This repository contains data science projects focused on developing and deploying machine learning models for various real-world applications. The primary use cases include predicting IPL cricket match outcomes, detecting credit card fraud, and analyzing sentiment in Flipkart product reviews.
- Developed a model to predict the outcome of IPL cricket matches based on historical match data.
- Applied data preprocessing techniques such as handling missing values, feature scaling, and encoding categorical variables.
- Used machine learning algorithms to train and evaluate the model for accuracy in match outcome predictions.
- Built a model to detect fraudulent credit card transactions using a highly imbalanced dataset.
- Implemented techniques like oversampling, undersampling, and SMOTE to address class imbalance.
- Applied various algorithms, including decision trees and logistic regression, to maximize detection performance.
- Analyzed product reviews from Flipkart to classify them as positive, negative, or neutral.
- Performed text preprocessing tasks such as tokenization, stemming, and stopword removal.
- Used machine learning models for sentiment classification and evaluated performance with precision, recall, and F1-score.