Actuarial Outpost
 
Go Back   Actuarial Outpost > Actuarial Discussion Forum > Software & Technology
FlashChat Actuarial Discussion Preliminary Exams CAS/SOA Exams Cyberchat Around the World Suggestions

Search Actuarial Jobs by State @ DWSimpson.com:
AL AK AR AZ CA CO CT DE FL GA HI ID IL IN IA KS KY LA
ME MD MA MI MN MS MO MT NE NH NJ NM NY NV NC ND
OH OK OR PA RI SC SD TN TX UT VT VA WA WV WI WY

Reply
 
Thread Tools Search this Thread Display Modes
  #1  
Old 02-07-2017, 11:04 AM
koudai8 koudai8 is offline
SOA
 
Join Date: Feb 2015
Posts: 23
Question Doing a Project on Data Science

Hello AO, I am enrolled in a course called "Applied Data Science" from the Statistics department, and it involves data science based projects with R and Shiny. One of the group project (of 4-5 people) is a freelance, and I want to do it on actuarial topics given that it will be refreshing to the audience of mostly stat majors.

However, after some googling, I cannot find one topic that ties data science with actuarial science, and is both doable and interesting.

Do you guys have any suggestions for this project topic?

By the way, I have passed all SOA prelims. And yes, it is a shame that I cannot find a good topic (I do not have any work experience yet).

Thanks!
__________________
ASA ERM Mods
ILALPM ILALFM DMAC FAC
Reply With Quote
  #2  
Old 02-07-2017, 01:55 PM
no driver's Avatar
no driver no driver is offline
Note Contributor
SOA
 
Join Date: Jan 2006
Studying for nothing!
Posts: 2,351
Default

What if you try to develop some intuition around demographic data? Something along the lines of http://flowingdata.com/2015/09/23/ye...live-probably/

Nathan Yau at FlowingData has done several things like this over the last couple of years, it's worth looking through the rest of his stuff too.
__________________
Exam FM Formula Summary (covers theory of interest formulas from the pre-2007 FM exam).
Reply With Quote
  #3  
Old 02-07-2017, 02:20 PM
d45's Avatar
d45 d45 is offline
Member
SOA
 
Join Date: Sep 2010
Location: Europe
Studying for Life
Favorite beer: Espresso
Posts: 184
Default

You can find insurance data (exposures, claims) and create a machine learning model to predict premium rates. Then build it on Shiny by transferring your output on the ui module and code on the server module.

You can add visualizations with ggplot2/plotly and key summaries/statistics with rhandsontable and DT. All these integrate very nicely with Shiny.

Last edited by d45; 02-07-2017 at 05:18 PM..
Reply With Quote
  #4  
Old 02-07-2017, 04:53 PM
Baron von Bootstrap's Avatar
Baron von Bootstrap Baron von Bootstrap is offline
Non-Actuary
 
Join Date: Jan 2016
Posts: 28
Default

might look into these kaggle datasets;

https://www.kaggle.com/uciml/caravan...ance-challenge
https://www.kaggle.com/rodrigodoming...e-motor-market
Reply With Quote
  #5  
Old 02-07-2017, 11:56 PM
venisonKurry venisonKurry is offline
Member
 
Join Date: Apr 2010
Posts: 323
Default

Quote:
Originally Posted by d45 View Post
You can find insurance data (exposures, claims) and create a machine learning model to predict premium rates. Then build it on Shiny by transferring your output on the ui module and code on the server module.

You can add visualizations with ggplot2/plotly and key summaries/statistics with rhandsontable and DT. All these integrate very nicely with Shiny.
where can we find nontrivial publicly available datasets?
Reply With Quote
Reply

Tags
actuarial science, data science, machine learning, predictive analytics, projects, r studio

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 11:28 PM.


Powered by vBulletin®
Copyright ©2000 - 2020, 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 0.43076 seconds with 9 queries