Abstract: Techniques for increasing computer system efficiency using unified encoding are disclosed. In some embodiments, a computer-implemented method comprises: for each skill in a plurality of skills, obtaining a plurality of features for the skill, each feature in the plurality of features comprising a different type of signal indicating a relationship between the skill and a first user; computing a unified embedding of the plurality of features of the plurality of skills for the first user using a neural network and the plurality of features for each skill in the plurality of skills, the computing the unified embedding comprising inputting the plurality of features for each skill in the plurality of skills into the neural network; and using the unified embedding for the first user in an application of an online service, the using the unified embedding comprising causing content to be displayed within a GUI of the application based on the unified embedding.

Abstract: Methods, systems, and apparatuses include determining a set of data. The set of data includes multiple numerical ranges associated with an embedding and an attribute. The numerical range is sampled to obtain a sample value which is also associated with the embedding and the attribute. A set of sample value training data is generated, the set including the sample value, the associated embedding, and the associated attribute. A trained neural network prediction model is generated by applying a prediction model to the set of sample value training data. A set of input data is applied to the trained neural network prediction model. An output is determined by the trained neural network prediction model based on the set of input data. The output is a predicted range of values based on an output mean and an output standard deviation.