There are many mlpack methods that have been added since the previous benchmarking system was build and they need to be benchmarked. These include ANN, Decision Trees, Hoeffding Tree and more. There are many Machine Learning libraries like mrtp,annoy, Tensorflow, spark-Mllib, astroML in Python and libraries like CARET, randomForest, e1071,etc in R and dlib-ml in C++ and Accord.Net also which have not been benchmarked. There are some implementations in sklearn which need to be upgraded to add more options and some need a change in the value of the default parameters to support the latest version of sklearn. So if chosen to work on this project my aim would be to implement Machine Learning algorithms in some of the libraries not benchmarked as well as upgrade the current codes to support latest version of these libraries.