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

The estimation of the amount of uncertainty featured by predictive machinelearning models has acquired a great momentum in recent years. Uncertaintyestimation provides the user with augmented information about the model'sconfidence in its predicted outcome. Despite the inherent utility of thisinformation for the trustworthiness of the user, there is a thin consensusaround the different types of uncertainty that one can gauge in machinelearning models and the suitability of different techniques that can be used toquantify the uncertainty of a specific model. This subject is mostly nonexistent within the traffic modeling domain, even though the measurement of theconfidence associated to traffic forecasts can favor significantly theiractionability in practical traffic management systems. This work aims to coverthis lack of research by reviewing different techniques and metrics ofuncertainty available in the literature, and by critically discussing howconfidence levels computed for traffic forecasting models can be helpful forresearchers and practitioners working in this research area. To shed light withempirical evidence, this critical discussion is further informed byexperimental results produced by different uncertainty estimation techniquesover real traffic data collected in Madrid (Spain), rendering a generaloverview of the benefits and caveats of every technique, how they can becompared to each other, and how the measured uncertainty decreases depending onthe amount, quality and diversity of data used to produce the forecasts.

Measuring the Confidence of Traffic Forecasting Models: Techniques, Experimental Comparison and Guidelines towards Their Actionability