System and method for tag-directed deep-learning-based features for predicting events and making determinations

A method, comprising:

• accessing one or more data items associated with a user, each data item being further associated with a feature of a plurality of features and a data item value;
• determining, for a set of one or more features of the plurality of features, an aggregate value, based on the one or more data items, for each feature of the set at one or more time intervals;
• inputting each aggregate value to an input layer of a neural network, wherein the neural network is configured to produce a predictive value predicting a likelihood of an event associated with the user;
• and
• receiving, from an output layer of the neural network, the predictive value.

A non-transitory machine-readable medium having stored thereon machine-readable instructions executable to cause a machine to perform operations comprising:

• accessing data associated with a user, the data being further associated with a feature of a plurality of features and a data value;
• determining, for a set of one or more features of the plurality of features, an aggregate value, based on the data, for each feature of the set at one or more time intervals;
• inputting a time series including each aggregate value to an input layer of a neural network, wherein the neural network is configured to produce a predictive value predicting a likelihood of an event associated with the user;
• receiving, from an output layer of the neural network, the predictive value;
• determining the predictive value is at or above a threshold;
• and
• storing a tag indicating the predictive value is at or above the threshold in an account record associated with the user.