nep-for New Economics Papers
on Forecasting
Issue of 2019‒10‒14
eleven papers chosen by
Rob J Hyndman
Monash University

  1. Forecasting Realized Volatility of Agricultural Commodities By Degiannakis, Stavros; Filis, George; Klein, Tony; Walther, Thomas
  2. Multiple Days Ahead Realized Volatility Forecasting: Single, Combined and Average Forecasts By Degiannakis, Stavros
  3. Evaluating Strange Forecasts: The Curious Case of Football Match Scorelines By J. James Reade; Carl Singleton; Alasdair Brown
  4. Macroeconomic Indicator Forecasting with Deep Neural Networks By Thomas Cook
  5. Forecasting European Economic Policy Uncertainty By Degiannakis, Stavros; Filis, George
  6. Boosting High Dimensional Predictive Regressions with Time Varying Parameters By Kashif Yousuf; Serena Ng
  7. Predictive, finite-sample model choice for time series under stationarity and non-stationarity By Kley, Tobias; Preuss, Philip; Fryzlewicz, Piotr
  8. Regularised forecasting via smooth-rough partitioning of the regression coefficients By Maeng, Hye Young; Fryzlewicz, Piotr
  9. Application of Machine Learning in Forecasting International Trade Trends By Feras Batarseh; Munisamy Gopinath; Ganesh Nalluru; Jayson Beckman
  10. Forecasting Formal Employment in Cities By Eduardo Lora
  11. Adapting Herzberg: Predicting Attendees' Satisfaction and Intention to Re-Visit a Festival - An Ordered Logit Approach By Love Odion Idahosa; Tembi Maloney Tichaawa

  1. By: Degiannakis, Stavros; Filis, George; Klein, Tony; Walther, Thomas
    Abstract: We forecast the realized and median realized volatility of agricultural commodities using variants of the Heterogeneous AutoRegressive (HAR) model. We obtain tick-by-tick data for five widely traded agricultural commodities (Corn, Rough Rice, Soybeans, Sugar, and Wheat) from the CME/ICE. Real out-of-sample forecasts are produced for 1- up to 66-days ahead. Our in-sample analysis shows that the variants of the HAR model which decompose volatility measures into their continuous path and jump components and incorporate leverage effects offer better fitting in the predictive regressions. However, we convincingly demonstrate that such HAR extensions do not offer any superior predictive ability in the out-of-sample results, since none of these extensions produce significantly better forecasts compared to the simple HAR model. Our results remain robust even when we evaluate them in a Value-at-Risk framework. Thus, there is no benefit by adding more complexity, related to volatility decomposition or relative transformations of volatility, in the forecasting models.
    Keywords: Agricultural Commodities, Realized Volatility, Median Realized Volatility, Heterogeneous Autoregressive model, Forecast.
    JEL: C22 C53 Q02 Q17
    Date: 2019
  2. By: Degiannakis, Stavros
    Abstract: The task of this paper is the enhancement of realized volatility forecasts. We investigate whether a mixture of predictions (either the combination or the averaging of forecasts) can provide more accurate volatility forecasts than the forecasts of a single model.We estimate long-memory and heterogeneous autoregressive models under symmetric and asymmetric distributions for the major European Union stock market indices and the exchange rates of the Euro. The majority of models provide qualitatively similar predictions for the next trading day’s volatility forecast. However, with regard to the one-week forecasting horizon, the heterogeneous autoregressive model is statistically superior to the long-memory framework. Moreover, for the two-weeks-ahead forecasting horizon, the combination of realized volatility predictions increases the forecasting accuracy and forecast averaging provides superior predictions to those supplied by a single model. Finally, the modeling of volatility asymmetry is important for the two-weeks-ahead volatility forecasts.
