| CPC G06F 16/152 (2019.01) [G06F 12/1018 (2013.01); G06F 16/24578 (2019.01); G06F 16/435 (2019.01); G06Q 50/10 (2013.01); G16H 10/40 (2018.01); H04L 67/02 (2013.01); H04L 67/535 (2022.05)] | 11 Claims |

|
1. A method for providing pre-validated data buckets for online experiments, comprising:
obtaining historical user activity data representing online activities of a plurality of users each having a corresponding user identifier;
hashing each of the plurality of user identifiers to obtain a plurality of hash values;
obtaining a set of metric values based on the historical user activity data, wherein the set of metric values represents user engagement of the plurality of users;
ranking the plurality of hash values of the plurality of users based on the set of metric values to obtain a ranked list of hash values; and
removing one or more of hash values from the ranked list based on an exclusion range rule provided for excluding users with hash values in a predetermined range, wherein the remaining hash values in the ranked list are to be placed in a data bucket for an online experiment, wherein the exclusion range rule indicates to exclude the one or more of hash values flagged by a metadata tag, and wherein the metadata tag indicates that the one or more of hash values are either unavailable for placement or should not be used in the data bucket for the online experiment.
|