A Comparative Study Of Multi-Relational Decision Tree Learning Algorithm
Vaibhav Tripathy · International journal of scientific and technology research · 2013
This paper provides a comparative study of the working and implementation of multi relational decision tree learning algorithm with that of MRDTL-2, which works on the theory initially proposed by Knobbe et al. This paper also outlines some of the shortcomings of MRDTL viz. calculation speed, accuracy and most importantly handling of missing values. We had used some of the real world data sets from various data mining competition and performed a graphical comparison for the aforementioned two approaches. Results from the experiments signify that MRDTL-2 is convincingly more efficient approach than its predecessor.