Engineering-on-Data

This project uses a pre-trained ResNet50 model from the FastAI library to detect pneumonia in chest X-rays. The dataset which is available on kaggle is used for training the model which classifies the chest xray as NORMAL, VIRAL or BACTERIAL and this project is deployed on Flask

Welcome to LookSense, an innovative project delving into facial expression recognition using deep convolutional neural networks. Trained on the FER-2013 dataset from the International Conference on Machine Learning (ICML), LookSense accurately categorizes emotions in grayscale images, offering a robust tool for understanding and interpreting human

Sentiment Analysis for Consumer Behavior Prediction

In the given list of locations of customers who frequently order Pizza we want to find out optimal locations of Pizza Parlours where they should be opened.

This repository presents a credit card fraud detection system utilizing a Logistic Regression model trained on a dataset of 284,807 transactions with significant class imbalance. After employing under-sampling for balance, the model achieves a test accuracy of around 93.40%, showcasing the effectiveness of ML in identifying fraudulent transactions.

This repository containing machine learning projects, including data preprocessing, model training, and evaluation. It includes well-documented code, datasets, and visualizations for various ML algorithms. The goal is to build and optimize predictive models using real-world data.

Titanic Classification project is a beginner friendly Data science project! This project aims to predict whether a passenger on the Titanic survived or not based on various features such as age, gender, class, and more.