DigiCow Farmer Training Adoption Challenge
'/%3e%3c/defs%3e%3cpath fill='%23fff' d='M-120-80h240V80h-240z'/%3e%3cpath d='M-120-80h240v48h-240z'/%3e%3cpath fill='%23060' d='M-120 32h240v48h-240z'/%3e%3cg id='b'%3e%3cuse xlink:href='%23a' stroke='%23000'/%3e%3cuse xlink:href='%23a' fill='%23fff'/%3e%3c/g%3e%3cuse xlink:href='%23b' transform='scale(-1 1)'/%3e%3cpath fill='%23b00' d='M-120-24v48h101c3 8 13 24 19 24s16-16 19-24h101v-48H19C16-32 6-48 0-48s-16 16-19 24z'/%3e%3cpath id='c' d='M19 24c3-8 5-16 5-24s-2-16-5-24c-3 8-5 16-5 24s2 16 5 24'/%3e%3cuse xlink:href='%23c' transform='scale(-1 1)'/%3e%3cg fill='%23fff'%3e%3cellipse rx='4' ry='6'/%3e%3cpath id='d' d='M1 5.85s4 8 4 21-4 21-4 21z'/%3e%3cuse xlink:href='%23d' transform='scale(-1)'/%3e%3cuse xlink:href='%23d' transform='scale(-1 1)'/%3e%3cuse xlink:href='%23d' transform='scale(1 -1)'/%3e%3c/g%3e%3c/svg%3e)
'%3e%3cpath fill='%23001489' d='M0 0v6h9V0z'/%3e%3cpath fill='%23e03c31' d='M0 0v3h9V0z'/%3e%3cg stroke='%23fff' stroke-width='2'%3e%3cpath id='d' d='m0 0 4.5 3L0 6m4.5-3H9'/%3e%3cuse xlink:href='%23b' stroke='%23ffb81c' clip-path='url(%23c)'/%3e%3c/g%3e%3cuse xlink:href='%23d' fill='none' stroke='%23007749' stroke-width='1.2'/%3e%3c/g%3e%3c/svg%3e){kind=small}
Hi all,
I have reviewed and updated the dataset following the discussion on potential data leakage in this post: https://zindi.africa/competitions/digicow-farmer-training-adoption-challenge/discussions/30471
Initially, the objective was to predict adoption within 120 days. However, after further consideration, a shorter prediction window was more practical. As a result, the primary target was updated to adoption within 7 days.
To avoid any risk of leakage, I have removed the features num_training_30d and num_training_60d. Computing these features implicitly relies on training dates which may not be available at prediction time. Additionally, having num_training_xd > 0 does not necessarily imply adoption, so removing these features is both safer and cleaner.
In addition to the 7-day target, I have also included two additional targets:
- Adoption within 90 days
- Adoption within 120 days
Please note that the data has been updated, IDs have been regenerated, and you will need to re-download the dataset.
I increased the total submission count from 200 to 220.
My apologies for the inconvenience, and thank you for your understanding.
Keep Zinding!
Yes my submission has not been corectly added.
If that’s the case, shouldn’t the previous submissions not be counted? What I mean is that we should start from zero, even though I had made about 20 submissions before.
For fairness, I have increase the submission count by 20 for all participants.
Adding twenty submissions for everyone effectively grants 20 extra entries to participants who had not submitted anything, but it does not compensate those who have already submitted more than 20 submissions since the competition started. I do not think that is fair.
@AJoel, the number of submissions should be reset to zero !!!
Hello, could you kindly update how the leaderboard rankings are now computed? In some previous chat, there was a formula on this. Given that we have new targets, I am requesting an updated formula
Secondly, can one target be used as a feature in the model to predict another i.e adoption within 7 days be used as a feature in adoption within 90 days?