Aggressive　driving　is　a　common　phenomenon　with　potential　safety　hazards.　The　primary　aim　of　this　study　is　to　investigate　the　relationship　among　driving　skill,　driving　behavior　and　driving　aggressiveness.　A　questionnaire　survey　consisting　of　three　subscales　was　conducted.　Subscale　1　is　about　driving　skill;　Subscale　2　is　associated　with　daily　driving　behavior,　while　Subscale　3　focuses　on　aggressive　driving　behaviors.　A　total　of　239　licensed　drivers　completed　the　survey.　The　five-factor　structure　was　extracted　by　factor　analysis.　Then,　the　correlation　analysis　method　was　used　to　explore　the　relationship　between　these　factors　and　drivers’　demographic　characteristics.　K-means　cluster　was　adopted　to　classify　drivers’　driving　aggressiveness　into　different　levels　using　behavioral　aggressiveness　and　emotional　aggressiveness　as　the　input　features.　Finally,　an　ordinal　regression　model　for　predicting　drivers’　driving　aggressiveness　levels　was　established　by　driving　skill　factor,　driving　behavior　factors　and　demographic　information.　The　results　indicated　that　more　experienced　drivers　(i.e.,　drivers　with　older　age,　longer　driving　years　or　professional　drivers)　reported　better　driving　behavior　and　less　aggression.　Male　drivers　were　more　aggressive　than　female　drivers,　especially　on　behavioral　aggressiveness.　In　addition,　drivers’　profession,　driving　years,　penalty　points,　errors/lapses　and　violations　can　be　used　to　predict　their　driving　aggressiveness　levels.　©　2020　Taylor　&　Francis　Group,　LLC　and　The　University　of　Tennessee.