nep-for New Economics Papers
on Forecasting
Issue of 2022‒07‒18
fourteen papers chosen by
Rob J Hyndman
Monash University

  1. The Role of the Monthly ENSO in Forecasting the Daily Baltic Dry Index By Elie Bouri; Rangan Gupta; Luca Rossini
  2. Forgetting Approaches to Improve Forecasting By Paulo M.M. Rodrigues; Robert Hill
  3. Forecasting Interest Rates with Shifting Endpoints: The Role of the Demographic Age Structure By Jiazi Chen; Zhiwu Hong; Linlin Niu
  4. Policy Uncertainty and Stock Market Volatility Revisited: The Predictive Role of Signal Quality By Afees A. Salisu; Riza Demirer; Rangan Gupta
  5. Stock Market Bubbles and the Forecastability of Gold Returns (and Volatility) By David Gabauer; Rangan Gupta; Sayar Karmakar; Joshua Nielsen
  6. The Impact of Sampling Variability on Estimated Combinations of Distributional Forecasts By Ryan Zischke; Gael M. Martin; David T. Frazier; D. S. Poskitt
  7. "Density forecasts of inflation using Gaussian process regression models". By Petar Soric; Enric Monte; Salvador Torra; Oscar Claveria
  8. Forecasting macroeconomic data with Bayesian VARs: Sparse or dense? It depends! By Luis Gruber; Gregor Kastner
  9. Ensemble distributional forecasting for insurance loss reserving By Benjamin Avanzi; Yanfeng Li; Bernard Wong; Alan Xian
  10. Aporte de las expectativas de empresarios al pronóstico de las variables macroeconómicas By María Alejandra Hernández-Montes; Ramón Hernández-Ortega; Jonathan Alexander Muñoz-Martínez
  11. Impact analysis of GDP related variables on economic growth of Sri Lanka By Samarasinghe, Tharanga
  12. Predicting Day-Ahead Stock Returns using Search Engine Query Volumes: An Application of Gradient Boosted Decision Trees to the S&P 100 By Christopher Bockel-Rickermann
  13. Nonlinear Forecasts and Impulse Responses for Causal-Noncausal (S)VAR Models By Christian Gourieroux; Joann Jasiak
  14. Spline-rule ensemble classifiers with structured sparsity regularization for interpretable customer churn modeling By Koen W. de Bock; Arno de Caigny

  1. By: Elie Bouri (Lebanese American University, Lebanon); Rangan Gupta (University of Pretoria, South Africa); Luca Rossini (University of Milan, Italy)
    Abstract: Using Bayesian Reverse Unrestricted-Mixed Data Sampling (RU-MIDAS) models, we predict the daily Baltic Dry Index (BDI) based on the monthly information content of the El Nino Southern Oscillation (ENSO) from January, 1985 to February, 2022. The results show that the Oceanic Nino Index (ONI) capturing the ENSO produces statistically significant forecast gains in terms of both point and density forecasts for the BDI, relative to a constant-mean benchmark model, at both short and long forecast horizons (i.e., one to twenty one-day-ahead). Notably, these gains primarily emanate from the El Nino rather than La Nina phase of the ENSO.
    Keywords: Baltic Dry Index (BDI), El Nino Southern Oscillation (ENSO), Reverse Unrestricted- Mixed Data Sampling (RU-MIDAS) Models, Forecasting
    JEL: C22 C53 Q02 Q54
    Date: 2022–06
  2. By: Paulo M.M. Rodrigues; Robert Hill
    Abstract: There is widespread evidence of parameter instability in the literature. One way to account for this feature is through the use of time-varying parameter (TVP) models that discount older data in favour of more recent data. This practise is often known as forgetting and can be applied in several different ways. This paper introduces and examines the performance of different (flexible) forgetting methodologies in the context of the Kalman filter. We review and develop the theoretical background and investigate the performance of each methodology in simulations as well as in two empirical forecast exercises using dynamic model averaging (DMA). Specifically, out-of-sample DMA forecasts of CPI inflation and S&P500 returns obtained using different forgetting approaches are compared. Results show that basing the amount of forgetting on the forecast error does not perform as well as avoiding instability by placing bounds on the parameter covariance matrix.
    JEL: C22 C51 C53
    Date: 2022
  3. By: Jiazi Chen; Zhiwu Hong; Linlin Niu
    Abstract: An extended dynamic Nelson-Siegel (DNS) model is developed with an additional functional demographic (FD) factor that considers the overall demographic age distribution as a persistent long-run driving force. The FD factor in the extended DNS model improves the accuracy of the yield curve forecast by reducing both bias and variance compared to the random walk model, the DNS model, the DNS model with a simple demographic factor of a middle-to-young (MY) age ratio, and a benchmark end-shifting model. The model with an unspanned FD factor performs substantially better than the alternative models for most maturities at forecast horizons between 1 and 5 years.
