Abstract: In one embodiment, a method separates subscriber features generated from subscriber interaction with a video delivery service into feature dimensions and inputs the feature dimensions into a respective prediction network. Each prediction network is trained to output a respective dimension score. The method outputs dimension scores using parameters in the plurality of prediction networks that are trained using a variance term to control a variance of the plurality of feature dimensions and using a de-correlation term to control a correlation of the plurality of feature dimensions. The dimension scores are combined into a retention prediction score and an action is performed on the video delivery service for the subscriber based on the retention score.

Abstract: In one embodiment, a method separates subscriber features generated from subscriber interaction with a video delivery service into feature dimensions and inputs the feature dimensions into a respective prediction network. Each prediction network is trained to output a respective dimension score. The method outputs dimension scores using parameters in the plurality of prediction networks that are trained using a variance term to control a variance of the plurality of feature dimensions and using a de-correlation term to control a correlation of the plurality of feature dimensions. The dimension scores are combined into a retention prediction score and an action is performed on the video delivery service for the subscriber based on the retention score.

Abstract: Embodiments of the present disclosure provide an effective, user-friendly approach to help prevent the abuse of social networks by users who misrepresent their age, identity, and/or other information.