We were given the Quora Duplicate Question pair Dataset. In that dataset, there were two question columns and a third column named "is_duplicate," which indicated whether the questions in both question columns were the same or not. If they were the same, the output was 1; otherwise, it was 0. I employed ML models such as Random Forest and XGBCLASSIFIER after preprocessing the given Quora Duplicate Question pair dataset. Additionally, I utilized LSTM with GloVe embedding, and finally, I employed the fine-tuned BERT model. Among all these approaches, the ML model delivered the best performance.