Adding manual signal features (Impact Severity, Energy Ratios) boosted Class 2 F1 score but caused...
Adding manual signal features (Impact Severity, Energy Ratios) boosted Class 2 F1 score but caused metric drop in Class 0 & 1, decreasing total leaderboard performance.
Root Causes
Multicollinearity: Re-creating Peak-to-RMS ratio when** Crest Factor** was already present.
- Dimensional Mismatch: Direct summation of unscaled velocity (mm/s) and acceleration (g).
-** Outlier Explosion**: Division by small RMS values creating extreme data spikes.
We built a feature that dominated our model's importance rankings. Across four random seeds and three...
In my agent fleet, role moves the metrics more than the model does — and the role mix differs per model, so pooled comparisons…
TL;DR A metrics engine had two query paths — a SQL push-down for big datasets, an...
Stop Shipping ML Models With Bare Floats Every week, somewhere, a team makes a deployment...
Too many experiment metrics can make meaningful changes harder to detect. Learn how Discord used simulations and Principal…
Thanks to Dipankar Sarkar, Mike Czerwinski, Max Quimby, and Ponsubash Raj R for the detailed comments...
