I'm trying to adopt a solution for long-term electricity annual prices forecasting (depending on past electricity prices, past oil prices, past consumption data, etc.)

I'm considering some solutions:

  • off-the-shelf specific software: Alyuda, Aleasoft, ...
  • already-built modules of known software (Excel, MatLab, R): neuroXL for Excel, modules for Simulink, ...
  • code from scratch (Python, R) by using known models and Machine Learning: scikit-learn, Weka, regression, ...

I would like to find more solutions to test and, if possible, some experiences using them.

  • 4
    $\begingroup$ Regardless of software it's more important for you to select the type of analysis/forecasting. Given that in addition to past prices you have also some independent variables to account too, ARIMA with option of transfer functions is what comes to mind immediately. There exist software for automatic building ARIMA model. However, it is always a good idea to first investigate your price data for stationarity, seasonality and shifts. $\endgroup$ – ttnphns Mar 1 '13 at 10:36

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.