This is an overview of the approach I took in my solution that was ranked first following the top 5 challenge and review by Fossil. I may have to get confirmati... See more

Hey, I hope you are all doing well. I don't know if my approach will be in the final prize area, but I am sharing a part of it before the final score. During th... See more

I was waiting for the top 3 to share their solutions, but sadly no one did.Btw, for anyone interested here is part of our solution:Projects_Portfolio/[Zindi] Fo... See more

Could the winners please give insights into how they could make it to the top of the leaderboard? Thank you as we all await to learn from you!

Dear Zindi, please give us 3-4 more days | computer stuck. . . praying

Are any tools for hyperparameter tuning allowed or they are all considered as AutoML tools and we have to do it manually?

I'm a new learner of machine learning. Some personal projects were been completed recently. Now trying to compete in ML competitions. So, Anyone likes to join m... See more

Are Neural Networks (e.g Recurrent & Deep NN) considered Automated ML tools, as per competition rules?

Hi, Given that this is a forecasting task, how does the rest of the featues (such as price,sellout, inventories:...etc) which are not in the test set benefit ou... See more

I have done my first and second submission still yet my name is not appearing on the leaderboard.but it is showing that i have submitted, what should i do?

Hi, I see some sku_name&date duplicates only in train data. e.g. Does anyone know if they are real duplicates and we should eliiminate them (I mean it is... See more

Hi Zindi, the column "leftover_inventory" in the train data is not explained in the data dictionary. Please explain what it means.

Hi Zindi,In the dataset, we have some time gaps of no sale records for already existing SKU's. Some SKU's are obsolete after sometime and 2020 is explained to b... See more

THE LENGTH IS 1528, but when I submit, it tells me some SKU_NAME ids are missing.Missing entries for IDsABEAHAMASHL_1_2022, ABEENNEARMAZZ_2_2022, ABERTHAKEVAZZ_... See more

I just curious about sku name. I suspect there is any feature for us that can be extracted from sku name, because some prefix was same.

Hi,I wanted to know how could I evaluate my model from on test data as it has different dimension/size?Any clue/idea?

It is interesting that Zindi does not like automated tools.They abound, especially in this space.What about automated imputers such as datawig?Or time series fo... See more

Can I ask what the rules for scoring on the leaderboard are? The Info part presents various criteria and the rules for scoring on the leaderboard is some weird... See more

Hello !Here is (another) starter with some (quick) theoretical justification explaining the score improvement, hope you will find it useful !https://www.thekern... See more

As I understand no external data is allowed, correct?

Hi,Upon basic checking, i found out that this sku 'CATHHALREYZZ' does not exit in train data set but is there in the test set. Kindly suggest if additional data... See more

here is the starter notebook which gives the baseline scorehttps://www.kaggle.com/code/yohannesmelese/starter-notebook-for-fossil-demand-forecasting/notebookple... See more

Hello, The test and train data available have let different number of columns. After modeling and applying a machine learning algorithm, when I try to predict,... See more

It is pretty obvious after glimpse at training data to find out year '2020' is missing.would it be possible for us to obtain data during 2020?I'm assuming these... See more

Hi @zindi team,Can we get a little more info about how the data can be used for training model. The number of features are different in both training and test s... See more