One of the challenges faced by research was the unavailability of reliable training datasets. In fact this challenge faces any researcher in the field. However, although plenty of articles about predicting phishing websites have been disseminated these days, no reliable training dataset has been published publically, may be because there is no agreement in literature on the definitive features that characterize phishing webpages, hence it is difficult to shape a dataset that covers all possible features.
In this notebook a ML model is being built in order to rightfully identify and classify Phishing websites
Data from https://www.openml.org/d/4534