Tourism forecasting competition data as an R package

The data used in the tourism forecasting competition, discussed in Athanasopoulos et al (2011), have been made available in the Tcomp package for R. The objects are of the same format as for Mcomp package containing data from the M1 and M3 competitions.

Thanks to Peter Ellis for putting the package together. He has also produced a nice blog post about it.

GEFCom2017: Hierarchical Probabilistic Load Forecasting

After the great success of the previous two energy forecasting competitions we have run (GEFCom2012 and GEFCom2014), we are holding another one, this time focused on hierarchical probabilistic load forecasting. Check out all the details over on Tao Hong’s blog.

The previous GEFComs have led to some major advances in forecasting methodology, available via IJF papers by the winning teams. I expect similar developments to arise out of this competition. Winners get to present their work in Cairns, Australia at ISEA2017.

Come to Melbourne, even if not to Monash

The University of Melbourne is advertising for a “Professor in Statistics (Data Science)”. Melbourne (the city) is fast becoming a vibrant centre for data science and applied statistics, with more than 4700 people signed up for the Data Science Meetup Group, a thriving start-up scene, the group at Monash Business School (including Di Cook and me), and the Monash Centre for Data Science (including Geoff Webb and Wray Buntine). Not to mention that Melbourne is a wonderful place to live, having won the “World’s most liveable city” award from the Economist for the last 6 years in a row.

Actually, the Uni of Melbourne currently has two professorships on offer — the other being the Peter Hall Chair in Mathematical Statistics. (Not sure that anyone would actually feel qualified to have a job with that title!)

So any professors of statistics out there looking for a new challenge, please consider coming to Melbourne. We’ll even invite you to visit us from time to time at Monash.


Forecast intervals for aggregates

A common problem is to forecast the aggregate of several time periods of data, using a model fitted to the disaggregated data. For example, you may have monthly data but wish to forecast the total for the next year. Or you may have weekly data, and want to forecast the total for the next four weeks.

If the point forecasts are means, then adding them up will give a good estimate of the total. But prediction intervals are more tricky due to the correlations between forecast errors.

Continue reading →