[Forum SIS] seminario Steven Scott in Bicocca 2/9

[fabio.bellini]

Cari colleghi, vi segnalo che il giorno venerdì 2 
settembre alle ore 17, presso la Aula Martini al piano 
interrato dell'edificio U6, Steven Scott, Director of 
Statistics Research at Google, terrà un seminario su

Predicting the Present with Bayesian Structural Time 
Series

This article describes a system for short term forecasting 
based on an ensemble prediction that averages over 
different combinations of predictors. The system combines 
a structural time series model for the target series with 
regression component capturing the contributions
of contemporaneous search query data. A spike-and-slab 
prior on the regression coefficients induces sparsity, 
dramatically reducing the size of the regression problem. 
Our system averages over potential contributions from a 
very large set of models and gives easily digested reports 
of which coefficients are likely to be important. We 
illustrate with applications to initial claims for 
unemployment benefits and to retail sales. Although our 
exposition focuses on using search engine data to forecast 
economic time series, the underlying statistical methods 
can be applied to more general short term forecasting with 
large numbers of contemporaneous predictors (joint work 
with Hal Varian).

L'evento è organizzato in collaborazione con Innovation 
Pub e sarà seguito da un piccolo rinfresco.
Sarà inoltre possibile seguire lo streaming su 
http://streaming.unimib.it/.