Probabilistic Prediction Model Revision via Social Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing prediction models are preprogrammed and fail to adjust probability distributions based on new inputs not considered in training data, and do not effectively utilize social inputs to modify predictions.
Innovation Solution
A method and system for social collaboration in probabilistic prediction that allows users to input new predictions, which are used to revise prediction models, considering user categories and weights to adjust probability distributions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If prediction models are preprogrammed with fixed training data, then model structure and training process are simplified, but the models cannot adjust probability distributions based on new inputs not considered in training data
Solution Approach 1:
The system implements feedback by receiving new predictions from users, comparing them with existing model predictions, and using this feedback to revise the prediction model. The feedback mechanism allows the model to learn from discrepancies between its predictions and user-provided predictions, enabling adaptation to new inputs while maintaining a structured revision process through automated comparison and weighted integration of user inputs.
2Reliability
If prediction models do not incorporate social inputs, then model structure remains simple, but the models fail to effectively utilize user feedback to modify predictions
Solution Approach 1:
The system introduces an intermediary mechanism that processes social inputs from multiple users before integrating them into the prediction model. This intermediary layer handles user authentication, input validation, weighting based on user categories, and aggregation of predictions, thereby enabling reliable incorporation of social feedback while managing complexity through structured intermediate processing steps rather than direct model modification.
3Reliability
If the system incorporates user inputs and social feedback to revise models, then prediction accuracy improves, but the processing time and computational resources increase
Solution Approach 1:
The system applies partial action by selectively revising only those aspects of the prediction model that are most affected by user feedback, rather than completely retraining the entire model. The revision process focuses on adjusting probability distributions and specific model parameters based on the magnitude and relevance of feedback, thereby improving prediction accuracy while minimizing the time and computational resources required compared to full model retraining.
Data Source
AI summary
A method, system, and computer program product for social collaboration in probabilistic prediction are provided in the illustrative embodiments. A set of predictions is sent to a user device. A prediction in the set of predictions is a probability of an outcome of an event. The probability is computed using a prediction model trained with training data corresponding to the event. An input is received from the user device. The input comprises a new prediction made at the user device using a new prediction model executing on the user device. A difference is determined between the prediction and the new prediction. The prediction model is revised to produce a revised prediction. A revised difference between the revised prediction and the new prediction is smaller than the difference.