The accuracy of extrapolation (time series) methods: Results of a forecasting competition

By Spyros Makridakis, A. Andersen, R. Carbone, Robert Fildes, M. Hibon, R. Lewandowski, J. Newton, Emanuel Parzen, Robert L. Winkler. 1982

Subfields: Evaluation & Benchmarks, Time-Series & Forecasting

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Evaluation & Benchmarks

In Time-Series & Forecasting

Citations in the corpus

N-BEATS: Neural basis expansion analysis for interpretable time series forecasting (2019, background): “M4 is the latest in an influential series of forecasting competitions organized by Spyros Makridakis since 1982 [21].”
Forecasting Across Time Series Databases using Long Short-Term Memory Networks on Groups of Similar Series (2017, methodology): “In particular, Nelson et al. (1999) compare the forecasts generated from NNs trained with deseasonalized data and non-deseasonalized data, using 68 monthly time series from the M-competition (Makridakis et al., 1982).”
FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting (2022, background): “(2020), they often suffer from problems such as gradient vanishing/exploding Pascanu et al. (2013), which limits their practical performance. Following the success of Transformer Vaswani et al. (2017) in the NLP and CV communities Vaswani et al.”
SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction (2021, methodology): “To make a fair comparison, we follow existing experimental settings, and use the same evaluation metrics as the original publications [17, 26, 40, 19] in each dataset.”
Soft computing system for bank performance prediction (2008, background): “[28] reported that combining several single models has become common practice in improving forecasting accuracy.”
25 years of time series forecasting (2006, methodology): “In the original M-competition (Makridakis et al., 1982), measures used included the MAPE, MSE,”
Forecasting model selection through out-of-sample rolling horizon weighted errors (2011, methodology): “Other studies on the levels of accuracy of forecasting models may be consulted at Reid (1975), Newbold & Granger (1974), Makridakis & Hibon (1979), (Makridakis et al., 1982), (Makridakis et al.”
Exponential Smoothing Model Selection for Forecasting (2006, background): “formed surprisingly well in forecasting competitions against more sophisticated approaches (Makridakis et al., 1982; Makridakis & Hibon, 2000).”
Forecasting Time Series With Complex Seasonal Patterns Using Exponential Smoothing (2011, methodology): “A TBATS model should be distinguished from two other 171 related (Proietti 2000) multiple source of error seasonal formulations presented by Hannan 172 et al. (1970) and Harvey (1989).”
Neural network forecasting for seasonal and trend time series (2005, background): “Results from the wellknown M-competition (Makridakis et al., 1982) suggest that data deseasonalization is an effective approach to seasonal time series modeling (Gardner and McKenzie, 1989).”