Paper: Efficient generation of time series with diverse and controllable characteristics

The explosion of time series data in recent years has brought a flourish of new time series analysis methods, for forecasting, clustering, classification and other tasks. The evaluation of these new methods requires a diverse collection of time series data to enable reliable comparisons against alternative approaches. We propose the use of mixture autoregressive (MAR) models to generate collections of time series with diverse features. We simulate sets of time series using MAR models and investigate the diversity and coverage of the simulated time series in a feature space. An efficient method is also proposed for generating new time series with controllable features by tuning the parameters of the MAR models. The simulated data based on our method can be used as evaluation tool for tasks such as time series classification and forecasting.

Workshop: The 2017 Beijing Workshop on Forecasting

I am organizing a workshop on forecasting to be held in Central University of Finance and Economics on Saturday, November 18, 2017. We have invited Professor Rob J Hyndman as keynote speaker. He will give four talks as part of the workshop. Other speakers are Junni Zhang for Peking University, Lei Song for, Hui Bu and Yanfei from Beihang University and I.

Full program details are available online.

Slides for the keynote speaker are available here.