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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Spatio-temporal information is used for driving a plethora of intelligenttransportation, smart-city, and crowd-sensing applications. Since data is nowconsidered a valuable production factor, data marketplaces have appeared tohelp individuals and enterprises bring it to market to satisfy the ever-growingdemand. In such marketplaces, several sources may need to combine their data inorder to meet the requirements of different applications. In this paper westudy the problem of estimating the relative value of different spatio-temporaldatasets combined in wholesale and retail marketplaces for the purpose ofpredicting demand in metropolitan areas. Using as case studies large datasetsof taxi rides from Chicago and New York, we ask questions such as "When does itmake sense for different taxi companies to combine their data?", and "Howshould different companies be compensated for the data that they share?". Wethen turn our attention to the even harder problem of establishing the relativevalue of the data brought to retail marketplaces by individual drivers.Overall, we show that simplistic but popular approaches for estimating therelative value of data, such as using volume, or the ``leave-one-out''heuristic, are inaccurate. Instead, more complex notions of value fromeconomics and game-theory, such as the Shapley value need to be employed if onewishes to capture the complex effects of mixing different datasets on theaccuracy of forecasting algorithms. Applying the Shapley value to largedatasets from many sources is, of course, computationally challenging. Weresort to structured sampling and manage to compute accurately the importanceof thousands of data sources. We show that the relative value of the data heldby different taxi companies and drivers may differ substantially, and that itsrelative ranking may change from district to district within a metropolitanarea.

Computing the Relative Value of Spatio-Temporal Data in Wholesale and Retail Data Marketplaces