ML Feature Reuse Suggestions From User Interaction Signals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge of efficiently discovering and reusing suitable features from existing machine learning models during the creation of new models is not adequately addressed, leading to missed opportunities for improving the output and expediting the development and deployment of new models.
Innovation Solution
A system and method that monitors user interactions to detect events triggering suggestions, performs searches for relevant existing data, presents suggestions for reusing model components, and adapts based on user feedback to enhance the development process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual search and selection of existing model features is performed, then precision of feature selection can be controlled by user expertise, but time consumption and labor intensity increase significantly
Solution Approach 1:
The system performs self-service by automatically monitoring user interactions, detecting triggering events, searching data sources for relevant existing model features, and presenting suggestions without requiring manual user search. This automation eliminates the time-consuming manual search process while maintaining precision through event-driven relevance detection.
Solution Approach 2:
The system implements feedback mechanisms by receiving user feedback on presented suggestions and generating updated suggestions in response. This continuous feedback loop ensures that the feature selection precision is maintained and improved over time, while the automated nature of the process eliminates manual search time requirements.
2Loss of time
If automated suggestion system is implemented, then time consumption is reduced, but system complexity increases
Solution Approach 1:
The system segments the complex automated suggestion process into distinct functional modules: interaction monitoring, event detection, data source search, suggestion generation, and feedback processing. Each module handles a specific aspect of the workflow, making the overall complex system more manageable and maintainable while achieving time reduction through automation.
3Productivity
If existing model features are reused, then development speed increases, but risk of bias propagation from existing models increases
Solution Approach 1:
The system uses feedback mechanisms to receive user input and feedback on suggested features, allowing users to review and validate selected features before incorporation. This feedback loop enables users to identify and reject potentially biased features while maintaining the productivity benefits of automated suggestion and feature reuse.
Data Source
AI summary
A method performed by a processing system including at least one processor includes monitoring interactions of a human user with a platform for building machine learning models, where the human user is using the platform to build a new machine learning model, detecting, within the interactions, an event that triggers a suggestion feature, performing a search of a data source for existing data from existing machine learning models which can be reused to build the new machine learning model, using information about the event, presenting a suggestion to the human user to reuse a portion of the existing data discovered in the search in the new machine learning model, receiving a user feedback in response to the suggestion, and generating an updated suggestion in response to the user feedback.