"Time Series Prediction"

DaiWizard

Hi!

Currently I'm using a process in Rapid Miner to predict the closing value of a specific stock of the subsequent day.

I feed the process with untransformed data, that means: (1) Date (as ID) (2) Closing value (as Attribute (Real)).


Do you think executing a data transformation, before does make sense in this case ? If so, which one should I choose and how exactly do I implement it?  ???


Best regards !
 

DocMusher

http://www.simafore.com/blog/bid/106430/Using-RapidMiner-for-time-series-forecasting-in-cost-modeling-1-of-2
This might be a good starting point.
Cheers
Sven

DaiWizard

Thanks!