Insurance Claims Case Study

An in-depth data analytics case study evaluating an insurance policyholder dataset. The project demonstrates a complete analytical workflow: data hygiene, missing value treatment, exploratory data analysis (EDA), hypothesis formulation and testing, and visual communication of claim distributions and risk factors across policyholder segments.

• Performed comprehensive data audit, treating missing data and examining skewness in claim amount distributions.
• Conducted exploratory data analysis evaluating relationships between policyholder age, coverage type, location, and incident characteristics.
• Formulated statistical hypotheses to test whether claim amounts differed significantly across distinct demographic and coverage tiers.
• Built clear visualizations in Matplotlib and Seaborn to communicate variance, distribution shapes, and outlier clusters.
• Documented analytical findings with clear business interpretations regarding policy pricing and claim monitoring.

• Demonstrates structured application of Python analytical libraries for statistical inquiry and data cleansing.
• Applies formal parametric and non-parametric statistical tests to real-world business datasets.
• Translates statistical patterns into readable risk evaluation takeaways for business stakeholders.