This website requires JavaScript.
Explore
Help
Sign In
morits
/
Airplay-Predictor
Watch
1
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
Packages
Projects
Releases
Wiki
Activity
Files
868d3cb96d302af7ba026838fef2e96f3fecbfe0
Airplay-Predictor
/
docs
T
History
morits
and
Claude Opus 5.5
1ff6b4bdd6
Comebacks and event backtest with iTunes release dates
...
Co-Authored-By: Claude Opus 5.5 <
noreply@anthropic.com
>
2026-11-19 15:19:00 +00:00
..
ADDCHECK.md
Knowable pool (artists enter only from their first release/play/chart/list/NMF), pooled out-of-sample recalibration (Platt vs isotonic; the site uses pooled Platt per channel, isotonic any channel), release-timing baseline, 8-week bootstrap blocks, surge-rule precision/recall vs the lists with a constant grid (docs/ADDCHECK.md); backtests restructured to score all variants with calibration tables
2026-11-16 00:34:30 +00:00
BACKTEST-ADDS.md
Knowable pool (artists enter only from their first release/play/chart/list/NMF), pooled out-of-sample recalibration (Platt vs isotonic; the site uses pooled Platt per channel, isotonic any channel), release-timing baseline, 8-week bootstrap blocks, surge-rule precision/recall vs the lists with a constant grid (docs/ADDCHECK.md); backtests restructured to score all variants with calibration tables
2026-11-16 00:34:30 +00:00
BACKTEST-EVENTS.md
Comebacks and event backtest with iTunes release dates
2026-11-19 15:19:00 +00:00
BACKTEST.md
Daily job parses new rotation lists and refits thresholds before ranking; fix backfill wait loop (pgrep -f matched its parent shell); NMF runs inside backfill.sh
2026-11-15 03:05:05 +00:00
CALIBRATION.md
Rotation thresholds fitted to DR's own lists (P3 23, P4 ~14, P6 16 plays/week: ~3x the old guess); IFPI 2010-2026 walk-forward test bed and route/lead-lag analysis; site and docs updated
2026-11-15 02:54:59 +00:00
COMEBACKS.md
Comebacks and event backtest with iTunes release dates
2026-11-19 15:19:00 +00:00
DATA_SOURCES.md
Collect daily instead of every 6 hours
2026-11-15 01:00:55 +00:00
IFPI.md
Rotation thresholds fitted to DR's own lists (P3 23, P4 ~14, P6 16 plays/week: ~3x the old guess); IFPI 2010-2026 walk-forward test bed and route/lead-lag analysis; site and docs updated
2026-11-15 02:54:59 +00:00
LONG.md
Long model: sustained-add target (blips were 58% of adds), sanity-check notes
2026-11-17 10:39:49 +00:00
MODELS.md
Knowable pool (artists enter only from their first release/play/chart/list/NMF), pooled out-of-sample recalibration (Platt vs isotonic; the site uses pooled Platt per channel, isotonic any channel), release-timing baseline, 8-week bootstrap blocks, surge-rule precision/recall vs the lists with a constant grid (docs/ADDCHECK.md); backtests restructured to score all variants with calibration tables
2026-11-16 00:34:30 +00:00
NMF.md
Synthetic lists: top-N rule (N = typical DR list size), 4-week blocks (weekly samples are noise); long-history features (archive presence 2012-21, DR lists before t); NMF analysis on full artist histories
2026-11-15 11:33:17 +00:00
SYNTH.md
Synthetic lists: top-N rule (N = typical DR list size), 4-week blocks (weekly samples are noise); long-history features (archive presence 2012-21, DR lists before t); NMF analysis on full artist histories
2026-11-15 11:33:17 +00:00