Method and system for adjusting analytics model characteristics to reduce uncertainty in determining users' preferences for user experience options, to support providing personalized user experiences to users with a software system

A computer system implemented method for adjusting analytics model characteristics to reduce uncertainty in determining user preferences for user experience options, to support providing personalized user experiences to users, at least partially based on the user preferences, comprising:

• training a user experience analytics model, including:
• retrieving, with one or more processors, a plurality of existing user characteristics data for a plurality of existing users of a software system that provided services to the plurality of existing users, the plurality of existing user characteristics data representing a plurality of existing user characteristics for the plurality of existing users;
• identifying user experience options data representing user experience options received by the plurality of existing users from the software system, the user experience options being appliable to current user experiences in the software system to modify the current user experiences to improve a likelihood of causing particular user responses in the software system by at least some of a plurality of current users of the software system;
• analyzing, with the one or more processors, the plurality of existing user characteristics data and the user experience options data to generate a decision tree having nodes that correlate the plurality of existing user characteristics with the user experience options that were received by the plurality of existing users prior to the plurality of existing users performing at least some of the particular user responses,
• wherein each of the nodes is associated with one of a plurality of segments of existing users;
• and
• selectively splitting the nodes to increase a resolution of the decision tree with which the decision tree determines user preferences for the user experience options, at least partially based on one of a local stop probability and a minimum segment size threshold;
• applying current user characteristics data representing current user characteristics of the plurality of current users to the user experience analytics model to identify user preferences for the plurality of current users for the user experience options;
• generating personalized user experience display data including the user preferences for the plurality of current users for the user experience options identified by the user experience analytics model;
• and
• delivering the personalized user experience display data to user computing systems to improve the likelihood of causing particular user responses in the software system by at least some of the plurality of current users of the software system.

A system for adjusting analytics model characteristics to reduce uncertainty in determining user preferences for user experience options, to support providing personalized user experiences to users, at least partially based on the user preferences, comprising:

• a memory that stores information of users of a software system;
• one or more processors communicatively coupled to the memory to perform operations on the information of users of the software system;
• a system engine that receives, with the one or more processors, current user characteristics data and current user responses data from a plurality of current users, wherein the system engine stores the user characteristics data and the user responses data in the memory;
• a user experience analytics model training module that uses at least one of a local stop probability and a minimum segment size threshold to define a decision tree used by a user experience analytics model;
• and
• a decision engine that receives, with the one or more processors, the user characteristics data from the memory and applies the user characteristics data to the user experience analytics model to determine which of a plurality of user experience options to provide to users having user characteristics that are represented by the current user characteristics data, the user experience analytics model being configured to identify selected ones of the plurality of user experience options at least partially based on the current user characteristics data, the selected ones of the plurality of user experience options being probabilistically likely to cause the users to perform a particular task,
• wherein the system engine is configured to integrate the selected ones of the plurality of user experience options into user experience displays, and to host the user experience displays to provide personalized user experiences to the users at least partially based on the current user characteristics of the users to increase a likelihood that the users perform the particular task during user sessions with the software system.