Forecasting Nord Pool day-ahead prices with an autoregressive model

This paper presents a model to forecast Nord Pool hourly day‐ahead prices. The model is based on but reduced in terms of estimation parameters (from 24 sets to 1) and modified to include Nordic demand and Danish wind power as exogenous variables. We model prices across all hours in the analysis period rather than across each single hour of 24hours. By applying three model variants on Nord Pool data, we achieve a weekly mean absolute percentage error (WMAE) of around 6–7% and an hourly mean absolute percentage error (MAPE) ranging from 8% to 11%. Out of sample results yields a WMAE and an hourly MAPE of around 5%. The models enable analysts and traders to forecast hourly day‐ahead prices accurately. Moreover, the models are relatively straightforward and user‐friendly to implement. They can be set up in any trading organization.