Parallel decision tree with map reduce model for big data analytics

In today's world the modern generation applications such as social media application, web based application, big data analytics producing huge amount of data which brings up many challenges to data mining algorithm such as Decision Tree algorithms. First, as challenge is regarding volume of data which is growing terabyte to petabyte, larger dataset takes more time to build Decision Tree. Second, data not efficiently get stored in main memory we need to move it to secondary memory hence it will increase communication cost. Considering this challenges with traditional Decision Tree we have implemented the C4.5 which is latest Decision Tree algorithm with Map Reduce model which is suitable for parallel processing of big data. The algorithm is tested with big dataset of student alcohol consumption, experiments shows proposed algorithm is time saving and provides scalability.