You'll be running endlessly in the subway surfers because someone is chasing and trying to catch you. While running, you'll collect lots of coins and attractive... See more

Hey, Please can the winners make their solutions public?Would appreciate it

3rd place solution Problem Highlight:We approached the problem as a binary classification problem. We formulated the problem as developing separate models for e... See more

You can find my solution fully commented here:https://www.kaggle.com/danielbruintjies/zindi-user-behaviour-5th-place-solution/notebook

Problem Formulation:The problem formulation is not a major aspect of our solution, but we feel it is worth mentioning.This competition can be formulated in many... See more

Thank you @ZINDI for the awesome competition! Big congrats to those who were able to build the robust models for private and to those who flourished on the publ... See more

I am seeing changes in scores on the leaderboard.Why would some want to hide their scores? Zindi you need to fix this bug ASAP to protect the integrity of the p... See more

As far as I remember, top team has LB of 93+ and now it is under 92. Did some rescoring happened, how's that got changed ?

Hi Friends,Can anyone give a hint on how the merging can be done for training and testing? Test set do not seem to contain any features given in competition, pa... See more

Hello everyone! am a bit confused with the given dataset i.e there are alot of dataset, all the datasets are supposed to be merged or what should do first?

Having a hard time breaching that 0.90. CV LB both now stuck at 0.89 :(

It seems the DiscID feature is not related to the Comments table, contary to information in the Variable Definitions file. Any clarification please?

Hey Guys.. . I just Joined the Hackathon. Please I will need a little hint on how to handle the rest dataset that has just 2 columns.... Any hint on how to gene... See more

When I am only using the Users dataset the accuracy is high. But when I join other data sets the auc score is decreasing. Any insights would be appretitated.

My 5 fold CV gives AUC around 92% with both Neural Net as well as Tree Boosting, However the LB auc is below 75% and I couldn't figure out why that's the case.A... See more

I can't seem to improve my score people LOL. Any tips and tricks from the leading pack?

Can anyone help me with the different data pre processing techniques required ,for the available csv files and the which model has to be selected???

is it allowed to change or add features to train and test dataset and run model on the reconstructed one?

Hi, The target column in the train dataset means that the user is active during the next month or the given month ? Thanks.

It was stated that "An active user is one that enters a competition, makes a submission, or engages through the discussion forums". I just want to clarify. Doe... See more

the months and years given how have they been attained are they the total number of months or years the user has been discussing or submitting or what do they a... See more

Hello everyone, is this competition open to participants from regions not in Africa? For example, can my friends from Europe be allowed to join in?

What does the secret code variable mean in the reality of Zindi?

should we include other datasets into our training dataset.

Hello Zindi. The definition of month and year of the train csv was not provided in the variable definition csv. Kindly tell us what they mean.