Lenz, 2010;Diaz et al, 2016), unless further assumptions are made on the evolution of the factors as, e.g., in the extension by Diebold & Li (2006).…”

Section: Parsimonious Models For Forecastingmentioning

confidence: 99%

See 1 more Smart Citation

A Comparative Analysis of Parsimonious Yield Curve Models with Focus on the Nelson-Siegel, Svensson and Bliss Versions

2021

View full text Add to dashboard Cite

We shed light on computational challenges when fitting the Nelson-Siegel, Bliss and Svensson parsimonious yield curve models to observed US Treasury securities with maturities up to 30 years. As model parameters have a specific financial meaning, the stability of their estimated values over time becomes relevant when their dynamic behavior is interpreted in risk-return models. Our study is the first in the literature that compares the stability of estimated model parameters among different parsimonious models and for different approaches for predefining initial parameter values. We find that the Nelson-Siegel parameter estimates are more stable and conserve their intrinsic economical interpretation. Results reveal in addition the patterns of confounding effects in the Svensson model. To obtain the most stable and intuitive parameter estimates over time, we recommend the use of the Nelson-Siegel model by taking initial parameter values derived from the observed yields. The implications of excluding Treasury bills, constraining parameters and reducing clusters across time to maturity are also investigated.

show abstract

Section: Models For Estimating the Term Structurementioning

confidence: 99%

Section: Parsimonious Models For Forecastingmentioning

confidence: 99%

A Comparative Analysis of Parsimonious Yield Curve Models with Focus on the Nelson-Siegel, Svensson and Bliss Versions

2021

View full text Add to dashboard Cite

show abstract

“…(13) EN SS t,j is likely to be correlated with the zero yield levels, because BOJ decides JGBs' purchasing amount referring to the interest rate levels, in addition to other macroeconomic variables such as inflation rates and GDP. 3 More concretely, at the introduction of the YCC policy, BOJ stated that it would purchase JGBs so that the 10 year JGB yield rate would remain more or less at 0 %. In fact, when the market interest rates deviated from the related target levels to certain extents, BOJ also implemented the fixed rate method once for the 1-3 and 3-5 year sectors as well as twice for the 5-10 year sector: On November 17, 2016, BOJ showed the purchase price at -0.09% for the 2 year current issue and at -0.04 % for the 5 year current issue.…”

Section: Model With Mos and Enssmentioning

confidence: 99%

“…To overcome this problem, some researches begin to pay attention to policy or/and qualitative factors in the modeling of interest rates (e.g., Diaz, Theodoulidis & Dupouy, 2016;Oh & Han, 2000). For example, Jarrow and Li (2014) extended HJM (Heath, Jarrow, & Morton, 1992) model to explicitly include the quantitative impact of the Fed's trades on Treasury market prices, in order to consider the effect of the quantitative easing (QE) program on the U.S. term structure of interest rates.…”

Section: Introductionmentioning

confidence: 99%

On the Effect of Bank of Japan’s Outright Purchase on the JGB Yield Curve

Nakano

Takahashi

et al. 2018

Asia-Pac Financ Markets

View full text Add to dashboard Cite

This paper examines an impact of Bank of Japan (BOJ)'s outright purchase on the JGB (Japanese government bond) yield curve. Particularly, we develop a simple state space model, which incorporates new factors regarding the BOJ's announcement for its outright purchase and the current market outstanding with standard level and spread factors. Based on the model with a filtering method, we also implement an empirical analysis with time series of the BOJ's announcement records during 2014/10/22-2017/8/3 in the quantitative-qualitative easing(QQE) period to estimate the sensitivities of interest rates against the changes in the market expectation for the net supply with each sector of JGB. We expect the current work provides a basis for considering quantitative effects on the term structure by BOJ's policy changes such as termination or significant reduction of the BOJ's outright purchase. For instance, our scenario analysis shows substantial increase in the 30 year yield with widening of 20-30 year spread.

show abstract

“…The reason for this difficulty is the presence of mixed, complex and non-linear time series. The reason why linear time series cannot be formed is that financial markets are affected by politics, investors, and the overall economy (Bezerra & Albuquerque, 2017;Diaz, Theodoulidis & Dupouy, 2016;Göçken, Özçalıcı & Boru, 2016;Henrique, Sobreiro & Kimura, 2019;Tay & Cao, 2001;Zhang, Lin & Shang, 2017;Zhong & Enke, 2017).…”

Section: Introductionmentioning

confidence: 99%

Data mining application with machine learning algorithms to manage interest rate risk

KOÇOĞLU

Ersöz²

2022

bmij

View full text Add to dashboard Cite

In trade, the risks taken may increase the expected income; however, they may also cause large amounts of losses as well. Banks transfer the capital and the deposits they collect from their clients to the individuals or institutions in need of profit, taking certain risks into account. One of the important risks taken in this process of capital transfer is the market's change in interest or profit share rates. If the bank transfers the deposit collected with a certain commitment to the market at a lower rate, it will make a loss. Models for predicting future interest or profit share rates gain importance for preventing this situation. The aim of this study is to determine which variables will be taken into account for the loan interest rate that banks will offer to their customers during the lending process, and to create a machine learning model that can predict the loan interest rate that the bank will offer to its customers by using these variables. Multiple Linear Regression analysis was performed to demonstrate the relationship between the variables selected based on the literature review, expert opinions, and the interest rate. In order to facilitate decision-makers in practice, Random Forests, Decision Trees, K-Nearest Neighbours (KNN), Artificial Neural Networks (ANN), and Support Vector Machine (SVM) algorithms from machine learning algorithms were compared by using the prediction model. Accuracy Rate, Cohen's Kappa, Precision, Sensitivity, and F-Measure measurements were used to compare the algorithms used in the study. According to the analysis results, it was observed that the Random Forest algorithm was more successful on the first model consisting of weekly data. The Decision Tree algorithm succeeded more on the second model consisting of monthly data prediction performance. In the model consisting of weekly data, USD Selling Price, Stock Index (BIST100), and Central Bank Gold Reserve from the Multiple Linear Regression variables were found significant in affecting the interest rate.

show abstract

Modelling and forecasting interest rates during stages of the economic cycle: A knowledge-discovery approach

Abstract: The opinions and results of this work are the sole responsibility of the authors. They do not represent in any way the institutional views or policies of their affiliations.

Cited by 17 publications

References 54 publications

A Comparative Analysis of Parsimonious Yield Curve Models with Focus on the Nelson-Siegel, Svensson and Bliss Versions

A Comparative Analysis of Parsimonious Yield Curve Models with Focus on the Nelson-Siegel, Svensson and Bliss Versions

On the Effect of Bank of Japan’s Outright Purchase on the JGB Yield Curve

Data mining application with machine learning algorithms to manage interest rate risk

Contact Info

Product

Resources

About