'The future is another country' - while this is certainly true, some things are more predictable than others.

Time series prediction is fundamentally about simulating a system. Whether this is trader psychology, the weather or popular opinion, if the system can be simulated the results can be accurate, though they will always be susceptible to events outside of the system that may affect it.

Scientio has a product, ChaosKit, which is targeted at chaotic time series of a single variable. 'Chaos' here is used in the mathematical sense. A chaotic process is one where positive feedback of some kind exists. Under some circumstances such systems can create time series that appear to be completely random - the corollary of this is that some seemingly random series are in fact chaotic, and thus to a certain extent predictable. Chaotic systems are never completely predictable; because of feedback the simulation and the real series will always rapidly diverge.

Chaotic time series commonly occur in engineering and finance.

XmlMiner can be used for all other time series prediction tasks. This includes sales predictions, demand predictions and many other business and governmental prediction tasks.

XmlMiner can, as the name suggests, take input from XML data and create predictions that are plugged back into the XML.

Since all databases and many other kinds of applications  input and output XML, this guarantees universal connectivity with little programming effort.