Cold start machine learning algorithm

A system comprising:

• one or more processors;
• a non-transitory computer-readable medium having instructions stored thereon, which, when executed by the one or more processors a processor, cause the system to:
• obtain a first plurality of images stored on a computing device, at least some of the first plurality of images not having the indication that they depict the first member;
• feeding each of the first plurality of images to a first machine learning algorithm model unique to a first user, the first machine learning algorithm model trained, using images containing an indication that they depict the first user, to calculate a user likelihood score for a candidate image based on the feature data, the user likelihood score being a measurement of a likelihood that the candidate image depicts the first user;
• and
• based on the user likelihood scores for the first plurality of images, select one or more user images from the first plurality of images.

A non-transitory machine-readable storage medium comprising instructions, which, when implemented by one or more machines, cause the one or more machines to perform operations comprising:

• obtaining a first plurality of images stored on a computing device, at least some of the first plurality of images not having the indication that they depict the first member;
• feeding each of the first plurality of images to a first machine learning algorithm model unique to a first user, the first machine learning algorithm model trained, using images containing an indication that they depict the first user, to calculate a user likelihood score for a candidate image based on the feature data, the user likelihood score being a measurement of a likelihood that the candidate image depicts the first user;
• and
• based on the user likelihood scores for the first plurality of images, selecting one or more user images from the first plurality of images.