Actuarial Outpost
 
Go Back   Actuarial Outpost > Actuarial Discussion Forum > Property - Casualty / General Insurance
FlashChat Actuarial Discussion Preliminary Exams CAS/SOA Exams Cyberchat Around the World Suggestions


Upload your resume securely at https://www.dwsimpson.com
to be contacted when new jobs meet your skills and objectives.


Reply
 
Thread Tools Search this Thread Display Modes
  #1  
Old 10-21-2017, 06:52 PM
calculusjunkie calculusjunkie is offline
CAS SOA
 
Join Date: Mar 2014
College: University of Illinois, undergrad
Posts: 10
Default Incomplete loss data to estimate credibility

I am learning about ratemaking and recently someone asked me how do you estimate credibility on incomplete loss data? I havenít done this analysis but I would like to learn. I would appreciate your comments.
Thank you!
Reply With Quote
  #2  
Old 10-21-2017, 08:46 PM
Marcie's Avatar
Marcie Marcie is online now
Member
CAS
 
Join Date: Feb 2015
Posts: 7,469
Default

Quote:
Originally Posted by calculusjunkie View Post
I am learning about ratemaking and recently someone asked me how do you estimate credibility on incomplete loss data? I haven’t done this analysis but I would like to learn. I would appreciate your comments.
Thank you!
What do you mean by "incomplete loss data," Junkie?
Reply With Quote
  #3  
Old 10-21-2017, 09:22 PM
calculusjunkie calculusjunkie is offline
CAS SOA
 
Join Date: Mar 2014
College: University of Illinois, undergrad
Posts: 10
Default

For example, the product department is sure that the losses should sum up to $5,000 in one specific city, but after extracting the data from the database it shows that the losses are only $3,000. How does that affect my analysis and what should I do to gather the data accurately. Does that make sense?
Reply With Quote
  #4  
Old 10-21-2017, 11:12 PM
Marcie's Avatar
Marcie Marcie is online now
Member
CAS
 
Join Date: Feb 2015
Posts: 7,469
Default

Quote:
Originally Posted by calculusjunkie View Post
For example, the product department is sure that the losses should sum up to $5,000 in one specific city, but after extracting the data from the database it shows that the losses are only $3,000. How does that affect my analysis and what should I do to gather the data accurately. Does that make sense?
Not really.

Why is the product department sure the losses should be $5000?

Is the $3000 total questionable?

Did you extract the data from the database yourself, or did you get it from someone? If you did it, do you know what you're doing? If someone else, do they know what they're doing?

Have you performed any checks on the data to make sure of its accuracy and reasonability?

I have some more questions but I'll stop there for now.
Reply With Quote
  #5  
Old 10-21-2017, 11:29 PM
Colonel Smoothie's Avatar
Colonel Smoothie Colonel Smoothie is offline
Member
CAS
 
Join Date: Sep 2010
College: Jamba Juice University
Favorite beer: AO Amber Ale
Posts: 47,166
Default

Yeah, incomplete data can mean a lot of things, like censoring/truncation or undeveloped losses or IBNR.

Sounds like in your case, the data are there but you aren't extracting all of it. This is more of a data reconciliation problem rather than one that would require credibility weighting. In that case, work with product to fix the problem and bring it up with your manager if you lack the resources/influence to do so.
__________________
Recommended Readings for the EL Actuary || Recommended Readings for the EB Actuary

Quote:
Originally Posted by Wigmeister General View Post
Don't you even think about sending me your resume. I'll turn it into an origami boulder and return it to you.
Reply With Quote
  #6  
Old 10-22-2017, 12:16 AM
calculusjunkie calculusjunkie is offline
CAS SOA
 
Join Date: Mar 2014
College: University of Illinois, undergrad
Posts: 10
Default

I was asked this by the product department. As far as I know the person that extracted the data was confident on what he was doing. I asked them to check with claims as they could give them more accurate information on the losses. I am now wondering if they are looking at paid or reported losses and they are not classifying them accordingly. I also think that the problem is in data reconciliation.
Thank you for your comments, this has been helpful.
Reply With Quote
Reply

Thread Tools Search this Thread
Search this Thread:

Advanced Search
Display Modes

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off


All times are GMT -4. The time now is 09:05 PM.


Powered by vBulletin®
Copyright ©2000 - 2018, Jelsoft Enterprises Ltd.
*PLEASE NOTE: Posts are not checked for accuracy, and do not
represent the views of the Actuarial Outpost or its sponsors.
Page generated in 0.32217 seconds with 11 queries