Introduction
The insurance industry generates massive volumes of data daily. Without the right tools and strategy, this data remains underutilized. With Power BI, insurers can turn raw data into interactive dashboards that drive strategic decisions. This Power BI dashboard visualizes policy and claims data over a five-year period (2014–2018). It demonstrates how insurers can monitor performance, assess risk, and identify customer trends across multiple dimensions such as vehicle type, usage, and gender.
-
Accessing data from open-source data platform.
-
Performing Extract, Transform, Load (ETL) processes using Power Query to manipulate and shape the data.
-
Conducting data preparation tasks such as updating and appending tables.
-
Transforming data into a suitable data model and exploring it by removing duplicates, adding conditional columns, unpivoting and splitting columns, as well as normalizing tables.
-
Creating custom tables and establishing relationships, implementing either star or snowflake schema tables based on the requirements.
-
Preparing data visualizations and reports using a wide range of chart types including bar, line, column, scatter, donut, ribbon along with tables, matrices, KPIs and slicers.
-
Implementing DAX (Data Analysis Expressions) measures to perform calculations such as sum, count, calculate, divide, and time intelligence functions.
-
Building dynamic measures, dynamic dimensions, tooltips, and bookmarks to enhance the interactivity and usability of the reports.
-
Publishing, sharing, and collaborating on dashboards, workspaces, and apps, ensuring effective communication and knowledge sharing within the project team.
Key Highlights
»Top-Level KPIs
-
Policy Opened: 57K total indicating a strong customer base.
-
Total Premiums: $384M collected, with an average premium of $7K.
-
Claim Count: 2K total claims with an average payout of $170K.
-
Total Claims Paid: $337M, a substantial proportion of collected premiums.
These high-level KPIs help decision-makers instantly grasp profitability and exposure.
»Vehicle Type Distribution
On the left, the bar chart shows who is buying policies. Key observations:
-
Motor-cycles (16.2K) and Trucks (10.3K) lead in policy count.
-
Special Construction and Tanker vehicles have minimal policy counts, possibly indicating niche but high-risk markets.
-
Icons (✅/🔴) provide intuitive classification based on profitability.
This view helps underwriters and marketing teams understand customer segmentation by vehicle.
»Policy Usage Trends Over Time
The center heatmap is a treasure trove for actuarial and pricing teams. It reveals:
-
Exponential growth in categories like Agricultural Own Farm and Special Construction from 2014 to 2018.
-
Usage like Learners, Private, and Fare Paying Passengers remained relatively stable.
Color gradients quickly show which segments grew (green) or declined (red), offering actionable insights for pricing and sales strategies.
»Gender Distribution
Two donut charts break down policies opened and claims by gender:
-
57% of policyholders are male, but they represent 50% of claims.
-
Females hold 39% of policies yet account for a slightly lower claim rate (781 out of 2K).
This can inform targeted engagement strategies and policy design for gender-specific segments.
»Claims Over Time
The area chart shows total claims by usage across the years. There’s a noticeable peak around 2015–2016, likely tied to either a regulatory change, policy growth, or claim backlog. Exploring this anomaly could help risk teams preempt similar spikes.
»Premium vs Claim Bubble Chart
In the bottom-right quadrant, a scatter plot maps premium values against claim payouts:
-
The green dots highlight vehicle types that either over- or underperform in terms of profitability.
-
Most policies cluster in the low-premium/low-claim zone, but a few outliers suggest high-risk or high-value policies.
This chart is a goldmine for identifying underpriced high-risk vehicles or overpriced low-risk segments.
Strategic Insights
-
High Growth, High Risk: Agricultural and construction-related categories have rapidly growing usage, but may need close monitoring for risk exposure.
-
Profitability Focus: The bubble chart can be used to adjust pricing or policy limits on underperforming segments.
-
Gender Disparities: While males dominate the policy base, females appear to have slightly lower claim frequencies, this might support gender-based risk-adjusted pricing.
Final Thoughts
This dashboard exemplifies the power of interactive data storytelling with Power BI. It not only surfaces trends and anomalies but also provides clear visual cues for taking action, whether that’s refining underwriting models, optimizing pricing, or launching targeted campaigns.
