Automatic Model Building in GEFCom 2017 Qualifying Match
This is an incremental improvement for participants in energy forecasting competitions, demonstrating automated strategies.
The team tackled the problem of automatic model building for time series in the GEFCom 2017 competition by using the Tangent Information Modeller (TIM) with historical temperature shuffling, resulting in winning the competition, and they showed that a fully automated version would also win.
The Tangent Works team participated in GEFCom 2017 to test its automatic model building strategy for time series known as Tangent Information Modeller (TIM). Model building using TIM combined with historical temperature shuffling resulted in winning the competition. This strategy involved one remaining degree of freedom, a decision on using a trend variable. This paper describes our modelling efforts in the competition, and furthermore outlines a fully automated scenario where the decision on using the trend variable is handled by TIM. The results show that such a setup would also win the competition.