Visualizing interest charges based on payment options

An electronic payment system comprising:

• one or more processors;
• and
• memory storing instructions that, when executed by the one or more processors, cause the electronic payment system to:
• receive transaction information that is associated with a plurality of recurring payment accounts for a user;
• train a machine learning classifier to determine an optimal threshold amount for the plurality of recurring payment accounts associated with the user by:
• assigning, by the machine learning classifier, an initial threshold amount indicating a preferred threshold received from the user;
• generating, based on the initial threshold amount, one or more alerts associated with a historical calendar view, wherein the historical calendar view displays an aggregated daily balance associated with each of a plurality of historical dates, and an aggregated daily interest charge associated with each of the plurality of historical dates;
• receiving, from a user device, user correction action in response to the one or more alerts;
• and
• iteratively adjusting, by the machine learning classifier and based on the user corrective action, the initial threshold amount to generate the optimal threshold amount;
• detect that a projected daily interest charge exceeds the optimal threshold amount, wherein the projected daily interest charge is based on a calendar view of the transaction information of the plurality of recurring payment accounts;
• and
• after detecting that the projected daily interest charge exceeds the optimal threshold amount, send, to the user device, an alert recommending an alternative payment method.

One or more non-transitory media storing instructions that, when executed by one or more processors, cause the one or more processors to perform steps comprising:

• receiving transaction information that is associated with a plurality of recurring payment accounts for a user;
• training a machine learning classifier to determine an optimal threshold amount for the plurality of recurring payment accounts associated with the user by:
• assigning, by the machine learning classifier, an initial threshold amount indicating a preferred threshold received from the user;
• generating, based on the initial threshold amount, one or more alerts associated with a historical calendar view, wherein the historical calendar view displays an aggregated daily balance associated with each of a plurality of historical dates, and an aggregated daily interest charge associated with each of the plurality of historical dates;
• receiving, from a user device, user correction action in response to the one or more alerts;
• and
• iteratively adjusting, by the machine learning classifier and based on the user corrective action, the initial threshold amount to generate the optimal threshold amount;
• detecting that a projected aggregated daily interest charge exceeds the optimal threshold amount, wherein the projected aggregated daily interest charge is based on a calendar view of the transaction information of the plurality of recurring payment accounts;
• and
• after detecting that the projected aggregated daily interest charge exceeds the optimal threshold amount, sending, to the user device, an alert recommending an alternative payment method.