The Insurance Risk & Claims Analysis Dashboard is an interactive Power BI project designed to analyze insurance policy distribution, claim exposure, and customer risk patterns across multiple demographic and vehicle-related dimensions.
This dashboard helps in understanding how insurance metrics such as total policies and total claim amount vary by factors like car use, car make, coverage zone, age group, car year, gender, education, and kids driving count.
The goal of this project was to transform raw insurance data into a clear, business-friendly dashboard that supports faster and better decision-making.
Insurance companies deal with a large volume of customer, vehicle, and claims data. But raw data alone does not clearly show:
- which customer segments hold the most policies
- which groups contribute more to overall claim amount
- how claims vary across vehicle and demographic categories
- where risk concentration may exist
Without an interactive dashboard, it becomes difficult for stakeholders to quickly identify patterns, monitor claim exposure, and evaluate segment-wise insurance performance.
The objective of this project was to build an interactive Power BI dashboard that can:
- monitor key insurance KPIs
- compare policy count and claim amount across multiple dimensions
- identify customer and vehicle segments with higher claim exposure
- support data-driven analysis for insurance risk monitoring
- present complex insurance data in a simple and visually effective format
The insurance dataset contained information related to policies, claims, customer demographics, vehicle details, and coverage-related attributes. Since the data had multiple dimensions, it was difficult to manually identify meaningful patterns and risk-heavy segments from raw records alone.
My task was to create a dashboard that could help analyze insurance performance from both policy volume and claim amount perspectives. The dashboard needed to provide a complete and easy-to-understand view of how insurance metrics change across customer and vehicle categories.
To complete this project, I:
- imported and prepared the insurance dataset in Power BI
- cleaned and structured the data for reporting
- created KPI cards for key business metrics
- designed an interactive dashboard with a professional dark theme
- added a dynamic measure selector to switch between:
- Total Policies
- Total Claim Amount
- built visuals to analyze data by:
- car use
- car make
- coverage zone
- age group
- car year
- education
- kids driving
- gender
- used multiple visual types such as:
- KPI cards
- donut charts
- bar charts
- area/line chart
- matrix table
- arranged the visuals in a way that makes the dashboard easy to read and business-friendly
The final dashboard transformed raw insurance data into meaningful visual insights. It allows users to quickly identify:
- high-policy concentration segments
- high-claim contribution groups
- demographic and vehicle-based patterns
- risk-related trends across customer categories
This project demonstrates my ability to work on data cleaning, dashboard design, KPI reporting, segmentation analysis, and business storytelling using Power BI.
The dashboard tracks the following top-level metrics:
- Total Policies: 37,542
- Total Claim Amount: $187.82M
- Average Claim Frequency: 0.5
- Average Claim Amount: 5.0K
It also includes gender-based policy distribution:
- Male: 18.7K
- Female: 18.8K
A measure selector allows the user to switch the dashboard analysis between:
- Total Policies
- Total Claim Amount
This makes the dashboard more flexible and interactive without needing separate pages.
The dashboard provides breakdowns across several important dimensions:
- Car Use
- Car Make
- Coverage Zone
- Age Group
- Car Year
- Kids Driving
- Education
- Gender
The dashboard uses a combination of KPI cards, donut charts, bar charts, trend charts, and matrix tables to present insurance insights in a clean and understandable way.
The report is designed with a dark-themed layout, clear sectioning, and consistent visual formatting to improve readability and presentation quality.
This dashboard helps answer important business questions such as:
- How many total insurance policies are there?
- What is the total claim amount?
- Which car use category contributes the most?
- Which car makes have higher policy or claim contribution?
- How are policies and claims distributed across age groups?
- How does insurance exposure vary by coverage zone?
- Is there any visible trend by car year?
- How do education and family-driving factors relate to claim amount?
The dashboard compares insurance performance by vehicle usage type, such as:
- Private
- Commercial
This helps identify whether a specific usage category contributes more to policy count or total claim amount.
A category-wise comparison of car manufacturers helps identify which car brands have stronger contribution in the dataset.
Some visible makes in the dashboard include:
- Ford
- Chevrolet
- Dodge
- Toyota
- GMC
- Mitsubishi
- Mazda
- Pontiac
The dashboard shows how policies are distributed across different coverage zones, helping identify spread or concentration of insurance exposure.
Insurance metrics are analyzed across customer age bands such as:
- 15–25
- 26–35
- 36–45
- 46–55
- 56–65
- 66–75
This helps understand which age groups represent stronger policy volume or claim contribution.
A yearly trend chart helps analyze how policies or claim amount vary based on vehicle year.
The project also includes analysis by the number of kids driving, which may help understand household driving-related patterns.
The dashboard compares metrics by education level, such as:
- Bachelors
- High School
- Masters
- PhD
It also includes a matrix visual for deeper claim analysis by education and marital status.
Based on the dashboard view:
- Private car use contributes a significantly larger share compared to commercial use.
- Policy and claim distribution are not equal across all age groups.
- Certain car makes have higher representation in the dataset.
- Mid-range age groups appear to contribute more strongly than the youngest and oldest groups.
- Education and household-related attributes add another layer of insight into insurance segmentation.
- Trend analysis by car year helps identify changes in exposure across vehicle age categories.
- Power BI
- Power Query
- DAX
- Data Modeling
- Data Visualization
- Dashboard Design
- Data cleaning and preparation
- KPI creation
- DAX-based reporting
- Interactive dashboard development
- Business insight generation
- Segmentation analysis
- Risk and claims reporting
- Visual storytelling
In this project, I worked on:
- preparing the insurance dataset for analysis
- creating business KPIs for policy and claims reporting
- building interactive visuals for segment-wise comparison
- designing a professional dashboard layout
- enabling dynamic metric switching for better analysis
- presenting insights in a structured and decision-friendly format
This dashboard can help insurance stakeholders:
- monitor overall policy and claim performance
- identify high-risk or high-claim segments
- compare customer groups and vehicle categories
- improve visibility into insurance exposure
- support more informed risk and claims-related decisions