View Table of Contents »


Fall 2014

Special Feature: Role of the Sales Force in Forecasting

  • Role of the Sales Force in Forecasting by Mike Gilliland
    Mike draws on his own and others’ experience to identify the key issues in using sales force input to the forecasts. As you would no doubt expect, these are not black-and-white concerns, but demonstrate the importance of thinking through how sales input should be provided, how to motivate reliable input, and how to judge its value to the organization.
  • Commentaries by Joe Smith, Rob Dhuyvetter and Lauge Valentin


    1. Data Cube Forecasting for the Forecasting Support System by Igor Gusakov
      In this article, Igor examines the process of data-cube forecasting and its potential for improving an organization’s forecasting support system (FSS). The process utilizes online analytical processing (OLAP) to embed time-series methods and forecast adjustments, thus integrating key aspects of forecast generation, reconciliation, and reporting.
    2. Forecasting by Aggregation, 2 articles
      Forecasting by Cross-Sectional Aggregation, by Giulio Zotteri, Matteo Kalchschmidt, and Nicola Saccani
      Rather than automatically proceeding to forecast with data at the same level of aggregation as that required for an organization’s operations, the authors explain that the best level of aggregation for forecasting should be chosen by the forecasters in consideration of the trade-off between sampling error (data inadequate to generate reliable forecasts) and specification error (data too aggregated to represent diverse demands). Doing so frees the forecaster from an unneeded constraint, thus opening new opportunities to improve forecasting performance.

      Optimally Reconciling Forecasts in a Hierarchy, by Rob J. Hyndman and George Athanasopoulos
      We know that when forecasting the product hierarchy, reconciliation is invariably needed to make the sum of lower-level forecasts equate to the upper level forecasts. The authors argue that the traditional Bottom-Up, Top-Down, and Middle-Out procedures for reconciliation all fail to make best use of the available data. They show we can do better by taking weighted averages of the forecasts from different levels, an approach they call optimal reconciliation.

    3. SPIES – A Simple Method for Improving Forecasts? by Paul Goodwin
      My previous Hot New Research column discussed the benefits of including information about uncertainty in forecasts (“Getting Real about Uncertainty,” Foresight Issue 33, Spring 2014). Forecasts expressed as a single number (point forecasts) give no information about the forecast’s reliability, which is unhelpful when decisions have to be made about levels of safety stock or what cash reserves to hold for unexpected contingencies.
Go to Top