Multi-task learning of time series and its application to the travel demand

We address the problem of modeling and prediction of a set of temporal events in the context of intelligent transportation systems. To leverage the information shared by different events, we propose a multi-task learning framework. We develop a support vector regression model for joint learning of mutually dependent time series. It is the regularization-based multi-task learning previously developed for the classification case and extended to time series. We discuss the relatedness of observed time series and first deploy the dynamic time warping distance measure to identify groups of similar series. Then we take into account both time and scale warping and propose to align multiple time series by inferring their common latent representation. We test the proposed models on the problem of travel demand prediction in Nancy (France) public transport system and analyze the benefits of multi-task learning.

[1]  Rich Caruana,et al.  Multitask Learning , 1997, Machine-mediated learning.

[2]  Stefan Rüping,et al.  SVM Kernels for Time Series Analysis , 2001 .

[3]  Yan Liu,et al.  Granger Causality for Time-Series Anomaly Detection , 2012, 2012 IEEE 12th International Conference on Data Mining.

[4]  Sophocles J. Orfanidis,et al.  Optimum Signal Processing: An Introduction , 1988 .

[5]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[6]  Terence C. Mills,et al.  Time series techniques for economists , 1990 .

[7]  Eamonn J. Keogh,et al.  Searching and Mining Trillions of Time Series Subsequences under Dynamic Time Warping , 2012, KDD.

[8]  Sanjay Chawla,et al.  Inferring the Root Cause in Road Traffic Anomalies , 2012, 2012 IEEE 12th International Conference on Data Mining.

[9]  Man-Chun Tan,et al.  An Aggregation Approach to Short-Term Traffic Flow Prediction , 2009, IEEE Transactions on Intelligent Transportation Systems.

[10]  Edwin V. Bonilla,et al.  Multi-task Gaussian Process Prediction , 2007, NIPS.

[11]  Paolo Frasconi,et al.  Short-Term Traffic Flow Forecasting: An Experimental Comparison of Time-Series Analysis and Supervised Learning , 2013, IEEE Transactions on Intelligent Transportation Systems.

[12]  Massimiliano Pontil,et al.  Regularized multi--task learning , 2004, KDD.

[13]  L. Baum,et al.  A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains , 1970 .

[14]  Radford M. Neal,et al.  Multiple Alignment of Continuous Time Series , 2004, NIPS.

[15]  Tak-Chung Fu,et al.  A review on time series data mining , 2011, Eng. Appl. Artif. Intell..

[16]  Ravi Sankar,et al.  Time Series Prediction Using Support Vector Machines: A Survey , 2009, IEEE Computational Intelligence Magazine.

[17]  Pavel Senin,et al.  Dynamic Time Warping Algorithm Review , 2008 .

[18]  Boris Chidlovskii,et al.  Learning Multiple Tasks with Boosted Decision Trees , 2012, ECML/PKDD.

[19]  Luis Gómez-Chova,et al.  Multitask Remote Sensing Data Classification , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[20]  Gunnar Rätsch,et al.  Predicting Time Series with Support Vector Machines , 1997, ICANN.