Telescope: An Automatic Feature Extraction and Transformation Approach for Time Series Forecasting on a Level-Playing Field

One central problem of machine learning is the inherent limitation to predict only what has been learned —stationarity. Any time series property that eludes stationarity poses a challenge for the proper model building. Furthermore, existing forecasting methods lack reliable forecast accuracy and time-to-result if not applied in their sweet spot. In this paper, we propose a fully automated machine learning-based forecasting approach. Our Telescope approach extracts and transforms features from an input time series and uses them to generate an optimized forecast model. In a broad competition including the latest hybrid forecasters, established statistical, and machine learning-based methods, our Telescope approach shows the best forecast accuracy coupled with a lower and reliable time-to-result.

[1]  R. Clemen.  Combining forecasts: A review and annotated bibliography , 1989 .

[2]  Víctor M. Guerrero.  Time‐series analysis supported by power transformations , 1993 .

[3]  Jianhua Zhang,et al.  A hybrid forecasting model with parameter optimization for short-term load forecasting of micro-grids , 2014 .

[4]  Benjamin Letham,et al.  Forecasting at Scale , 2018, PeerJ Prepr..

[5]  Rob J Hyndman,et al.  A state space framework for automatic forecasting using exponential smoothing methods , 2002 .

[6]  Richard A. Davis,et al.  Introduction to time series and forecasting , 1998 .

[7]  Tie-Yan Liu,et al.  LightGBM: A Highly Efficient Gradient Boosting Decision Tree , 2017, NIPS.

[8]  P. Young,et al.  Time series analysis, forecasting and control , 1972, IEEE Transactions on Automatic Control.

[9]  Rob J Hyndman,et al.  Forecasting Time Series With Complex Seasonal Patterns Using Exponential Smoothing , 2011 .

[10]  R. K. Agrawal,et al.  An Introductory Study on Time Series Modeling and Forecasting , 2013, ArXiv.

[11]  George Athanasopoulos,et al.  Forecasting: principles and practice , 2013 .

[12]  Nikolas Herbst,et al.  Autonomic Forecasting Method Selection: Examination and Ways Ahead , 2019, 2019 IEEE International Conference on Autonomic Computing (ICAC).

[13]  Evangelos Spiliotis,et al.  Statistical and Machine Learning forecasting methods: Concerns and ways forward , 2018, PloS one.

[14]  Luís Torgo,et al.  Arbitrated Ensemble for Time Series Forecasting , 2017, ECML/PKDD.

[15]  D. Cox,et al.  An Analysis of Transformations , 1964 .

[16]  Motoaki Kawanabe,et al.  Machine Learning in Non-Stationary Environments - Introduction to Covariate Shift Adaptation , 2012, Adaptive computation and machine learning.

[17]  Rob J. Hyndman,et al.  Meta‐learning how to forecast time series , 2023, Journal of Forecasting.

[18]  Irma J. Terpenning,et al.  STL : A Seasonal-Trend Decomposition Procedure Based on Loess , 1990 .

[19]  David H. Wolpert,et al.  No free lunch theorems for optimization , 1997, IEEE Trans. Evol. Comput..

[20]  Rob J Hyndman,et al.  Another look at measures of forecast accuracy , 2006 .

[21]  Carlos Soares,et al.  Machine Learning vs Statistical Methods for Time Series Forecasting: Size Matters , 2019, ArXiv.

[22]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[23]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[24]  Fotios Petropoulos,et al.  forecast: Forecasting functions for time series and linear models , 2018 .