Deep and Confident Prediction for Time Series at Uber

Zhu, Lingxue; Laptev, Nikolay

doi:10.1109/icdmw.2017.19

Cited by 266 publications

(189 citation statements)

References 11 publications

Supporting

Mentioning

189

Contrasting

Order By: Relevance

“…More speci cally, the rst component of the prediction network is an encoder-decoder structure with LSTM (Long-Short Term Memory) units [9], which can learn the hidden representation for each station to catch the temporal correlations in the bike ow history. en, by decomposing the prediction uncertainty into three parts: model uncertainty, model misspeci cation, and inherent noise [34] (details will be elaborated later), we further estimate the con dence interval of our station-level bike ow prediction, which can provide more information to the managers of bike sharing systems for decision making.…”

Section: Framework Overviewmentioning

confidence: 99%

“…Con dence Estimation: Next, we elaborate how to infer the uncertainty of our prediction, i.e., con dence interval based on the encoder-decoder prediction network. According to literature, the uncertainty of the prediction result can be divided into three parts: model uncertainty, model misspeci cation, and inherent noise [34] ( Figure 4).…”

Section: (Ii) Multi-graph Convolutionmentioning

confidence: 99%

See 1 more Smart Citation

Bike flow prediction with multi-graph convolutional networks

Chai

Wang

Yang

2018

Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems

202

114

View full text Add to dashboard Cite

One fundamental issue in managing bike sharing systems is the bike ow prediction. Due to the hardness of predicting the ow for a single station, recent research works o en predict the bike ow at cluster-level. While such studies gain satisfactory prediction accuracy, they cannot directly guide some ne-grained bike sharing system management issues at station-level. In this paper, we revisit the problem of the station-level bike ow prediction, aiming to boost the prediction accuracy leveraging the breakthroughs of deep learning techniques. We propose a new multi-graph convolutional neural network model to predict the bike ow at station-level, where the key novelty is viewing the bike sharing system from the graph perspective. More speci cally, we construct multiple interstation graphs for a bike sharing system. In each graph, nodes are stations, and edges are a certain type of relations between stations.en, multiple graphs are constructed to re ect heterogeneous relationships (e.g., distance, ride record correlation). A erward, we fuse the multiple graphs and then apply the convolutional layers on the fused graph to predict station-level future bike ow. In addition to the estimated bike ow value, our model also gives the prediction con dence interval so as to help the bike sharing system managers make decisions. Using New York City and Chicago bike sharing data for experiments, our model can outperform state-of-the-art station-level prediction models by reducing 25.1% and 17.0% of prediction error in New York City and Chicago, respectively.

show abstract

Section: Framework Overviewmentioning

confidence: 99%

Section: (Ii) Multi-graph Convolutionmentioning

confidence: 99%

Bike flow prediction with multi-graph convolutional networks

Chai

Wang

Yang

2018

Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems

202

114

View full text Add to dashboard Cite

show abstract

“…It is precisely this success of deep learning in handling different types of data, such as images, audio and text from different domains, that makes it particularly well-suited for the data fusion problem of combining time-series and textual data. Indeed, deep learning has already been shown to be able to outperform traditional approaches for taxi demand forecasting and achieve new state-of-the-art results [9,10]. However, none of the previous approaches explore Web data about events, particularly in the form of unstructured text, in order to develop more accurate demand forecasting models.…”

Section: Introductionmentioning

confidence: 99%

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

2019

View full text Add to dashboard Cite

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.

show abstract

“…We plan to adapt the implementation of this method described in ref. [40] to provide rough estimates of model uncertainty associated with our emulated models.…”

Section: Resultsmentioning

confidence: 99%

Enabling immersive engagement in energy system models with deep learning

Bugbee

Bush

Gruchalla

et al. 2019

Statistical Analysis

View full text Add to dashboard Cite

Complex ensembles of energy simulation models have become significant components of renewable energy research in recent years. Often the significant computational cost, high‐dimensional structure, and other complexities hinder researchers from fully utilizing these data sources for knowledge building. Researchers at National Renewable Energy Laboratory have developed an immersive visualization workflow to dramatically improve user engagement and analysis capability through a combination of low‐dimensional structure analysis, deep learning, and custom visualization methods. We present case studies for two energy simulation platforms.

show abstract

Deep and Confident Prediction for Time Series at Uber

Cited by 266 publications

References 11 publications

Bike flow prediction with multi-graph convolutional networks

Bike flow prediction with multi-graph convolutional networks

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

Enabling immersive engagement in energy system models with deep learning

Contact Info

Product

Resources

About