All issues in one
-
General: remove, ./data mention from everywhere.
-
Evaluation criteria: remove log loss, remove the invalid equation error in this section
-
Submission: make the submission section more detailed, even if you have to write redundant repetitive statements. example https://gitlab.aicrowd.com/aicrowd/practice-challenges/aicrowd_ADCLK_challenge , i am not writing it myself.
-
Files: follow the pattern of https://gitlab.aicrowd.com/aicrowd/practice-challenges/aicrowd_ADCLK_challenge, use bullets not hyphens for starting off test and train file name, there is a space missing between test and train lines. the takeaway is to NOT use words like validation and training here, we do not want any prejudice for the solver. give information as clearly as possible.
-
Dataset: No questions should be posed in this section the dataset should be very very informative and easy to understand as we do not explain much in the introduction. even if you restate
simple things it is ok. below is what is expected. you can use bullets if you want. description of the dataset in the link was good.
" The dataset basically describes the marketing campaign of a portuguese banking institution. The campaign was based on phone calls and
the dataset describes the clients who were contacted, the description also includes the details of previous contacts made to the
client as telesales typically need multiple contacts to convince a client.The final aim of the calls was to convince the client to ‘subscribe to a term deposit’. So for each call made to a client you have a total of 20 attributes describing the client and corresponding to a description, there is a final outcome of the call , whether or not the client ‘subscribe to a term deposit’.
For details about input variable visit here!."