nep-for New Economics Papers
on Forecasting
Issue of 2019‒01‒07
four papers chosen by
Rob J Hyndman
Monash University

  1. Can we beat the Random Walk? The case of survey-based exchange rate forecasts in Chile By Pincheira, Pablo; Neumann, Federico
  2. Retail forecasting: research and practice By Fildes, Robert; Ma, Shaohui; Kolassa, Stephan
  3. Nowcasting real GDP growth with business tendency surveys data: A cross country analysis By Evzen Kocenda; Karen Poghosyan
  4. Forecast ranked tailored equity portfolios By Buncic, Daniel; Stern, Cord

  1. By: Pincheira, Pablo; Neumann, Federico
    Abstract: We examine the accuracy of survey-based expectations of the Chilean exchange rate relative to the US dollar. Our out-of-sample analysis reveals that survey-based forecasts outperform the Driftless Random Walk (DRW) in terms of Mean Squared Prediction Error at several forecasting horizons. This result holds true even when comparing the survey to a more competitive benchmark based on a refined information set. A similar result is found when precision is measured in terms of Directional Accuracy: survey-based forecasts outperform a “pure luck” benchmark at several forecasting horizons. Differing from the traditional “no predictability” result reported in the literature for many exchange rates, our findings suggest that the Chilean peso is indeed predictable.
    Keywords: Survey expectations, Exchange Rates, Forecasting, Random Walk, Directional Accuracy, Mean Squared Prediction Error.
    JEL: C0 C00 C01 C1 C10 C12 C14 C20 C22 C52 C53 C58 D00 E0 E17 E31 E37 E43 E44 E47 E50 E52 E58 F00 F31 F32 F37 F41 F47 G00 G12 G17
    Date: 2018–12–08
  2. By: Fildes, Robert; Ma, Shaohui; Kolassa, Stephan
    Abstract: This paper first introduces the forecasting problems faced by large retailers, from the strategic to the operational, from the store to the competing channels of distribution as sales are aggregated over products to brands to categories and to the company overall. Aggregated forecasting that supports strategic decisions is discussed on three levels: the aggregate retail sales in a market, in a chain, and in a store. Product level forecasts usually relate to operational decisions where the hierarchy of sales data across time, product and the supply chain is examined. Various characteristics and the influential factors which affect product level retail sales are discussed. The data rich environment at lower product hierarchies makes data pooling an often appropriate strategy to improve forecasts, but success depends on the data characteristics and common factors influencing sales and potential demand. Marketing mix and promotions pose an important challenge, both to the researcher and the practicing forecaster. Online review information too adds further complexity so that forecasters potentially face a dimensionality problem of too many variables and too little data. The paper goes on to examine evidence on the alternative methods used to forecast product sales and their comparative forecasting accuracy. Many of the complex methods proposed have provided very little evidence to convince as to their value, which poses further research questions. In contrast, some ambitious econometric methods have been shown to outperform all the simpler alternatives including those used in practice. New product forecasting methods are examined separately where limited evidence is available as to how effective the various approaches are. The paper concludes with some evidence describing company forecasting practice, offering conclusions as to the research gaps but also the barriers to improved practice.
    Keywords: retail forecasting; product hierarchies; big data; marketing analytics; user-generated web content; new products; comparative accuracy; forecasting practice
    JEL: L81 M20 M30
    Date: 2019–10
  3. By: Evzen Kocenda (Institute of Economic Studies, Faculty of Social Sciences, Charles University in Prague, Czech Republic); Karen Poghosyan (Central Bank of Armenia, Economic Research Department, Yerevan, Armenia)
    Abstract: We use nowcasting methodology to forecast the dynamics of the real GDP growth in real time based on the business tendency surveys data. Nowcasting is important because key macroeconomic variables on the current state of the economy are available only with a certain lag. This is particularly true for those variables that are collected on a quarterly basis. To conduct out‐of‐sample forecast evaluation we use business tendency surveys data for 22 European countries. Based on the different dataset and using outof‐sample recursive regression scheme we conclude that nowcasting model outperforms several alternative short‐term forecasting statistical models, even when the volatility of the real GDP growth is increasing both in time and across different countries. Based on the Diebold‐Mariano test statistics, we conclude that nowcasting strongly outperforms BVAR and BFAVAR models, but comparison with AR, FAAR and FAVAR does not produce sufficient evidence to prefer one over another.
    Keywords: Nowcasting, short‐term forecasting, dynamic and static principal components, Bayesian VAR, Factor Augmented VAR, real GDP growth, European OECD countries
    JEL: E52 C33 C38 C52 C53 E37
    Date: 2018–09
  4. By: Buncic, Daniel; Stern, Cord
    Abstract: We use a dynamic model averaging (DMA) approach to construct forecasts of individual equity returns for a large cross-section of stocks contained in the SP500, FTSE100, DAX30, CAC40 and SPX30 headline indices, taking value, momentum, and quality factors as predictor variables. Fixing the set of ‘forgetting factors’ in the DMA prediction framework, we show that highly significant return forecasts relative to the historic average benchmark are obtained for 173 (281) individual equities at the 1% (5%) level, from a total of 895 stocks. These statistical forecast improvements also translate into considerable economic gains, producing out-of-sample R 2 values above 5% (10%) for 283 (166) of the 895 individual stocks. Equally weighted long only portfolios constructed from a ranking of the best 25% forecasts in each headline index can generate sizable returns in excess of a passive investment strategy in that index itself, even when transaction costs and risk taking are accounted for.
    Keywords: Active factor models, model averaging and selection, computational finance, quantitative equity investing, stock selection strategies, return-based factor models.
    JEL: C11 C52 F37 G11 G15 G17
    Date: 2018–11–25

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.