A Clustering Approach to Identify High-Risk Taxi Drivers Based on Self-Reported Driving Behavior

<table class="table-group" id="tab10"><tr><td><table class="table"><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr class="thead"><td class="align_left">Cluster</td><td class="align_center"><i>N</i> of drivers</td><td class="align_center"><i>N</i> of correct predictions</td><td class="align_center">% of correct predictions</td></tr><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr><td class="align_left">Low-risk drivers</td><td class="align_center">366</td><td class="align_center">310</td><td class="align_center">84.6</td></tr><tr><td class="align_left">High/Medium-risk drivers</td><td class="align_center">182</td><td class="align_center">135</td><td class="align_center">74.1</td></tr><tr class="table-tr"><td colspan="4"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>The correctness ratio of the second model.</div>

Journal of Advanced Transportation

tab10

Table 10

Table 10: A Clustering Approach to Identify High-Risk Taxi Drivers Based on Self-Reported Driving Behavior 