Simulations using a token exchange system

A computer-readable storage medium storing instructions that, when executed by a computing system, cause the computing system to simulate a goal state using token conversions, the process comprising:

• receiving goal information comprising an amount and a goal date criteria;
• generating, by an automated agent, a token conversion schedule comprising a goal date and multiple instances of goal token conversions based on the goal information, features of an account, and features of a user, wherein the features of the account comprise at least changes to the account balance over time and the features of the user comprise at least an aggregate account balance for the user across multiple accounts;
• performing, by the automated agent, conversions of account balance to tokens by automatically performing updates to a data structure that manages, for the account, a number of tokens in the account;
• receiving user-initiated changes that convert goal tokens to account balance or account balance to goal tokens;
• and
• generating, by the automated agent using a trained machine learning model, a modified token conversion schedule that comprises a modification to the goal date based on the user-initiated changes, wherein the machine learning model is trained using historical data representative of:
• a) past token conversion schedules, and b) outcomes for the past token conversion schedules, and the modified token conversion schedule is displayed as a graph comprising goal token amounts over time.

A computing system for simulating a goal state using token conversions, the system comprising:

• one or more processors;
• and
• one or more memories storing instructions that, when executed by the one or more processors, cause the computing system to perform a process comprising:
• receiving goal information comprising an amount and a goal date criteria;
• generating, by an automated agent, a token conversion schedule comprising a goal date and multiple instances of goal token conversions based on the goal information, features of an account, and features of a user, wherein the features of the account comprise at least changes to the account balance over time and the features of the user comprise at least an aggregate account balance for the user across multiple accounts;
• performing, by the automated agent, conversions of account balance to tokens by automatically performing updates to a data structure that manages, for the account, a number of tokens in the account;
• receiving user-initiated changes that convert goal tokens to account balance or account balance to goal tokens;
• and
• generating, by the automated agent using a trained machine learning model, a modified token conversion schedule that comprises a modification to the goal date based on the user-initiated changes, wherein the machine learning model is trained using historical data representative of:
• a) past token conversion schedules, and b) outcomes for the past token conversion schedules, and the modified token conversion schedule is displayed as a graph comprising goal token amounts over time.