    Keywords: averaging forecasts, combining forecasts, heterogeneous autoregressive, intra-day data, long memory, model confidence set, predictive ability, realized volatility, ultra-high frequency
    JEL: C14 C32 C50 G11 G15
    Date: 2018
  3. By: J. James Reade (Department of Economics, University of Reading); Carl Singleton (Department of Economics, University of Reading); Alasdair Brown (School of Economics, University of East Anglia)
    Abstract: This study analyses point forecasts for a common set of events. These forecasts were made for distinct competitions and originally judged differently. The event outcomes were low-probability but had more predictable sub-outcomes upon which they were also judged. Hence, the forecasts were multi-dimensional, complicating any evaluation. The events were football matches in the English Premier League. The forecasts were of exact scoreline outcomes. We compare these with implied probability forecasts using bookmaker odds and a crowd of tipsters, as well as point and probabilistic forecasts generated from a statistical model suited to predicting football match scorelines. By evaluating these sources and types of forecast using various methods, we decide that forecasts of this type are strange, which we define. We argue that regression encompassing is the most appropriate way to compare point and probabilistic forecasts, and find that both types of forecasts for football match scorelines generally add information to one another.
    Keywords: Forecasting, Statistical modelling, Regression models, Prediction markets
    JEL: C53 L83 G14 G17
    Date: 2019–06
  4. By: Thomas Cook (Federal Reserve Bank of Kansas City)
    Abstract: Economic policymaking relies upon accurate forecasts of economic conditions. Current methods for unconditional forecasting are dominated by inherently linear models that exhibit model dependence and have high data demands. We explore deep neural networks as an opportunity to improve upon forecast accuracy with limited data and while remaining agnostic as to functional form. We focus on predicting civilian unemployment using models based on four different neural network architectures. Each of these models outperforms bench- mark models at short time horizons. One model, based on an Encoder Decoder architecture outperforms benchmark models at every forecast horizon (up to four quarters).
    Date: 2019
  5. By: Degiannakis, Stavros; Filis, George
    Abstract: Forecasting the economic policy uncertainty in Europe is of paramount importance given the on-going sovereign debt crisis. This paper evaluates monthly economic policy uncertainty index forecasts and examines whether ultra-high frequency information from asset market volatilities and global economic uncertainty can improve the forecasts relatively to the no-change forecast. The results show that the global economic policy uncertainty provides the highest predictive gains, followed by the European and US stock market realized volatilities. In addition, the European stock market implied volatility index is shown to be an important predictor of the economic policy uncertainty.
    Keywords: Economic policy uncertainty, forecasting, financial markets, commodities markets, HAR, ultra-high frequency information
    JEL: C22 C53 E60 E66 G10
    Date: 2019
  6. By: Kashif Yousuf; Serena Ng
    Abstract: High dimensional predictive regressions are useful in wide range of applications. However, the theory is mainly developed assuming that the model is stationary with time invariant parameters. This is at odds with the prevalent evidence for parameter instability in economic time series, but theories for parameter instability are mainly developed for models with a small number of covariates. In this paper, we present two $L_2$ boosting algorithms for estimating high dimensional models in which the coefficients are modeled as functions evolving smoothly over time and the predictors are locally stationary. The first method uses componentwise local constant estimators as base learner, while the second relies on componentwise local linear estimators. We establish consistency of both methods, and address the practical issues of choosing the bandwidth for the base learners and the number of boosting iterations. In an extensive application to macroeconomic forecasting with many potential predictors, we find that the benefits to modeling time variation are substantial and they increase with the forecast horizon. Furthermore, the timing of the benefits suggests that the Great Moderation is associated with substantial instability in the conditional mean of various economic series.
    Date: 2019–10
  7. By: Kley, Tobias; Preuss, Philip; Fryzlewicz, Piotr
    Abstract: In statistical research there usually exists a choice between structurally simpler or more complex models. We argue that, even if a more complex, locally stationary time series model were true, then a simple, stationary time series model may be advantageous to work with under parameter uncertainty. We present a new model choice methodology, where one of two competing approaches is chosen based on its empirical, finite-sample performance with respect to prediction, in a manner that ensures interpretability. A rigorous, theoretical analysis of the procedure is provided. As an important side result we prove, for possibly diverging model order, that the localised Yule-Walker estimator is strongly, uniformly consistent under local stationarity. An R package, forecastSNSTS, is provided and used to apply the methodology to financial and meteorological data in empirical examples. We further provide an extensive simulation study and discuss when it is preferable to base forecasts on the more volatile time-varying estimates and when it is advantageous to forecast as if the data were from a stationary process, even though they might not be.
