Important notice: Due to the outbreak of the coronarvirus globally. We have to postpone this IIF workshop to 2021. We are sorry for this decision. We will keep this page updated please keep in tune.
August 2-4, 2020 TBA August 2 (Sunday): Registration August 3-4: Workshop
Venue: Ordos City, Inner Mongolia, China
Ordos is located in the southwestern part of the Inner Mongolia Autonomous Region. The Mongolian word “Ordos” means “many palaces.” Ordos has a long history and diverse cultures. Visiting the desert scenery, feeling the coolness of Lake Engebei, and then riding a camel to explore the Mongolian folk customs, all combine to create a very special and memorable experience. Ordos also hosts the Yellow River Canyon, where visitors can admire the cliffs and attractions on both banks. There are tourists attractions such as the Tomb of Genghis Khan, Whistling Dune Bay (Xiangshawan), Ordos Grasslands. See this page for other popular attractions around Ordos city.
Feature-based forecasting aims to use meta-learning to produce more accurate forecasts based on time series features. As early as the 1970s, Adam (1973) argued that the statistical characteristics of time series can be used to improve forecasting performances. Later literature supported this argument. For example: Collopy & Armstrong (1992) provided 99 rules using 18 features to combine four extrapolation methods to forecast annual economic and demographic time series; Adya et al. (2001) proposed an automatic way to identify time series features for rule-based forecasting; Petropoulos et al. (2014) proposed ‘horses for courses’ and measured the effects of seven time series features on the forecasting performances of 14 popular forecasting methods applied to the monthly data from the M3 competion; and Kang, Hyndman & Smith-Miles (2017) proposed to visualize the performances of different forecasting methods in a two-dimensional principal component feature space and provided a preliminary understanding of their relative performances.
Recently, three related feature-based algorithms have been developed with great success. The FFORMS (feature-based forecast model selection) framework by Talagala, Hyndman & Athanasopoulos (2018) uses a random forest to select the best forecasting method based on time series features. Remarkably, the related FFORMA (feature-based forecast model averaging) method proposed by Montero-Manso et al. (2019) won second position in the recent M4 competition. Third, Talagala, Li & Kang (2019) proposed the FFORMPP (feature-based forecast model performance prediction) framework that uses an efficient Bayesian multivariate surface regression approach to model forecast error as a function of features calculated from the time series.
Feature-based time series forecasting has shown great potential, while some key issues remain to be tackled including automatic feature extraction and selection, feature-based density forecasting, forecasting related time series with features, time series generation based on features, and minimum forecast model pools for forecast model averaging. The proposed workshop aims to bring people together with diverse expertise and facilitate new research collaborations.
The Chinese Academy of Sciences, Beihang University and Central University of Finance and Economics will jointly host the 2023 International Symposium on Forecasting. We believe this workshop will be a useful forerunner for the Chinese forecasting community, and also a good opportunity to bring together international forecasters and Chinese forecasters to form a potential collaborating network.
Organizers: Yanfei Kang, Feng Li and Rob Hyndman
- Yanfei Kang, Beihang University
- Feng Li, Central University of Finance and Economics
- Rob Hyndman, Monash University
- Rob Hyndman
- By air: Ordos Ejin Horo Airport
- Ordos Ejin Horo Airport is located at Ejin Horo of Ordos City, 18 km from the Kangbashi New District. The Ordos city can be connected by China’s domestic flights in most cities. See trip.com plan your trip.
- By high-speed train:
- Information available in 2021
Feng Li <firstname.lastname@example.org>