FORESIGHT, Issue 34

$0.00$45.00

Clear

Description

Summer 2014

Special Feature: Forecasting by Aggregation

  • Forecasting by Temporal Aggregation by Aris Syntetos
    Forecasting by temporal aggregation is the process of aggregating demands from higher-frequency to lower-frequency time buckets – for example, aggregating daily data to weekly – and using the aggregate time series to generate forecasts. This intuitively appealing approach will almost always reduce demand uncertainty. Still, the benefits of temporal aggregation may not be well understood by managers, which may make implementation a harder sell, and the necessary software applications are not adequately supported in commercial forecasting packages – at least, not yet. In this foundational article, Aris describes the approaches to temporal aggregation and summarizes the benefits and challenges faced in implementation.
  • Improving Forecasting via Multiple Temporal Aggregation by Fotios Petropoulos and Nikolaos Kourentzes
    In most business forecasting applications, the decision-making need we have directs the frequency of the data we collect (monthly, weekly, etc.) and use for forecasting. In this article, Fotios and Nikolaos introduce an approach that combines forecasts generated by modeling the different frequencies (levels of temporal aggregation). Their technique augments our information about the data used for forecasting and, as such, can result in more accurate forecasts. It also automatically reconciles the forecasts at different levels.
  • Forecaster in the Field: Aris Syntetos

Articles

  1. Forecasting for Revenue Management: An Introduction by McKay Curtis 
    Revenue management (RM) is concerned with maximizing the revenue earned from a given set of resources. Practitioners in this fieldwork to (1) define the precise set of products, (2) optimally set product prices, and (3) optimally control product availability. In this article, McKay and Fred describe key elements of revenue management and the challenges of forecasting in this context.
  2. Using Relative Error Metrics to Improve Forecast Quality in the Supply Chain by Steve Morlidge. 
    How can we identify our best opportunities to improve forecast accuracy? Steve Morlidge concludes his four-part Foresight series on forecast quality by offering an approach based on (a) product volumes and variability, and (b) a forecastability metric that assesses forecast accuracy in relation to the accuracy of a naïve (i.e., no change) forecast. The metric helps supply-chain forecasters set meaningful targets for improvement, quantifies the scope for improvement, and tracks progress toward final goals.
  3. Book Reviews by Ira Sohn {Free article}
    Fortune Tellers: The Story of America’s First Economic Forecasters
     by Walter A. Friedman 
    In 100 Years: Leading Economists Predict the Future
    edited by Ignacio Palacios-Huerta

Additional information

Content

Complete Issue, Special Feature, Special Feature 1, Special Feature 2, Article 1, Article 2, Article 3, Article 4, Article 5, Article 6, Article 7, Article 8, Article 9, Free Article, Free Article 1, Free Article 2, Free Article 3, Free Article 4