In order to determine the likely intent and generate a dynamic conversational response that is both timely and pertinent, the methods and systems herein use one or more machine learning models. For example, the methods and system may use a two-tier machine learning model (e.g., a first machine learning model that feeds a second machine learning model, in which each model may be separately generated and/or trained). For example, the methods and systems disclosed herein may use the two-tier machine learning model to both quickly and accurately determine an intent of the user. The use of the two-tier machine learning model improves accuracy and precision, while providing the responses in a timely manner.

For example, aggregated information about the user action, information about the user, and/or other circumstances related to the user action (e.g., time of day, previous user actions, current account settings, etc.) may be used to generate a feature input (e.g., a vector of data) that expresses the information quantitatively or qualitatively. However, feature inputs for similar intents (e.g., a first intent of a user to learn his/her maximum credit limit and a second intent of a user to learn a current amount in his/her bank account) may have similar feature inputs as much of the underlying aggregated information may be the same. Moreover, training data for a machine learning model (e.g., known intents and labeled feature inputs) may be sparse. Accordingly, determining a specific intent of a user, with a high level of precision is difficult, even when using a machine learning model.