The Zimnat Insurance Assurance Challengeby #ZindiWeekendz
Can you predict when an insurance policy will lapse in Zimbabwe?
$300 USD
Ended almost 3 years ago
105 active · 295 enrolled
My Solution
Notebooks · 25 May 2020, 08:28 · 8

Kudos to everyone who participated in this challenge as it was a difficult one.

My approach is quite straightforward. create some aggregate features from the policy data, some flags. the major improvement was to train on only policies in the client data and drop policies that lasped in 2017 and 2018.


unqiue counts: policies, products ,principals, family per policy,count of unique mean_premium, frequency encoding of location

mean NPR PREMIUM , minimum NPR PREMIUM per policy, location, agent, type

Flags: flag if policy was effected in 2020 else 0, flag if policy id is present in client data else 0, flag if policy has premium data from 2019 else 0

And Finally, umap dimemsion reduction features using tsne (2 dimensions)

Single Xgboost 5 FOLD: CV 0.2420, Public 0.2419, Private 0.243

Discussion 8 answers

Wonderful to see R code. Thanks for sharing

25 May 2020, 08:54
Upvotes 0

Congratulations Holar, thanks for sharing !!!

25 May 2020, 17:38
Upvotes 0

Nice, Solution Holar. I learned a few things. Thank you for sharing :)

25 May 2020, 19:38
Upvotes 0

hello, and good morning. i would need your assistance on some concepts in this challenge. how do i get in touch with you?

9 Jun 2020, 07:19
Upvotes 0