Jaunel Ansari's repositories
CNN-Image-Classifier
A Image classification CNN model with more than 85% accuracy. An interactive API is been designed using flask framework for better user experience. Techniques like batch normalization, dropouts is used for improved accuracy.
Content-Based---Movie-Recommender-System
This project is a Recommendation based project. Similar movies will be recommended based upon the content of the movie. I have used ML algorithm & BOW technique of NLP for our model. An interactive web page is also designed using streamlit library for next level user experience.
Face-Recognition-using-opencv
This is a computer vision based project, quite useful in daily life. I have used face_recognition & cv2 library for building this project.
Fraudulent-Transaction-classificationTask
Classification model to detect fraudulent transactions in an imbalanced dataset. The best model achieved high performance metrics, including an accuracy of 99.95% & precision of 0.97 on the testing set. It also covers key data preprocessing steps, including outlier removal using the Interquartile Range (IQR) method, to improve model performance
Live-detection-of-Sunglasses
Developed CNN model with 93% validation accuracy using techniques like Dropouts & Batch Normalization. Using haar cascade of Computer Vision It is then used to detect sunglasses on real time basis
ML-Classification--Customer-Churn-Prediction
Developed Machine Learning Model to categorize customer with more than 91% accuracy and 88% roc_auc score. Best ML model is selected after evaluating all performance metric like Accuracy, Precision & recall