888.470760_415140.lt. [HD]

The paper proposes training both components simultaneously rather than separately. This allows the model to optimize for both accuracy (via the wide component) and serendipity/novelty (via the deep component) [1606.07792]. Key Results & Impact

The model was heavily used for app recommendations on the Google Play Store [1606.07792]. 888.470760_415140.lt.

The implementation was made publicly available within TensorFlow . 888.470760_415140.lt.

Online experiments showed that "Wide & Deep" significantly increased app acquisitions compared to models that used either approach alone [1606.07792]. 888.470760_415140.lt.