    Keywords: Demographic distribution; Yield curve forecasting; Functional data analysis; Life cycle; Nelson-Siegel model; Semiparametric modeling.
    JEL: E31 E43 G12 J11
    Date: 2022–06–25
  4. By: Afees A. Salisu (Centre for Econometrics & Applied Research, Ibadan, Nigeria; Department of Economics, University of Pretoria, Private Bag X20, Hatfield 0028, South Africa); Riza Demirer (Department of Economics and Finance, Southern Illinois University Edwardsville, Edwardsville, IL 62026-1102, USA); Rangan Gupta (Department of Economics, University of Pretoria, Private Bag X20, Hatfield 0028, South Africa)
    Abstract: This paper provides novel mixed-frequency insight to the growing literature on the (monthly) economic policy uncertainty-(daily) stock market volatility nexus by examining the out-of-sample predictive ability of the quality of political signals over stock market volatility at various forecast horizons, and whether or not accounting for the signal quality in forecasting models can help achieve economic gains for investors. Both in- and out-of-sample tests, based on a GARCH-MIDAS framework, show that the quality of the policy signal indeed matters when it comes to the predictive role played by policy uncertainty over subsequent stock market volatility. While high EPU is found to predict high volatility, particularly when the signal quality is high, the positive relationship between EPU and volatility breaks down when the signal quality is low. The improved out-of-sample volatility forecasts obtained from the models that account for the quality of policy signals also helps typical mean-variance investors achieve improved economic outcomes captured by higher certainty equivalent returns and Sharpe ratios. Although our results indicate clear distinctions between the U.S. and U.K. stock markets in terms of how policy signals are processed by market participants, they highlight the role of the quality of policy signals as a driver of volatility forecasts with significant economic implications.
    Keywords: Economic policy uncertainty, Signal quality, Market Volatility, Forecasting
    JEL: C32 C53 D8 E32 G15
    Date: 2022–06
  5. By: David Gabauer (Data Analysis Systems, Software Competence Center Hagenberg, Austria); Rangan Gupta (Department of Economics, University of Pretoria, Private Bag X20, Hatfield 0028, South Africa); Sayar Karmakar (Department of Statistics, University of Florida, 230 Newell Drive, Gainesville, FL, 32601, USA); Joshua Nielsen (Boulder Investment Technologies, LLC, 1942 Broadway Suite 314C, Boulder, CO, 80302, USA)
    Abstract: Firstly, we use the Multi-Scale LPPLS Confidence Indicator approach to detect both positive and negative bubbles at short-, medium- and long-term horizons for the stock markets of the G7 and the BRICS countries. We were able to detect major crashes and rallies in the 12 stock markets over the period of the 1st week of January, 1973 to the 2nd week of September, 2020. We also observed similar timing of strong (positive and negative) LPPLS indicator values across both G7 and BRICS countries, suggesting interconnectedness of the extreme movements in these stock markets. Secondly, we utilize these indicators to forecast gold returns and its volatility, using a method involving block means of residuals obtained from the popular LASSO routine, given that the number of covariates ranged between 42 to 72, and gold returns demonstrated a heavy upper tail. We found that, our bubbles indicators, particularly when both positive and negative bubbles are considered simultaneously, can accurately forecast gold returns at short- to medium-term, and also time-varying estimates of gold returns volatility to a lesser extent. Our results have important implications for the portfolio decisions of investors who seek a safe haven during boom-bust cycles of major global stock markets.
    Keywords: Gold, Stock Markets, Bubbles, Forecasting, Returns, Volatility
    JEL: C22 C53 G15 Q02
    Date: 2022–06
  6. By: Ryan Zischke (Department of Econometrics and Business Statistics, Monash University; Methodology Division, Australian Bureau of Statistics); Gael M. Martin (Department of Econometrics and Business Statistics, Monash University); David T. Frazier (Department of Econometrics and Business Statistics, Monash University); D. S. Poskitt (Department of Econometrics and Business Statistics, Monash University)
    Abstract: We investigate the performance and sampling variability of estimated forecast combinations, with particular attention given to the combination of forecast distributions. Unknown parameters in the forecast combination are optimized according to criterion functions based on proper scoring rules, which are chosen to reward the form of forecast accuracy that matters for the problem at hand, and forecast performance is measured using the out-of-sample expectation of said scoring rule. Our results provide novel insights into the behavior of estimated forecast combinations. Firstly, we show that, asymptotically, the sampling variability in the performance of standard forecast combinations is determined solely by estimation of the constituent models, with estimation of the combination weights contributing no sampling variability whatsoever, at first order. Secondly, we show that, if computationally feasible, forecast combinations produced in a single step -- in which the constituent model and combination function parameters are estimated jointly -- have superior predictive accuracy and lower sampling variability than standard forecast combinations -- where constituent model and combination function parameters are estimated in two steps. These theoretical insights are demonstrated numerically, both in simulation settings and in an extensive empirical illustration using a time series of S&P500 returns.
