Shell.ai Hackathon

Hello ! I have two questions: I want to confirm that the distance matrix is not given to us and we need to compute it by ourselves. And we are expected to use euclidean distance. Will the evaluation be done on a single ground truth. For example, the 2019 demand is unknown. So we have to make a decision under uncertainity. One team makes a decision that by accident does well on the actual 2019 prediction but could have been very wrong if relaity was slightly different. Other team does okayish on 2019 but the decisions are such that they would have done good on wide variety of possible scenarios. So basically, a good decision may not necessarily lead to a good outcome. So in this case, are we evaluating on a single ground truth scenario (and the one with good outcome wins) or a multiple scenarios (where one with good decisions wins) ?

After a submission, we got a contsraint violation 4. We manually checked all SCS and FCS values of 2019 and 2020 that we have predicted, and compared them with the original infrastructre, and found that there is no decsrease in the number of charging stations in our submission. Can you help us figure out why we're still getting this violation?

Given that fast charging stations cost 1.5 the amount of slow charging stations, but deliver twice the charging capacity of a slow charging station, it seems like a solution should always build as much fast charging stations as needed to fulfill the demand. Am I correct or do I overlook something?

Hi, first of all, thank you for the competition and this opportunity. On the website,  in the start-up participation section, it says "Open to registered start-ups only (minimum 2 members)". I would like to clarify this so that there is no misunderstanding. Is it related to the size of the start-up (number of employees in the start-up). In other words, if more than two employees are working in the business, is it enough for 1 person to represent the start-up? Or, does the number of participants needs to be at least 2 people? Thanks in advance for the information.

we have a loss L= a*COSTcd +b*COSTdm +c*COSTif I far as I can think that we can reduce a loss (a*COSTcd +b*COSTdm) by Gradient D but any idea how to deal with the 3rd loss term? Any idea relevant to this?

Hello, I am new in optimzation with this kind of problem. Can you share any relavent link to start with

Shouldn't  be the index of demand and supply point are coordinates instead of ranges as mentioned

Dear the host of Shell.ai Hackathon, Given the known impact of COVID on economics and industry worldwide, should we consider the factor of COVID in predicting the demand? Or the demand of charging is simulated or under some special conditions, so we don't have to think about the factor? Thanks in advance for your explanation.  

Can any on eplease tell me where is the dataset. I am unable to find it. Thank you

It has been 4 days since the start of the competetion and the Shell has not released the recording of the video. If the video is not a part of confidentiality, then please try to upload it in hackerearth as soon as possible.

Hi team, We would like to have access to the webinar, as we wanna refer to the problem statement explaination.

Hi i am unable to connect ot Live session.

Is there only one submission link? Or are there different links for continuous evaluation and final submission?

So, overall cost COST = a x Cost_CD + b x Cost_DM + c x Cost_DM.  I think the last term should be c x Cost_IF. 

I'm constantly getting error code 5; though I have manually tested the values, it's satisfying. Can you check?

Hi Team, I was not able to find dataset for the challenge, can anyone suggest or guide?