Add time-decay weighting support for ML spam detection#114
Merged
Conversation
Add configurable time-decay weighting w(t) = exp(-k * age_days) for ML training examples via ML_WEIGHT_DECAY_K env variable (default 0 = disabled). When enabled, recent messages have higher weight in model training, making the model more responsive to new spam patterns. Also add ml-experiment.fsx script for REPL-based comparison of baseline vs weighted models with per-interval precision/recall analysis. Co-authored-by: Cursor <cursoragent@cursor.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add configurable time-decay weighting w(t) = exp(-k * age_days) for ML training examples via ML_WEIGHT_DECAY_K env variable (default 0 = disabled). When enabled, recent messages have higher weight in model training, making the model more responsive to new spam patterns. Also add ml-experiment.fsx script for REPL-based comparison of baseline vs weighted models with per-interval precision/recall analysis.