Fault Impact Analysis: Towards Service-Oriented Network Operation & Maintenance by ITU
8 000 CHF
Completed (over 2 years ago)
Classification
273 joined
89 active
Start
Jul 26, 23
Close
Aug 18, 23
Reveal
Aug 18, 23
'/%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){kind=small}
Wow! 0.75 still stands!!
Platform · 19 Aug 2023, 02:24 · 16
Congratulations to @Krishna_Priya WHAT A SCORE!!! @JuliusFx impressive!!!. What was the trick guys , what was the trick??
😅, second ask. This is one of the toughest I've done in a while. Congratulations to all the winners. I saw impressive moves this week. 🙌🙌.
This one was tough indeed, You can see it in the number of submissions I made haha
😅, glad it's over too.
No kidding😂I've never struggled in a competition like this one. I basically gave up😪. Kindly share your approach too.
I will for sure just need to clean it up a bit
Same! Glad it's over too! 😆😆😆
And BIG Congratulations to the winners : @Krishna_Priya @JuliusFx and @Yisakberhanu
Thank you @ff. Learnt alot from your notebook share. Hoping to share mine once the position is confirmed.
Hi @koleshjr, I will share a write up on Monday after code submission deadline. However, funny thing is, I was conservative in ensembling the models and chose to give very low weightage to very high CV and low LB.
The current score is an ensemble of 16 models. Where top 2 single models based on private score are the ones with highest local CV. and both of them have a private score of 0.765 + 😅
Will share the detailed feature eng + models soon. No tricks. Plain old feature eng+
0.765++!!!!!😱, you definitely hacked this for sureeee, can't wait to read your write up😁
@Krishna_Priya Congratulations on the amazing score!
For me, choosing the right threshold had a significant impact on the private score. Please add in your write up your strategy for choosing the right threshold!
Do you mean a post-processing to choose a threshold on probabilities allowing to define "0" and "1"?
@ff Exactly yes
Congrats @Krishna_Priya !! Well deserved. You were very strong since the first submission. I'm looking forward to see your code.
Hello @Krishna_Priya still patiently waiting to read your write up :)
uploaded. it is just a copy-paste, not well formatted :)
Thanks @koleshjr. I did not break the mighty 0.75, congrats @Krishna_Priya for setting the pace and maintaining. Just posted a solution on the discussion. You can check it out, guys