Forecasting with time series imaging

Abstract

Feature-based time series representations have attracted substantial attention in a wide range of time series analysis methods. Recently, the use of time series features for forecast model averaging has been an emerging research focus in the forecasting community. Nonetheless, most of the existing approaches depend on the manual choice of an appropriate set of features. Exploiting machine learning methods to extract features from time series automatically becomes crucial in state-of-the-art time series analysis. In this paper, we introduce an automated approach to extract time series features based on time series imaging. We first transform time series into recurrence plots, from which local features can be extracted using computer vision algorithms. The extracted features are used for forecast model averaging. Our experiments show that forecasting based on automatically extracted features, with less human intervention and a more comprehensive view of the raw time series data, yields highly comparable performances with the best methods in the largest forecasting competition dataset (M4) and outperforms the top methods in the Tourism forecasting competition dataset.

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• XGBoost: A Scalable Tree Boosting System
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• CNN Features off-the-shelf: an Astounding Baseline for Recognition
• Imaging Time-Series to Improve Classification and Imputation
• Highly comparative time-series analysis: The empirical structure of time series and their methods
• Highly comparative feature-based time-series classification
• Bag-of-Words Representation for Biomedical Time Series Classification
• GRATIS: GeneRAting TIme Series with diverse and controllable characteristics
• FFORMPP: Feature-based forecast model performance prediction

Cited by in corpus (10)

• Review of automated time series forecasting pipelines
• Distributed ARIMA Models for Ultra-long Time Series
• Trends in recurrence analysis of dynamical systems
• FFORMPP: Feature-based forecast model performance prediction
• Forecasting: theory and practice
• Predicting the Future is like Completing a Painting!
• Visual Time Series Forecasting: An Image-driven Approach
• Deep Video Prediction for Time Series Forecasting
• Forecast with Forecasts: Diversity Matters
• Identification of the nature of dynamical systems with recurrence plots and convolution neural networks: A preliminary test