Error measurement statistics play a critical role in tracking forecast accuracy, monitoring for exceptions, and benchmarking your forecasting process. Interpretation of these statistics can be tricky, particularly when working with low-volume data or when trying to assess accuracy across multiple items (e.g., SKUs, locations, customers, etc.). This installment of Forecasting 101 surveys common error measurement statistics, examines the pros and cons of each and discusses their suitability under a variety of circumstances.
Forecast Pro includes a forecasting approach called seasonal simplification. Seasonal simplification is an extension of exponential smoothing which “simplifies” the modeling of the seasonal pattern by reducing the number of indices used. In many cases the seasonally simplified model can substantially improve forecast accuracy.
Box-Jenkins (ARIMA) is an important forecasting method that can yield highly accurate forecasts for certain types of data. In this installment of Forecasting 101 we’ll examine the pros and cons of Box-Jenkins modeling, provide a conceptual overview of how the technique works and discuss how best to apply it to business data.
If you are forecasting a time series that contains an outlier, there is a danger that the outlier could have a significant impact on the forecast. One solution to this problem is to screen the historical data for outliers and replace them with more typical values prior to generating the forecasts. This process is referred to as outlier detection and correction.
An outlier is a data point that falls outside of the expected range of the data (i.e., it is an unusually large or small data point). If you ignore outliers in your data, there is a danger that they can have a significant adverse impact on your forecasts. This article surveys three different approaches to forecasting data containing outliers, discusses the pros and cons of each and makes recommendations about when it is best to use each approach.
Preparing forecasts using data that contain one or more unusually large or small demand periods can be challenging. Depending on your forecasting approach, these “outliers” can have a significant impact on your forecasts. This article surveys three different approaches to forecasting data containing unusual demand periods, discusses the pros and cons of each and recommends when it is best to use each approach.
The recording of our recent educational one-hour Webinar is now available for viewing on-demand
This session demystifies regression modeling, demonstrating how these models can provide insight into your data and why they often yield more accurate results than alternative forecasting methods. Learn:
- When to apply regression models
- How to build and diagnose the models
- How to use leading indicators, lagged vari¬ables, Cochrane-Orcutt terms and “dummy” variables
- Best practices for applying regression models
You can register now for our next live Webinar How to Effectively Combine Judgment with Statistical Forecasts
When you use a statistical model to generate a 12-month forecast, you get more than just twelve numbers. You also get a great deal of information about how the forecast was generated, the model’s fit to the historic data and different measures of expected forecast accuracy. In this article, we dissect and catalogue the different components of a statistical forecast.
The 34th International Symposium on Forecasting (ISF)
Rotterdam, The Netherlands
June 29 – July 2, 2014
Early bird deadline: May 31, 2014
Among the many business issues to be tackled at the 34th International Symposium on Forecasting (ISF) in Rotterdam is integrating academic research into practical application. Sponsored annually by the International Institute of Forecasters (IIF), the conference is recognized as the premier international event for presenting important forecasting research. At the ISF, the world’s top forecasting professionals and researchers, presenters, and participants learn from each other and discuss cutting-edge forecasting trends.
Encompassing a broad range of forecasting sectors, this year’s conference includes sessions on forecasting for climate predictability, recession in real time, financial market volatility, forecast optimality, and a history of prediction science. Register by May 31 to take advantage of early bird registration discounts.
Forecast Pro TRAC provides a wide array of exception reports, including reports which monitor your archived forecasts (i.e., previously created and saved forecasts) and reports which monitor your current forecasts (i.e., the forecasts you are working with but haven’t yet finalized). Exception reports enable you to quickly find cases where key performance metrics have fallen outside of an acceptable range. In this installment of Forecast Pro Tips & Tricks we look at the Forecasts vs. History Exception Report which monitors current forecasts.