    Keywords: forecasting; Yule-Walker estimate; local stationarity; covariance stationarity; EP/L014246/1
    JEL: C1
    Date: 2019–10–01
  8. By: Maeng, Hye Young; Fryzlewicz, Piotr
    Keywords: change-point detection; prediction; penalised spline; functional linear regression; EP/L014246/1
    JEL: C1
    Date: 2019–06–22
  9. By: Feras Batarseh; Munisamy Gopinath; Ganesh Nalluru; Jayson Beckman
    Abstract: International trade policies have recently garnered attention for limiting cross-border exchange of essential goods (e.g. steel, aluminum, soybeans, and beef). Since trade critically affects employment and wages, predicting future patterns of trade is a high-priority for policy makers around the world. While traditional economic models aim to be reliable predictors, we consider the possibility that Machine Learning (ML) techniques allow for better predictions to inform policy decisions. Open-government data provide the fuel to power the algorithms that can explain and forecast trade flows to inform policies. Data collected in this article describe international trade transactions and commonly associated economic factors. Machine learning (ML) models deployed include: ARIMA, GBoosting, XGBoosting, and LightGBM for predicting future trade patterns, and K-Means clustering of countries according to economic factors. Unlike short-term and subjective (straight-line) projections and medium-term (aggre-gated) projections, ML methods provide a range of data-driven and interpretable projections for individual commodities. Models, their results, and policies are introduced and evaluated for prediction quality.
    Date: 2019–10
  10. By: Eduardo Lora (Center for International Development at Harvard University)
    Abstract: Can “full and productive employment for all” be achieved by 2030 as envisaged by the United Nations Sustainable Development Goals? This paper assesses the issue for the largest 62 Colombian cities using social security administrative records between 2008 and 2015, which show that the larger the city, the higher its formal occupation rate. This is explained by the fact that formal employment creation is restricted by the availability of the diverse skills needed in complex sectors. Since skill accumulation is a gradual path-dependent process, future formal employment by city can be forecasted using either ordinary least square regression results or machine learning algorithms. The results show that the share of working population in formal employment will increase between 13 and nearly 32 percent points between 2015 and 2030, which is substantial but still insufficient to achieve the goal. Results are broadly consistent across methods for the larger cities, but not the smaller ones. For these, the machine learning method provides nuanced forecasts which may help further explorations into the relation between complexity and formal employment at the city level.
    Keywords: Employment creation
    Date: 2019–07
  11. By: Love Odion Idahosa; Tembi Maloney Tichaawa
    Abstract: This study adapts Herzberg's two-factor theory to investigate the satisfaction levels of attendees at the 2016 Festival of Arts and Culture (FESTAC) held in Cameroon. Specifically, it investigates how satisfaction is influenced by a-priori motivations for attending the event, which, in turn, affects revisit intentions. Using survey data collected from 324 participants at the festival, the study findings confirm the applicability of the Herzberg theory in evaluating the relationship between participants' motivation factors and their satisfaction levels. Satisfaction levels were also found to significantly influence return intentions. Results also emphasise the moderating effect of expenditure considerations on the attendees' satisfaction levels. These findings have implications for event planners and festival organisers as it highlights the superiority of unique festival `motivators' in predicting satisfaction levels, suggesting that event planners focus on these characteristics if they intend to increase attendees' satisfaction. The study is the first of its kind to apply Herzberg's theory to evaluating the relationship between motivation factors and satisfaction in a festival context. It is also the first West African contribution to the literature on the impact of event motivation on satisfaction levels and return intentions. The adoption of the Ordinal Logit Methodology is unique to this strand of literature.
    Keywords: Motivation, Satisfaction, Festival Attendees, Ordered Logit Model, Cameroon
    Date: 2019–10

This nep-for issue is ©2019 by Rob J Hyndman. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.