Underwriter and Broker Location Relation Ideation Challenge

Key Information

Register
Submit
The challenge is finished.

Challenge Overview

Challenge Overview

Given a large amount data of the relationship of underwriter assignments to broker locations, we would like to gain insights through nice, neat visualizations.

Background

We have been working to understand the relationship of underwriter assignments to broker locations as a way to improve new business results.  While intuitive, we have been able to quantify that an underwriter is more successful at writing new business when they have a renewal book at that same location. Given the volume of data and the many intersections across underwriters and broker locations, we are struggling to find ways to visualize the data to make recommendations.  We are looking for a new way to visualize the data we have.

Task Detail

We provide the data in an Excel file. Specifically, the columns are:
  1. Source – Data Source Name
  2. Master ID – Numerical ID assigned to broker specific cities
  3. Broker – Anonymized Broker Name
  4. BU – Organization Level 1 (Highest)
  5. SBU – Organization Level 2
  6. MU – Organization Level 3
  7. PC – Organization Level 4 (Lowest)
  8. cal_mth – Calendar Month
  9. cal_yr – Calendar Year
  10. Zone – Broker Geographic Zone (Highest)
  11. Region – Broker Geographic Region
  12. Area – Broker Geographic Area
  13. State – Broker State
  14. mpl_city – Broker City (Lowest)
  15. BDL Name – Anonymized Business Leader
  16. Segment – Broker location designation
  17. UW – Anonymized Underwriter Name
  18. UWM – Anonymized Underwriter Manager
  19. Subs – Count of new business opportunities submitted by broker to carrier
  20. Quotes – Count of new business opportunities quoted by carrier
  21. Binds – Count of new business opportunities bound by carrier
  22. Lookup Node – Anonymized code combining UW Name with Broker City
  23. Retention Lookup – Flag detailing whether UW has renewals at given Broker City
  24. NB GWP Lookup – Flag detailing whether UW has new business at given Broker City
  25. Retention Status – Duplicate of Retention Lookup
 
 
In this challenge, we are looking for any insights that can be gathered from the relationship between Underwriter Name and Broker City. Performance can be measured in terms of Subs, Quotes,Binds and Ratios:
  1. Hit Ratio - Binds/Quotes;
  2. Quote ration - Quotes/Subs;
  3. Conversion ratio - Binds/Subs.
The higher the ratio the better. The higher the binds the better. The subs, quotes, binds only apply to new business. Therefore, we'd like to understand the impact on NB if the underwriter also has a renewal book at the same mpl_city.
 
Some potential questions:
  1. What is the ideal number of locations per underwriter?
  2. Does that vary by organization unit?
  3. Are the underwriters more effective for new business if they have a renewal book?
 

Final Submission Guidelines

Submission

Commercialization

This is a HARD requirement. You have to make sure your proposal can be used for the commercial purpose. If your solution involves any commercial license, please justify how can we purchase it and how much does it cost.

Final Submission

Format

  • A document should be minimum of 2 pages in PDF / Word format to describe your ideas.
  • It should be written in English.
  • Leveraging charts, diagrams, and tables to explain your ideas is encouraged from a comprehensive perspective.
  • PoC source files along with build and deployment steps

Judging Criteria

You will be judged on the quality of your ideas, the quality of your description of the ideas, and how much benefit it can provide to the client. The winner will be chosen by the most logical and convincing reasoning as to how and why the idea presented will meet the objective. Note that, this contest will be judged subjectively by the client and Topcoder. However, the judging criteria will largely be the basis for the judgment.
 
  1. Effectiveness (40%)
    1. What’s the key insights we can get from your analysis?
    2. How these discovered insights can benefit the client?
  2. Feasibility (60%)
    1. Is the data analysis efficient, scalable to large volume of data?
    2. Is the data analysis easy to implement? Did you include the example implementation?
    3. Proof of concept (PoC) codes are strongly recommended. If you are providing PoC codes, Python Jupyter Notebook is required.
 

Submission Guideline

You can submit at most TWO solutions but we encourage you to include your great solution and details as much as possible in a single submission.

ELIGIBLE EVENTS:

Topcoder Open 2019

REVIEW STYLE:

Final Review:

Community Review Board

Approval:

User Sign-Off

SHARE:

ID: 30086250