By: Heroshi Joe Abejuela (Data Science Intern at CODSOFT)
This repository contains three key projects completed during my internship at CODSOFT. Each project applies various machine learning and statistical techniques to solve real-world problems. Below, you will find a brief description of each project along with links to the corresponding code and results. The full executive summaries of the projects are available for download here.
This project involves predicting product sales based on advertising expenditures across TV, radio, and newspapers. By applying linear regression, we explore the relationships between advertising channels and their impact on sales. The model was evaluated based on metrics such as Mean Squared Error and R-squared, providing insights into which advertising channel contributed most to sales.
- Linear Regression Model
- Model evaluation using MSE and R²
The Titanic survival prediction project uses machine learning algorithms to predict passenger survival during the Titanic disaster based on features like age, gender, and ticket class. We applied Logistic Regression, Random Forest, and Gradient Boosting models and compared their performance to identify the best-performing model.
- Logistic Regression, Random Forest, and Gradient Boosting
- Model evaluation using accuracy, F1-score, and Kappa score
This project focuses on detecting fraudulent credit card transactions from highly imbalanced datasets. Various machine learning models such as Logistic Regression and Random Forest were applied, along with data balancing techniques to enhance fraud detection. The models were evaluated on accuracy, F1-score, and ROC AUC.
- Logistic Regression, Random Forest
- Data balancing techniques (oversampling and undersampling)
- Model evaluation using ROC AUC
For any queries or feedback, feel free to reach out:
- Email: [email protected]