Performed comprehensive exploratory data analysis and data cleaning on a real-world marketing dataset from FreshDirect to uncover customer behavior patterns and business insights. The project involved handling complex missing data, transforming currency variables, and imputing demographic information using segment-based approaches. Key analyses included customer segmentation, income and spending patterns, loyalty behavior, promotion usage, and delivery service adoption. Statistical methods and visualizations were applied to evaluate relationships such as income vs. orders, gender vs. sales, and customer tenure vs. loyalty. The findings highlight key drivers of customer value, including the dominance of frequent shoppers, the impact of DeliveryPass on revenue, and behavioral differences across income and age groups, providing actionable insights for targeted marketing strategies.

This project presents a comprehensive survival analysis of the rats dataset using non-parametric, semi-parametric, and parametric methods. It integrates Kaplan–Meier and Nelson–Aalen estimators, hypothesis testing, and Cox proportional hazards models to evaluate treatment and sex effects on tumour development. The study further assesses model assumptions, performs diagnostics, and refines models to address violations, providing a robust comparison of survival modelling approaches and their practical interpretation in biomedical research.

This project conducts a comprehensive survival analysis of a rats dataset to investigate factors influencing survival time. It applies both non-parametric and parametric methods, including Kaplan–Meier estimation, Cox proportional hazards models, and accelerated failure time (AFT) models. The analysis evaluates the effects of treatment and sex on survival while accounting for clustering within litters, and compares different modeling approaches to identify the most appropriate framework for describing survival patterns.