About Seemingly Complex/Challenging Dynamics in Forecasting: Illustrations Based on the NNGC1 Competition

In my previous Blog entries 1 and 2 on `forecasting competitions' I criticized the design of this year's tourn… ament (series/results are available on the net: I provide some of the results in 1) and I proposed directions for the design of future competitions (more user-focused and more practically relevant dynamic and fair designs allowing for human interaction/intervention).

  • In 1, I mentioned that NNGC1 relies on six data sets, A to F, ranging from yearly to hourly data, and that data sets A to D are `possibly' subject to fraude i.e. results could be obtained on the net.
  • Data set E is daily transportation data, namely car counts in Swiss tunnels. It might be difficult to obtain results for `non-initiated' but our institute works, among others, on (Swiss) traffic research projects and therefore I conjecture that I would have access to the data (although I did not verify formally).
  • However, I was unable to find results/data for the F-series (hourly US-airport and Paris-metro data) on the net. Therefore, I conjecture that NNGC1 restricted to data set F is `clean'.  

I decided to compute forecasts for the hourly data set F (even if the whole tournament is at risk of being  cancelled). Here is my motivation for this decision.    

“About Seemingly Complex/Challenging Dynamics in Forecasting: Illustrations Based on the NNGC1 Competition” vollständig lesen