Has there been a result for the discussion about the ranking now? Does such an obvious mistake require such a long discussion? The ranking of this competition i... See more

Never mind. Saw the post.. Can't delete this message, only edit it.

https://github.com/Adeyinka-hub/13th-Place-Solution-Digital-Green-Crop-Yield-Estimate-Challenge-Feel free to star, fork, learn, and do whatever with this while... See more

Hello! We finished 3rd on the final leaderboard. We've made all our code and methodology for our model – which we have called XYieldBoost – available here.We us... See more

Yesterday, the challenge was finalized, where we had to select runs to submit. Logically, I selected my two submissions with the best scores on the public datas... See more

Hello, everyone. I hope you're all enjoying this competition, which feels like a lottery game.I've been using basic models with some tweaks to score high on the... See more

I would like to report a constant lack of communication that Zindi has been exhibiting towards the competitors since the first day of this competition. Many pro... See more

Hello everyone, here’s my solution summarized in a schema. You can find more details in the notebook here: https://github.com/kamel-yamani/Digital-Green-Crop-Yi... See more

Hi everyone!Thanks to Zindi and the host for this competition. And thanks to my teammate @AhmedTambal.I will try to give a detailed description of what we did.W... See more

Hello again, As @tomy4reel and @Koleshjr have pointed out, there are some IDs that have not been taken into account in the private leaderboard. I think even if... See more

I tried changing my prediction for ID_ECWVAC40SNWB from around 6000 to 0 but observed no difference in both public and private lb

Hello everyone, In the discussion titled “Digging Deeper: Investigating Potential Data Entry Errors”, @amyflorida626 stated, “To guide you in your approach to t... See more

It's obvious that Zindi changed the private dataset by removing all the outliers without announcing it to the participants. I stopped this competition long ago... See more

What a competition!!! I thought post processing was going to be the winning trick, Note: turns out the private test set had no outliers at allllll ------- Misl... See more

We'd like to see the top 3 solutions for the sake of learning

When you have several good options, you try to pick the best CV, right? Well, that approach didn't work for me. While this hurts me, wouldn't have been enough... See more

Best score breakdown from single model catboost:Q1q6TN8H ----- > catboost_v3 -- Public Score: 138.0288912 and Private Score: 114.1696573 Second best score... See more

Yeah just wanted to put this here :)Our solution is just a single xgboost with some feature engineering and a custom loss function (Huber loss). This was our be... See more

Hi guys, I am having an issue where whenever I try to submit the prediction I get an error saying that I have some missing ID in my prediction. However, when I... See more

There are some values in some categorical columns, which are present in test data("on which submission needs to be done") but not in train data. Model is never... See more

Hello I was inquiring about Public score, I have significantly worked on my model and I have reduced my RMSE from 667 to 323 and my public score increased to 43... See more

Guys I need some suggestion about the file I'm submitting in here. It is definitly showing me I have missing ID's, why?? Guys please help!!!!

How to use NursDetFactor and TranDetFactor. They seem like list of options filled by the responders and all are clubbed in single column. Can we get some meanin... See more

I am very new to data science so please bear with this noob question. I applied one hot encoding for the categorical variables. for the variable "LandPreparatio... See more

Hello am getting an error while making submission, am get this response Missing entries for IDs ID_UBBEFJS5I0QH, ID_CQ0FBB1L5EY3, ID_Y2ZY2HDPU6PE, ID_KWIMK8AMZF... See more