The Informational Content of the Term Spread in Forecasting the US Inflation Rate: A Nonlinear Approach

Abstract

The difficulty in modelling inflation and the significance in discovering the underlying data‐generating process of inflation is expressed in an extensive literature regarding inflation forecasting. In this paper we evaluate nonlinear machine learning and econometric methodologies in forecasting US inflation based on autoregressive and structural models of the term structure. We employ two nonlinear methodologies: the econometric least absolute shrinkage and selection operator (LASSO) and the machine‐learning support vector regression (SVR) method. The SVR has never been used before in inflation forecasting considering the term spread as a regressor. In doing so, we use a long monthly dataset spanning the period 1871:1–2015:3 that covers the entire history of inflation in the US economy. For comparison purposes we also use ordinary least squares regression models as a benchmark. In order to evaluate the contribution of the term spread in inflation forecasting in different time periods, we measure the out‐of‐sample forecasting performance of all models using rolling window regressions. Considering various forecasting horizons, the empirical evidence suggests that the structural models do not outperform the autoregressive ones, regardless of the model's method. Thus we conclude that the term spread models are not more accurate than autoregressive models in inflation forecasting. Copyright © 2016 John Wiley & Sons, Ltd.

Forecasting automobile gasoline demand in Australia using machine learning-based regression

“…The support vector regression (SVR) algorithm, developed by Vapnik et al (1992) and Cortes and Vapnik (1995), is an extension of the support vector machine and has gained popularity in the field of energy economics (see Ghoddusi et al 2019 for a survey). The major advantage of SVR over other ML techniques is that it results in a convex minimisation problem with a unique global minimum, which avoids local minima (Plakandaras et al 2017). SVR adopts the structural risk minimisation (SRM) principle by seeking to minimise an upper bound of the generalisation error rather than the training error, which results in improved generalisation performance, the absence of a local minimum and the sparse representation of a solution.…”

Analysis of the Term Structure of Major Currencies Using Principal Component Analysis and Autoencoders

“…Bianchi et al [24] provided statistical evidence in favor of bond return predictability using extreme-tree and neural-network methods. Baruník and Malinska [32] used machine-learning algorithms to predict the term structure of crude oil futures prices, Plakandaras et al [20] evaluated machine-learning algorithm and econometric methods for predicting US inflation based on the autoregression and structural models of period structures. Gogas et al [19] used a machine-learning framework to forecast the yield curve in terms of the real gross domestic product (GDP) cycle of the US.…”

“…In particular, Novosyolov and Satchkov [11] performed an analysis using PCA on US, EU, and UK Treasury bills, and LIBOR (London Interbank Offered Rate). Furthermore, various machine-learning models such as the multilayer perceptron (MLP), support vector machines, and long short-term memory (LSTM), have been used to analyze term structure (Kanevski et al [18], Gogas et al [19], Plakandaras et al [20], Nunes et al [21], Suimon et al [22], Kim et al [23], Bianchi et al [24], Jung and Choi [25]). Among the machine-learning approaches, the autoencoder (AE) is a more current method for determining term structure.…”

The Yield Curve as a Leading Indicator: Accuracy and Timing of a Parsimonious Forecasting Model

“…Thus, the prediction skill measure depends on the shift between the prediction and observed time series in addition to their cyclic characteristics. Both R and RMSE metrics are used in the literature, e.g., R (and a pseudo-R) was used by Estrella and Hardouvelis [1] and Fornaro [25], and versions of the RMSE were used by Gupta et al [26] and Plakandaras et al [27].…”