We graded a model that fills in tick data from one-minute bars. It misses the minutes that matter.
Part two of the breakout series. Last time we said we were training a model to fill in trade-by-trade detail from one-minute bars, with grades fixed before the first run. Here are the grades - all fifteen fields, including the ones that failed. How it was graded Trained on 150 days; graded on 90 da…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-11-19 14:05 · DEV Community — Machine Learning
We graded a model that fills in tick data from one-minute bars. It misses the minutes that matter.