Rank Position Forecasting in Car Racing

Forecasting is challenging since uncertainty resulted from exogenous factors exists. This work investigates the rank position forecasting problem in car racing, which predicts the rank positions at the future laps for cars. Among the many factors that bring changes to the rank positions, pit stops are critical but irregular and rare. We found existing methods, including statistical models, machine learning regression models, and state-of-the-art deep forecasting model based on encoder-decoder architecture, all have limitations in the forecasting. By elaborative analysis of pit stops events, we propose a deep model, RankNet, with the cause effects decomposition that modeling the rank position sequence and pit stop events separately. It also incorporates probabilistic forecasting to model the uncertainty inside each sub-model. Through extensive experiments, RankNet demonstrates a strong performance improvement over the baselines, e.g., MAE improves more than 10% consistently, and is also more stable when adapting to unseen new data. Details of model optimization, performance profiling are presented. It is promising to provide useful forecasting tools for the car racing analysis and shine a light on solutions to similar challenging issues in general forecasting problems.

[1]  Tim Januschowski,et al.  Deep Factors for Forecasting , 2019, ICML.

[2]  Bin Wang,et al.  Deep Uncertainty Quantification: A Machine Learning Approach for Weather Forecasting , 2018, KDD.

[3]  Matthias W. Seeger,et al.  Bayesian Intermittent Demand Forecasting for Large Inventories , 2016, NIPS.

[4]  Syama Sundar Rangapuram,et al.  GluonTS: Probabilistic Time Series Models in Python , 2019, ArXiv.

[5]  Ugur Demiryurek,et al.  Deep Learning: A Generic Approach for Extreme Condition Traffic Forecasting , 2017, SDM.

[6]  Yike Guo,et al.  Deep Sequence Learning with Auxiliary Information for Traffic Prediction , 2018, KDD.

[7]  Xiangnan He,et al.  Modeling Extreme Events in Time Series Prediction , 2019, KDD.

[8]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[9]  Nicolas Chapados,et al.  N-BEATS: Neural basis expansion analysis for interpretable time series forecasting , 2019, ICLR.

[10]  Ming Shao,et al.  CTC-Attention based Non-Parametric Inference Modeling for Clinical State Progression , 2019, 2019 IEEE International Conference on Big Data (Big Data).

[11]  Naren Ramakrishnan,et al.  EpiDeep: Exploiting Embeddings for Epidemic Forecasting , 2019, KDD.

[12]  Slawek Smyl,et al.  A hybrid method of exponential smoothing and recurrent neural networks for time series forecasting , 2020, International Journal of Forecasting.

[13]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[14]  Valentin Flunkert,et al.  DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks , 2017, International Journal of Forecasting.

[15]  Phil Blunsom,et al.  Optimizing Performance of Recurrent Neural Networks on GPUs , 2016, ArXiv.

[16]  Matthias W. Seeger,et al.  Deep State Space Models for Time Series Forecasting , 2018, NeurIPS.

[17]  J Bekker,et al.  Planning Formula One race strategies using discrete-event simulation , 2009, J. Oper. Res. Soc..

[18]  Zoubin Ghahramani,et al.  Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning , 2015, ICML.

[19]  Theja Tulabandhula.  Interactions between learning and decision making , 2017, SIGAI.

[20]  Kevin Leyton-Brown,et al.  Deep IV: A Flexible Approach for Counterfactual Prediction , 2017, ICML.

[21]  Alexander Heilmeier,et al.  A Race Simulation for Strategy Decisions in Circuit Motorsports , 2018, 2018 21st International Conference on Intelligent Transportation Systems (ITSC).

[22]  Holger Kantz,et al.  Dynamical Interpretation of Extreme Events: Predictability and Predictions , 2006 .

[23]  Cynthia Rudin,et al.  Tire Changes, Fresh Air, and Yellow Flags: Challenges in Predictive Analytics for Professional Racing , 2014, Big Data.

[24]  Wenhu Chen,et al.  Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting , 2019, NeurIPS.

[25]  Ponnuthurai Nagaratnam Suganthan,et al.  Empirical Mode Decomposition based ensemble deep learning for load demand time series forecasting , 2017, Appl. Soft Comput..

[26]  Mihaela van der Schaar,et al.  Deep Counterfactual Networks with Propensity-Dropout , 2017, ArXiv.

[27]  Christopher Ledesma Weisen Choo.  Real-time decision making in motorsports : analytics for improving professional car race strategy , 2015 .

[28]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[29]  J. Yosinski,et al.  Time-series Extreme Event Forecasting with Neural Networks at Uber , 2017 .