Abstract: Accident prediction has been in trend to provide alerts before accidents happen. Traffic on highways is monitored and lots of data is processed daily to predict probability of accidents based on highway conditions like road surface, light on highway, turns etc. In this paper to predict accident based on different queries and process this big data Hadoop has been used. It is found that execution time is very less on Hadoop as compared to sequential techniques.

Keywords: Data analysis, Hadoop, MapReduce, HDFS