This document provides an executive summary of a data visualization project using Tableau. The project explored customer insurance claims data to find insights and patterns. Key findings from segmentation and visualizations of variables like driver gender, car type, cost, and region included: 1) the dataset had slightly more female than male drivers who filed more claims, 2) SUVs were the most common and affordable car type but had the highest claims, and 3) older SUVs over 8 years had the most claims while vans and panel trucks had fewer claims even after 9+ years. The complete story and visualizations are available on Tableau Public.
This document provides an executive summary of a data visualization project using Tableau. The project explored customer insurance claims data to find insights and patterns. Key findings from segmentation and visualizations of variables like driver gender, car type, cost, and region included: 1) the dataset had slightly more female than male drivers who filed more claims, 2) SUVs were the most common and affordable car type but had the highest claims, and 3) older SUVs over 8 years had the most claims while vans and panel trucks had fewer claims even after 9+ years. The complete story and visualizations are available on Tableau Public.
This document provides an executive summary of a data visualization project using Tableau. The project explored customer insurance claims data to find insights and patterns. Key findings from segmentation and visualizations of variables like driver gender, car type, cost, and region included: 1) the dataset had slightly more female than male drivers who filed more claims, 2) SUVs were the most common and affordable car type but had the highest claims, and 3) older SUVs over 8 years had the most claims while vans and panel trucks had fewer claims even after 9+ years. The complete story and visualizations are available on Tableau Public.
Project 7 – Executive Summary (Data Visualization using TABLEAU)
Approach To explore the provided data set on Customer Insurance claims and come up with insights on the spread of data (themes/patterns). Primary direction of this activity was in a 3-way approach as below, 1. Perform customer segmentation to understand how the overall distribution of the base of customer data 2. Break down the single directional variable segmentation (here, Car variables like Car cost, car type, driver gender and so on) 3. Understand Claim trends and build charts and graphs that connect points 1 & 2. Post the above-mentioned activities, creation of dashboards was complete and in-turn used to build story with key findings. Tableau Public Link: CLICK HERE. Key findings 1. The dataset has an equal to slightly higher proportion of female driver patterns cutting across all the provided dimensions. For instance, dataset has 5.5k female drivers vs 4.7k male drivers with 3.3k married women vs 2.8k married men population distribution 2. Occupation wise, highest range of customers tagged with 'Blue Collar' occupation and ‘Doctor’ takes least position. On both these occupation, we are able to see Female/Women population is higher. The second chart gives us an essence that 6 out of 8 occupation classified below shows a higher average salary range for Women. 3. Private car use has recorded higher span of customers (specifically in urban area) as compared to Commercial car use. Extent of car use in rural area has been relatively lean as compared to urban areas. 4. SUV has been most sought car type overall (majority of female drivers) and is in the lower quartile when cost of car is to be considered. On contrary, Panel truck has been most less considered (majority of male drivers) which is the highest cost range for car type. 5. Tying car cost with how claim trend is, we are able to identify that Panel Truck having a higher average cost apparently has the least claim frequency (safe to underline a strong correlation of male driver behavior from previous blanks of the story). On the flipside, SUV car type having one of the least average cost has the highest claim frequency (also note, majority of SUV owners are females). 6. Overall claims over time (wrt birthdate of owners), we are able to identify a sharp increase in the number of claims for a decade (1940 to 1949). After a 1-year drop, new high recorded in 1953. This trend has been declining from 1963. In continuation, when broken down per gender, the earlier assumptions of female drivers claim events hold good. In addition, we can understand that the Rural area claim history have been below the average for both the genders and signifies that Urban population have a more active role in insurance claim events. 7. As for contribution distribution, we are able to find the below, ~58% of overall claims happen from customers who are in the education range of High School & Bachelors. Meaning, the more educated segment of society have fewer insurance claims. ~52% of claims come from Blue Collar, Clerical and Professional segment of occupation holders. ~68% of claims happen out of drivers who own lower/mid-range cost cars (SUV, Minivan and Pickup) ~94% of claim comes out of Urban region 8. Sports Car segment: Most affordable car type (both Commercial and Private use) across Rural and Urban areas have the highest average Old claims. Car Age factor: SUVs over ~8years runtime have recorded maximum claim amount overall. Vans and Panel Trucks have significant lower range of claims even after ~9+ years of run time.
PROJECT OWNER, R MANOJ PRABHAKAR PG BABI ONLINE BATCH (2019)