Binary Classifier for Work-Item Notification Importance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current issue tracking systems (ITS) generate numerous work-item notifications, overwhelming users with both important and unimportant updates, requiring manual filtering, which is inefficient and unproductive, especially for project managers and team leads.
Innovation Solution
A system that uses a trained binary classifier to analyze work-item notifications based on past and current work-item history, user profiles, and user interactions to predict the classification of notifications as 'important' or 'unimportant', reducing unnecessary notifications and improving user focus on relevant updates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual filtering of notifications is implemented, then users can isolate important notifications, but user productivity decreases due to time-consuming manual isolation
Solution Approach 1:
The system automatically classifies notifications as important or unimportant based on work-item attributes and user preferences without requiring manual user intervention. The classifier self-serves by analyzing notification data and assigning importance levels autonomously
Solution Approach 2:
The manual mechanical process of users reading and filtering notifications is replaced with an automated binary classifier system that uses machine learning algorithms to automatically sort and prioritize notifications based on trained models
2Loss of information
If all work-item notifications are transmitted to users, then users receive complete information, but notification overload occurs reducing user focus on critical updates
Solution Approach 1:
The system extracts and separates unimportant notifications from the overall notification stream using a binary classifier. Important notifications are identified and retained for user attention, while unimportant ones are filtered out or marked accordingly
Solution Approach 2:
Different quality levels of notifications are assigned based on their importance classification. Important notifications receive prominent display and attention, while unimportant notifications are subdued or batched, creating local quality differentiation in the notification presentation
3Adaptability or versatility
If manual configuration of notification preferences is provided, then users can customize notification receipt, but system complexity increases requiring manual setup
Solution Approach 1:
The system performs self-configuration by automatically learning user notification preferences through the binary classifier. Instead of requiring users to manually configure preferences, the system observes work-item patterns and autonomously adapts notification filtering to user needs
Data Source
AI summary
Embodiments of the present invention provide a system, method, and program product for predicting the classification of a work-item notification generated by an issue tracking system. A computing device analyzes a new work-item notification using a trained binary classifier that was trained using at least a past and/or current work-item history that was collected as a tuple that includes information reflecting the workitem-ID, actor, timestamp, attribute, work-item start-value, and work-item end-value. The computing device, in response to analyzing the new work-item notification, predicts a classification of the new work-item notification. In an embodiment, the classification is used for display of the new work-item notification.