Deep and Confident Prediction for Time Series at Uber

Abstract

Reliable uncertainty estimation for time series prediction is critical in many fields, including physics, biology, and manufacturing. At Uber, probabilistic time series forecasting is used for robust prediction of number of trips during special events, driver incentive allocation, as well as real-time anomaly detection across millions of metrics. Classical time series models are often used in conjunction with a probabilistic formulation for uncertainty estimation. However, such models are hard to tune, scale, and add exogenous variables to. Motivated by the recent resurgence of Long Short Term Memory networks, we propose a novel end-to-end Bayesian deep model that provides time series prediction along with uncertainty estimation. We provide detailed experiments of the proposed solution on completed trips data, and successfully apply it to large-scale time series anomaly detection at Uber.

To appear in DSBDA-2017 @ ICDM'17

References in corpus (7)

• Explaining and Harnessing Adversarial Examples
• Weight Uncertainty in Neural Networks
• Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
• Variational Bayesian Inference with Stochastic Search
• Dropout Inference in Bayesian Neural Networks with Alpha-divergences
• Nonlinear Systems Identification Using Deep Dynamic Neural Networks
• Concrete Dropout

Cited by in corpus (26)

• Deep Learning for Anomaly Detection: A Survey
• Recurrent Neural Networks for Time Series Forecasting
• Probabilistic Deep Learning to Quantify Uncertainty in Air Quality Forecasting
• On Last-Layer Algorithms for Classification: Decoupling Representation from Uncertainty Estimation
• Fast Transient Simulation of High-Speed Channels Using Recurrent Neural Network
• On Hallucination and Predictive Uncertainty in Conditional Language Generation
• Radflow: A Recurrent, Aggregated, and Decomposable Model for Networks of Time Series
• Probabilistic Time Series Forecasting with Implicit Quantile Networks
• Simultaneously Reconciled Quantile Forecasting of Hierarchically Related Time Series
• Bayesian Methods for Semi-supervised Text Annotation
• Uncertainty-aware Attention Graph Neural Network for Defending Adversarial Attacks
• Applying SVGD to Bayesian Neural Networks for Cyclical Time-Series Prediction and Inference
• SAFARI: Safe and Active Robot Imitation Learning with Imagination
• LSTM for Model-Based Anomaly Detection in Cyber-Physical Systems
• Deep Distribution Regression
• Uncertainty Intervals for Graph-based Spatio-Temporal Traffic Prediction
• Accurate and Reliable Forecasting using Stochastic Differential Equations
• Quantifying Uncertainty in Deep Spatiotemporal Forecasting
• Harnessing value from data science in business: ensuring explainability and fairness of solutions
• Simulation of Open Quantum Dynamics with Bootstrap-Based Long Short-Term Memory Recurrent Neural Network
• Predicting Requests in Large-Scale Online P2P Ridesharing
• A new approach to forecast service parts demand by integrating user preferences into multi-objective optimization
• Recoding latent sentence representations -- Dynamic gradient-based activation modification in RNNs
• Switching Scheme: A Novel Approach for Handling Incremental Concept Drift in Real-World Data Sets
• Nonparametric Online Learning Using Lipschitz Regularized Deep Neural Networks
• Uncertainty Surrogates for Deep Learning