/Ling-Gender

A Natural Language Processing model trained with over 1,00,000 (1 Lakh) names is used to predict a gender of a person based on the first name of the person.This model is created using Long Short Term Memory(LSTM) a variant of Recurrent Nueral Network which has training accuracy of 99.35% and tested over 11,000 samples with a test accuracy of 89.08% which is quite high in nlp for out of sample test cases.

Primary LanguageJupyter NotebookMIT LicenseMIT

Issues