Dropping forward-backward algorithms for feature selection

In this era of big data, feature selection techniques, which have long been proven to simplify the model, makes the model more comprehensible, speed up the process of learning, have become more and more important. Among many developed methods, forward, backward and stepwise feature selection regression remained widely used due to their simplicity and efficiency. However, they are not sufficient enough when it comes to large datasets. In this paper, we analyze the issues associated with those approaches and introduce a novel algorithm that may boost the speed up to 65.77% compared to stepwise while maintaining good performance compared to stepwise selection in terms of the number of selected features and error rates.