    Date: 2022–06
  7. By: Petar Soric (Faculty of Economics & Business University of Zagreb.); Enric Monte (Department of Signal Theory and Communications, Polytechnic University of Catalunya (UPC).); Salvador Torra (Riskcenter–IREA, University of Barcelona (UB).); Oscar Claveria (AQR–IREA, University of Barcelona (UB).)
    Abstract: The present study uses Gaussian Process regression models for generating density forecasts of inflation within the New Keynesian Phillips curve (NKPC) framework. The NKPC is a structural model of inflation dynamics in which we include the output gap, inflation expectations, fuel world prices and money market interest rates as predictors. We estimate country-specific time series models for the 19 Euro Area (EA) countries. As opposed to other machine learning models, Gaussian Process regression allows estimating confidence intervals for the predictions. The performance of the proposed model is assessed in a one-step-ahead forecasting exercise. The results obtained point out the recent inflationary pressures and show the potential of Gaussian Process regression for forecasting purposes.
    Keywords: Machine learning, Gaussian process regression, Time-series analysis, Economic forecasting, Inflation, New Keynesian Phillips curve. JEL classification: C45, C51, C53, E31.
    Date: 2022–07
  8. By: Luis Gruber; Gregor Kastner
    Abstract: Vectorautogressions (VARs) are widely applied when it comes to modeling and forecasting macroeconomic variables. In high dimensions, however, they are prone to overfitting. Bayesian methods, more concretely shrinking priors, have shown to be successful in improving prediction performance. In the present paper we introduce the recently developed $R^2$-induced Dirichlet-decomposition prior to the VAR framework and compare it to refinements of well-known priors in the VAR literature. We demonstrate the virtues of the proposed prior in an extensive simulation study and in an empirical application forecasting data of the US economy. Further, we shed more light on the ongoing Illusion of Sparsity debate. We find that forecasting performances under sparse/dense priors vary across evaluated economic variables and across time frames; dynamic model averaging, however, can combine the merits of both worlds. All priors are implemented using the reduced-form VAR and all models feature stochastic volatility in the variance-covariance matrix.
    Date: 2022–06
  9. By: Benjamin Avanzi; Yanfeng Li; Bernard Wong; Alan Xian
    Abstract: Loss reserving generally focuses on identifying a single model that can generate superior predictive performance. However, different loss reserving models specialise in capturing different aspects of loss data. This is recognised in practice in the sense that results from different models are often considered, and sometimes combined. For instance, actuaries may take a weighted average of the prediction outcomes from various loss reserving models, often based on subjective assessments. In this paper, we propose a systematic framework to objectively combine (i.e. ensemble) multiple stochastic loss reserving models such that the strengths offered by different models can be utilised effectively. Criteria of choice consider the full distributional properties of the ensemble. A notable innovation of our framework is that it is tailored for the features inherent to reserving data. These include, for instance, accident, development, calendar, and claim maturity effects. Crucially, the relative importance and scarcity of data across accident periods renders the problem distinct from the traditional ensembling techniques in statistical learning. Our ensemble reserving framework is illustrated with a complex synthetic dataset. In the results, the optimised ensemble outperforms both (i) traditional model selection strategies, and (ii) an equally weighted ensemble. In particular, the improvement occurs not only with central estimates but also relevant quantiles, such as the 75th percentile of reserves (typically of interest to both insurers and regulators).
    Date: 2022–06
  10. By: María Alejandra Hernández-Montes; Ramón Hernández-Ortega; Jonathan Alexander Muñoz-Martínez
    Abstract: Este documento evalúa el aporte de las expectativas de los empresarios, capturadas a través de las encuestas del Banco de la República y Fedesarrollo, a los pronósticos de las principales variables macroeconómicas: inflación, desempleo, empleo y crecimiento económico. Este aporte se evalúa mediante la comparación de los errores de pronóstico de uno a cuatro trimestres de dos modelos econométricos anidados. Los resultados sugieren que las expectativas de los empresarios reducen de manera importante el error de pronóstico de la inflación y del crecimiento económico, mientras que los aportes al pronóstico del empleo y el desempleo son limitados. **** ABSTRAC: In this paper we evaluate the contribution of business expectations from surveys of Banco de la República and Fedesarrollo, to the forecasts of the main macroeconomic variables: inflation, unemployment, employment and economic growth. We make this assessment by comparing one to four quarters ahead forecast errors of two nested models econometrics. The results suggest that the expectations of businessmen could have information that improves forecasts of economic growth and inflation and have other lower contributions to employment and unemployment predictions.
