Interpretable Time-Series Traffic-Volume Modelling for Construction Logistics Management

<p dir="ltr">This dataset contains the derived analytical sample used in the study <i>“Interpretable Time-Series Traffic-Volume Modelling for Construction Logistics Management: A Proposed Decision-Translation Framework.”</i> It was prepared from the publicly available UCI Metro Interstate Traffic Volume dataset (Hogue, 2019; <a href="" target="_new" rel="noopener">doi.org/10.24432/C5X60B</a>).</p><p dir="ltr">The original dataset contains 48,204 hourly observations from a westbound I-94 freeway segment in the Minneapolis–St.

Paul metropolitan area, covering October 2012 to September 2018. The shared analytical dataset contains 40,538 chronologically ordered observations after the application of predefined cleaning and feature-engineering procedures, including removal of duplicate timestamps, physically implausible weather records, zero traffic-volume records, and observations without the required autoregressive lag values.</p><p dir="ltr">Variables include hourly traffic volume, temporal features, lagged traffic-volume predictors, meteorological variables, and encoded weather categories.