Combining time-series and textual data for taxi demand prediction in event areas: a deep learning approach

Abstract

Accurate time-series forecasting is vital for numerous areas of application such as transportation, energy, finance, economics, etc. However, while modern techniques are able to explore large sets of temporal data to build forecasting models, they typically neglect valuable information that is often available under the form of unstructured text. Although this data is in a radically different format, it often contains contextual explanations for many of the patterns that are observed in the temporal data. In this paper, we propose two deep learning architectures that leverage word embeddings, convolutional layers and attention mechanisms for combining text information with time-series data. We apply these approaches for the problem of taxi demand forecasting in event areas. Using publicly available taxi data from New York, we empirically show that by fusing these two complementary cross-modal sources of information, the proposed models are able to significantly reduce the error in the forecasts.

arXiv comment20 pages, 6 figures

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Deep Learning in Neural Networks: An Overview
• Deep and Confident Prediction for Time Series at Uber
• Describing Multimedia Content using Attention-based Encoder--Decoder Networks
• Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction

Cited by in corpus (12)

• How to Build a Graph-Based Deep Learning Architecture in Traffic Domain: A Survey
• Air taxi service for urban mobility: A critical review of recent developments, future challenges, and opportunities
• Deep Learning for Spatio-Temporal Data Mining: A Survey
• Rethinking travel behavior modeling representations through embeddings
• Integrating Physiological Time Series and Clinical Notes with Deep Learning for Improved ICU Mortality Prediction
• RTFN: A Robust Temporal Feature Network for Time Series Classification
• Graph Neural Lasso for Dynamic Network Regression
• Forecasting of the Montreal Subway Smart Card Entry Logs with Event Data
• Textual Data for Time Series Forecasting
• Multi-axis Attentive Prediction for Sparse EventData: An Application to Crime Prediction
• Modeling vehicular mobility patterns using recurrent neural networks
• Contextualized Spatial-Temporal Network for Taxi Origin-Destination Demand Prediction