    Keywords: Expectativas, encuestas, pronósticos, expectations, surveys, forecast
    JEL: C53 D84 E37
    Date: 2022–06
  11. By: Samarasinghe, Tharanga
    Abstract: The objective of this study is to analyze the impacts of GDP related variables in economic growth of Sri Lanka. Although there are many important variables affects to the GDP growth, this study focuses only on Foreign Direct Investment (FDI), external debt stock, domestic saving rate, net export and final consumption expenditure. Except domestic saving rate, all other variables are measured by using the constant US$ value in 2005. The domestic saving rate was measured as a % of GDP. Auto Regressive Distributed Lag (ARDL) is proposed as the estimation method and the data set which was taken from World Bank will be analyzed using the EViews 8. I.
    Keywords: Economic growth, Sri Lanka, GDP, Economic growth rate of Sri Lanka, Economic growth forecasting, Auto Regressive Distributed Lag, ARDL
    JEL: D00 D04 O1 O11 O21 O4 O40
    Date: 2022–05–23
  12. By: Christopher Bockel-Rickermann
    Abstract: The internet has changed the way we live, work and take decisions. As it is the major modern resource for research, detailed data on internet usage exhibits vast amounts of behavioral information. This paper aims to answer the question whether this information can be facilitated to predict future returns of stocks on financial capital markets. In an empirical analysis it implements gradient boosted decision trees to learn relationships between abnormal returns of stocks within the S&P 100 index and lagged predictors derived from historical financial data, as well as search term query volumes on the internet search engine Google. Models predict the occurrence of day-ahead stock returns in excess of the index median. On a time frame from 2005 to 2017, all disparate datasets exhibit valuable information. Evaluated models have average areas under the receiver operating characteristic between 54.2% and 56.7%, clearly indicating a classification better than random guessing. Implementing a simple statistical arbitrage strategy, models are used to create daily trading portfolios of ten stocks and result in annual performances of more than 57% before transaction costs. With ensembles of different data sets topping up the performance ranking, the results further question the weak form and semi-strong form efficiency of modern financial capital markets. Even though transaction costs are not included, the approach adds to the existing literature. It gives guidance on how to use and transform data on internet usage behavior for financial and economic modeling and forecasting.
    Date: 2022–05
  13. By: Christian Gourieroux; Joann Jasiak
    Abstract: We introduce the closed-form formulas of nonlinear forecasts and nonlinear impulse response functions (IRF) for the mixed causal-noncausal (Structural) Vector Autoregressive (S)VAR models. We also discuss the identification of nonlinear causal innovations of the model to which the shocks are applied. Our approach is illustrated by a simulation study and an application to a bivariate process of Bitcoin/USD and Ethereum/USD exchange rates.
    Date: 2022–05
  14. By: Koen W. de Bock (Audencia Business School); Arno de Caigny (LEM - Lille économie management - UMR 9221 - UA - Université d'Artois - UCL - Université catholique de Lille - Université de Lille - CNRS - Centre National de la Recherche Scientifique)
    Abstract: An important business domain that relies heavily on advanced statistical- and machine learning algorithms to support operational decision-making is customer retention management. Customer churn prediction is a crucial tool to support customer retention. It allows an early identification of customers who are at risk to abandon the company and provides the ability to gain insights into why customers are at risk. Hence, customer churn prediction models should complement predictive performance with model insights. Inspired by their ability to reconcile strong predictive performance and interpretability, this study introduces rule ensembles and their extension, spline-rule ensembles, as a promising family of classification algorithms to the customer churn prediction domain. Spline-rule ensembles combine the flexibility of a tree-based ensemble classifier with the simplicity of regression analysis. They do, however, neglect the relatedness between potentially conflicting model components which can introduce unnecessary complexity in the models and compromises model interpretability. To tackle this issue, a novel algorithmic extension, spline-rule ensembles with sparse group lasso regularization (SRE-SGL) is proposed to enhance interpretability through structured regularization. Experiments on fourteen real-world customer churn data sets in different industries (i) demonstrate the superior predictive performance of spline-rule ensembles with sparse group lasso over a set well yet powerful benchmark methods in terms of AUC and top decile lift; (ii) show that spline-rule ensembles with sparse group lasso regularization significantly outperform conventional rule ensembles whilst performing at least as well as conventional spline-rule ensembles; and (iii) illustrate the interpretable nature of a spline-rule ensemble model and the advantage of structured regularization in SRE-SGL by means of a case study on customer churn prediction for a telecommunications company.
    Keywords: Customer churn prediction,Predictive analytics,Spline-rule ensemble,Interpretable data science,Sparse group lasso,Regularized regression
    Date: 2021–11

This nep-for issue is ©2022 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.