ML User Experience Prediction for Proactive Content Adaptation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for improving user experience based on net promoter scores (NPS) lack insight into specific elements that lead to higher NPS scores, resulting in changes that may satisfy one group of users while dissatisfying others.
Innovation Solution
A machine learning model is trained using clustering algorithms to predict user experience metrics and suggest interactive elements to enhance user experience, tailored to individual user characteristics and preferences.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If net promoter scores are collected after user interaction, then user experience feedback is obtained, but the content cannot be altered to improve user experience during their interactions
Solution Approach 1:
The system performs preliminary actions by predicting user experience metrics before the user completes their interaction. The machine learning model forecasts NPS scores and identifies suggested actions during the user session, enabling content modifications to be made proactively rather than reactively after feedback is received.
Solution Approach 2:
The system implements continuous feedback by monitoring user actions in real-time and using the machine learning model to predict experience metrics. This feedback loop allows the system to suggest content modifications based on predicted user satisfaction levels, enabling dynamic improvement of user experience during the interaction itself.
2Adaptability or versatility
If content is altered to improve user experience based on NPS, then some users are satisfied, but other users may be dissatisfied
Solution Approach 1:
The system applies local quality by generating personalized suggested actions tailored to each user's characteristics, preferences, and observed behavior. Instead of applying uniform content modifications to all users, the machine learning model predicts individual user experience metrics and recommends specific actions customized to each user's needs and preferences.
Solution Approach 2:
The system implements dynamics by making the content modification recommendations adaptive and changeable based on real-time user behavior. The suggested actions are not static but dynamically adjusted as the user interacts with the content, allowing the system to respond to changing user preferences and maintain satisfaction across diverse user groups.
3Loss of information
If driver questions are asked to understand user experience, then insights are gathered, but users often do not answer or provide insufficient information
Solution Approach 1:
The system implements self-service by automatically gathering user experience insights through passive monitoring of user actions and characteristics. Instead of requiring users to manually answer driver questions, the machine learning model analyzes user behavior patterns, preferences, and interaction data to automatically generate experience metrics and suggested actions, eliminating the need for user input while still gathering comprehensive insights.
Solution Approach 2:
The system replaces the mechanical system of explicit user questioning with an automated analytical system. The machine learning model substitutes for manual user responses by inferring experience metrics from observed user behavior, characteristics, and interaction patterns, thereby obtaining insights without requiring direct user input.
Data Source
AI summary
Described herein is a system for using a machine learning model to predict a metric value indicative of quality of user experience. The system can receive an indication that a mobile device was used to access electronic content. The system obtains a set of characteristics of a user of the mobile device and generates a predicted metric value indicative of a quality of user experience interacting with the electronic content by applying a trained machine learning model to the obtained set of characteristics. The machine learning model is trained on cluster data representing clusters of users of the system, and each cluster is associated with a one or more shared characteristics of users in the cluster and an average metric value selected by users in the cluster. The system selects and transmit an interactive element associated with the predicted metric value to the mobile device.