Skip to main content
Data / ML

M4 Forecasting Competition: Introducing a New Hybrid ES-RNN Model

25 June 2018 / Global
Featured image for M4 Forecasting Competition: Introducing a New Hybrid ES-RNN Model
Table 1. M4 time series spanned various sizes across a broad range.
Figure 1. Feature extraction by rolling windows. The smooth curve depicts level.
Figure 2. In all cases, dilated NNs were used but exact configuration differed; three examples are shown.
Slawek Smyl

Slawek Smyl

Slawek Smyl is a forecasting expert working at Uber. Slawek has ranked highly in international forecasting competitions. For example, he won the M4 Forecasting competition (2018) and the Computational Intelligence in Forecasting International Time Series Competition 2016 using recurrent neural networks. Slawek also built a number of statistical time series algorithms that surpass all published results on M3 time series competition data set using Markov Chain Monte Carlo (R, Stan).

Jai Ranganathan

Jai Ranganathan

Jai Ranganthan is a director of product management at Uber.

Andrea Pasqua

Andrea Pasqua

Andrea Pasqua is a data science manager overseeing our Intelligent Decisions Systems team at Uber.

Posted by Slawek Smyl, Jai Ranganathan, Andrea Pasqua

Category: