Combining time-series and textual data for taxi demand prediction in event areas: a deep learning approach
This addresses the problem of improving transportation efficiency for urban planners and taxi services, but it is incremental as it applies existing fusion techniques to a specific domain.
The paper tackled taxi demand prediction in event areas by proposing deep learning architectures that combine time-series and textual data, resulting in significantly reduced forecast errors using New York taxi data.
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.