Here is my winning solution for the IBM SkillsBuild Hydropower Climate Optimisation Challenge available on my GitHub repository: https://github.com/bakarys01/hy... See more

First off, congratulations to the winners! I really struggled with this competition so I understand how hard it is to pull off a good score.I created a repo for... See more

Here is my notebook for training and solution, want to hear your opinions! do you find it very simple ? 🧐https://www.kaggle.com/code/belalemadhussein/hydropowe... See more

🧹 Data Preprocessing & Cleaning Excluded devices not present in the test set to prevent leakage and noise Aggregated 5-minute data into daily features with... See more

My best private scores (4.45279869, 4.472504244, 4.485014314, 4.498282647 , ...) are well below what is displayed as my best private score .. my Question is... See more

I want to congratulate all of you. We expected some shake-up in the leaderboard, but not to this extent. I'm disappointed with how the test set was split betwee... See more

Hey Zindians! I wanted to share my solution to the recently concluded Hydropower Climate Optimisation Challenge. Even though I only started submitting on the la... See more

A fun and very useful competition as well.Congratulations to the winners and good luck to everyone.here is my solution in simple details:First, we group the dat... See more

Please, those topping the private leader board can you share your solutions, we want to learn from you 🙏

Congratulations to all the winners. Please, what strategy did you applied and how did you understand the data?

I see the leaderboard positions are still changing, what does this mean and how long it is expected to saturate after?

Congratulations guys, it was fun

Congratulatuons you all

The issue is that kWh is recorded every 5 minutes. The question is: do all the readings come from the same device and same user, reaching 288 readings per day a... See more

Can anybody give hint to do postprocessing

I'm really struggling ... I either get a great score or a very bad one ... it lead me to this ... how to aggregate ... what is it exactly that we are predicting... See more

Okay guys I think post processing might be the key to LB improvement what 's your opinion ,

Hey everyone, this has been a challenging competition and I've really struggled to break the baseline.Through my analysis I found something that may sound obvio... See more

What is your opinions?

Since the competition is nigh over I was wondering if the public test data could be made available after the deadline? I have reached the limit of my ideas and... See more

Everytime I downloadea Data.zip file I found it corrupted.

Hello everyone. I have been having problems with submitting my predictions. Every time I make a submission I get the following message instead of a score. Even... See more

Hey everyone! 👋I noticed that many of you were looking for more insights after the webinar, so I decided to share a starter notebook that improves performance.... See more

Has anyone tried tweedie as regression objective (irrespective of model type or CV strategy)? It appears tweedie regression demonstrates strong perf on local cv... See more

So several discussion posts talked about the oddly strange diffrerences in validation/test/leaderboard metrics. I've tried to upload three plots here but couldn... See more