English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Short-term demand forecasting for on-demand ride-hailing services is one ofthe fundamental issues in intelligent transportation systems. However, previoustravel demand forecasting research predominantly focused on improvingprediction accuracy, ignoring fairness issues such as systematicunderestimations of travel demand in disadvantaged neighborhoods. This studyinvestigates how to measure, evaluate, and enhance prediction fairness betweendisadvantaged and privileged communities in spatial-temporal demand forecastingof ride-hailing services. A two-pronged approach is taken to reduce the demandprediction bias. First, we develop a novel deep learning model architecture,named socially aware neural network (SA-Net), to integrate thesocio-demographics and ridership information for fair demand prediction throughan innovative socially-aware convolution operation. Second, we propose abias-mitigation regularization method to mitigate the mean percentageprediction error gap between different groups. The experimental results,validated on the real-world Chicago Transportation Network Company (TNC) data,show that the de-biasing SA-Net can achieve better predictive performance inboth prediction accuracy and fairness. Specifically, the SA-Net improvesprediction accuracy for both the disadvantaged and privileged groups comparedwith the state-of-the-art models. When coupled with the bias mitigationregularization method, the de-biasing SA-Net effectively bridges the meanpercentage prediction error gap between the disadvantaged and privilegedgroups, and also protects the disadvantaged regions against systematicunderestimation of TNC demand. Our proposed de-biasing method can be adopted inmany existing short-term travel demand estimation models, and can be utilizedfor various other spatial-temporal prediction tasks such as crime incidentspredictions.

Fairness-enhancing deep learning for ride-hailing demand prediction