Abstract: In some examples, a computer-implemented method is provided. The computer-implemented method includes accessing a training dataset including a plurality of data pairs. Each data pair of the plurality of data pairs includes first data from a first recorded observation for a first dependent user and second data from a first identifier for the first dependent user. The first identifier corresponds to the first recorded observation. The computer-implemented method also includes training a predictive model by using the training data set and accessing an unpaired recorded observation for a second dependent user. The unpaired recorded observation is missing a corresponding identifier. The computer-implemented method further includes using the trained predictive model to generate at least one paired identifier for the unpaired recorded observation, and outputting the at least one paired identifier.