Arabic name classification with Scikit-Learn and Pytorch

Posted on Fri 02 August 2019 in Machine Learning • Tagged with pytorch, skl, arabic

While working on arabic-vs-rest classification, I was curious how good out-of-the-box models perform with publicly available data, and then compare that with what we can achieve with internal data / features derived from millions of deliveries. We train Scikit-learn and Pytorch models for this classification task and achieve 90% prediction accuracy on publicly available data and out-of-the-box models, while internally 99% is achievable.

ROC curve

Continue reading