Zindi New User Engagement Prediction Challenge
Helping Africa
$5 000 USD
Challenge completed over 2 years ago
Prediction
1269 joined
222 active
Start
Oct 14, 22
Close
Feb 12, 23
Reveal
Feb 12, 23
'%3e%3ccircle r='120' fill='%230f47af'/%3e%3cg id='a'%3e%3cpath fill='%23fcdd09' d='m0-96-4.206 12.944 17.348 53.39h-23.13l-2.599 8h74.163l11.011-8H21.553z'/%3e%3cpath stroke='%23fcdd09' stroke-width='4' d='m25.863-35.597 30.564-42.069'/%3e%3c/g%3e%3cuse xlink:href='%23a' transform='rotate(72)'/%3e%3cuse xlink:href='%23a' transform='rotate(144)'/%3e%3cuse xlink:href='%23a' transform='rotate(216)'/%3e%3cuse xlink:href='%23a' transform='rotate(288)'/%3e%3c/g%3e%3c/svg%3e){kind=small}
Starter Notebook
Notebooks Ā· 12 Nov 2022, 10:09 Ā· 7
here is a link to a simple starter notebook with a public score of 0.305170239. But the lb isn't updating, i don't know why.
please upvote if you find it useful😊 and there might be some updates
Thanks for sharing this - very useful!
Are we 100 % sure we only need to predict for people with a "created_month=5"?
For now yes but the data will be updated I think. Actually, all the users in the submission file created their accounts in month 4.
The idea is that given some users who created their accounts 2-6 months before and their activities after and new users who created their accounts this month, will they be engaged the next month?
Thanks, man! It is real help. I've spent a while, just trying to understand, what to start from!
Glad it helped😊
Thanks for your initiative. It will be even more usefull, if you try to use the other tables as well, as the "UserActivity" file doesn't add much. At one point, I wanted to know the cost of each table, so when I used all the tables, I got a score of 0.427, then by eliminating the UserActivity features, I got 0.417, which means that this table will adjust the score with only 0.01...
The most valuable tables are CompetitionParticipation, Discussion, Comments.
Thanks too,
Oww really nice, i'll try them thanks again🙏
Hey