Uber Movement SANRAL Cape Town Challenge
'%3e%3cpath fill='%23001489' d='M0 0v6h9V0z'/%3e%3cpath fill='%23e03c31' d='M0 0v3h9V0z'/%3e%3cg stroke='%23fff' stroke-width='2'%3e%3cpath id='d' d='m0 0 4.5 3L0 6m4.5-3H9'/%3e%3cuse xlink:href='%23b' stroke='%23ffb81c' clip-path='url(%23c)'/%3e%3c/g%3e%3cuse xlink:href='%23d' fill='none' stroke='%23007749' stroke-width='1.2'/%3e%3c/g%3e%3c/svg%3e)
Helping South Africa
$5 500 USD
Challenge completed over 5 years ago
Prediction
Anomaly Detection
Forecast
853 joined
133 active
Start
Oct 11, 19
Close
Feb 09, 20
Reveal
Feb 10, 20
Definition of labels
Data · 27 Nov 2019, 07:01 · 1
Dear Organizers,
Could you help me with the following problem? How are the predicted labels connected with the datetime?
For example, let's consider the row
datetime x segment_id, predicition 2019-01-01 01:00:00 x S0B3CGQ,1
Does 1 indicate that at least one incident occurs during the time interval [2019-01-01 00:00:01, 2019-01-01 01:00:00] or not?
Thank you!
I think the approach you mentioned is the case. That approach was utilized in a previous competition. But it will be nice to get confirmation from Zindi.
The previous challenge is Mtoto Child line. See excerpt below from the data page.
"The format of time_index is YYYYMMDDHH (year month day hour). For example, the calls associated with time_index 2016071300 would be the calls received between 12:00:00 am until 12:59:59 am on 13 July 2016."