Isa Nakhaei - Assosiate professor Tarbiat Moderess university
Arezoo Atighehchian - Phd Candidates Tarbiat Modaress University
Hoda davarzani Tehrani - Phd Candidates Tarbiat Modaress University
Nasim Ghanbar - Phd Candidates Tarbiat Modaress University

This research applies data mining techniques to discover the relationship between motor vehicle accidents and the recorded data about the accident by the police. The data used in this research is obtained from the traffic police’s accident database, focused on the third traffic zone in Tehran from years 2004 to 2005. The data are first clustered using the K-mean method. Then, the patterns and rules of the data are explored and using this descriptions, some refinements in behaviors are proposed. Findings – Some refinements in 3 level ( for citizens, urban police and top level policy makers) are proposed based on the results. Using this method, regardless of the constraints of this study shows that it may provide useful knowledge about the safety of roads. This is one of few research papers utilizing data mining techniques to explore the motor vehicle crashes and related factors.

Urban Transportation, Data Mining, Incident Management, safety