Gender Recognition of Bangla Names Using Deep Learning Approaches

The name of individuals has a specific meaning and great significance. Individuals’ names generally have substantial gender differences, explicitly, Bengali usually solid sexual identity. We can determine if stranger is man or woman based on their with remarkably suitable precision. In this research, we primarily conducted thorough investigation into prediction person’s using DL-based methods. While various techniques been explored for the English language, there little progress in language. address gap by presenting large-scale experiment 2030 Bangladeshi unique names. used both convolutional neural network (CNN)- recurrent (RNN)-based deep learning methods to infer from presented one-dimensional CNN (Conv1D), simple long short-term memory (LSTM), bidirectional LSTM, stacked combined Conv1D LSTM-based models evaluated performance each scheme our own dataset. Experimental results are analyzed basis accuracy, precision, recall, F1-score, ROC AUC score, loss metrics. evaluative show that outperforms 91.18% which likely improve as size training data grows.