Independent writings
Support this site:

OpenForecast - User's Guide

Steven R. Gould

Getting Started with OpenForecast


OpenForecast is a package of general purpose, forecasting models written in Java that can be applied to any data series. One of the design goals was to make it easy for you to incorporate forecasts into your applications with little or no knowledge of the differences between the different forecasting models available.

Quick Start to Developing with OpenForecast

For those of you who do not want a detailed description of how to use OpenForecast, the following provides the general steps involved in using OpenForecast:

  • Create a DataSet object.

  • Add to the data set object a series of DataPoint objects that define a series of observations.

  • Using the static getBestForecast method of Forecaster, obtain a reference to the most appropriate forecast model for your data set.

  • Use the forecast method of this ForecastingModel to forecast additional values.

That's all there is to it.

Alternatively, if you want to force the application of a specific forecasting model, then refer to the class implementing that model in the net.sourceforge.openforecast.models package.

More Information

This User Guide is only intended to give you an introduction to the basic concepts and usage of OpenForecast. For the most, up-to-date and detailed information, refer to the JavaDocs. These can be accessed either via the OpenForecast web site, or by building the Ant target, docs using:

ant docs

and viewing the docs/index.html file in your web browser.

In the next section, we introduce you to a number of concepts and terms fundamental to forecasting.