Commit Graph
26 Commits
Author SHA1 Message Date
moritsandClaude Opus 5.5 2e31b1dc49 Next week page: 1-week add forecast (daily run, isotonic-calibrated), /api/nextweek with live plays and track record, new tab; nextweek backtest
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-20 12:16:20 +00:00
moritsandClaude Opus 5.5 c61800a51f Release-event model: channels capped at the any-channel chance; stratified calibration and competition scaling tested (rejected); slots analysis; docs
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-20 01:33:26 +00:00
moritsandClaude Opus 5.5 a3b225fa48 History: boundary fix (spurious adds, dropped rows), archive rows subsampled, both models use archive at 0.3; optional any>=channel floor; ROC; docs
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-20 00:53:36 +00:00
moritsandClaude Opus 5.5 30fed60407 Per-channel history 2023- behind AIRPLAY_HISTORY=1: observation mask, Christmas re-entries out of the add target, archive weights; results in docs/HISTORY.md
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-19 23:03:06 +00:00
moritsandClaude 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
moritsandClaude Opus 5.5 5c02e8a710 Add model: quiet former favourite flag (DR archive 2019-24), subgroup scores in the event backtest
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-17 13:02:08 +00:00
moritsandClaude Opus 5.5 7e2764ce8c Comebacks report: adds by prior status, release coverage, post-release add rates
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-17 11:18:24 +00:00
moritsandClaude Opus 5.5 9cd227755b Long model: sustained-add target (blips were 58% of adds), sanity-check notes
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-17 10:39:49 +00:00
moritsandClaude Opus 5.5 79b2cdc425 Long any-DR model on 2019- archive pages: all years vs 1 year backtest
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-17 09:58:17 +00:00
moritsandClaude Opus 5.5 0e511e1e0b Default window 2 weeks (1-week option added) on the site, best week and what-if; new-song backtest takes the window (--w, default 2)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-16 12:32:28 +00:00
moritsandClaude Opus 5.5 37b3029e02 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
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-16 00:34:30 +00:00
moritsandClaude Opus 5.5 94abfa0255 Old DR artist pages from the Wayback Machine (53 weeks of plays per capture, 2019-2024) into dr_artist_history; leak fixes (weeks since last add counts only adds up to t-1; training windows close a week before the origin) and a leak test (model leakcheck) that rebuilds every feature from data cut at the origin; backtests split pre-release (NMF from history) and post-release (NMF known); site shows the new-song backtest
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-16 00:22:55 +00:00
moritsandClaude Opus 5.5 7a16eb45ef Describe the surge-based add on the site and in the backtest report
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-15 13:18:43 +00:00
moritsandClaude Opus 5.5 cb5224fc4f Surge-based adds (onset, or plays jumping well above the artist's own baseline and staying up): finds 77% of DR's real song adds vs 64% for onset only; addcheck validation against the lists
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-15 13:04:22 +00:00
moritsandClaude Opus 5.5 bc222d3cd0 Channel affinity (share of the artist's DR plays per station before t, never played there) and genre fit (DR genre x station) in the per-station rows; Best week: any date range up to 12 months
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-15 13:00:34 +00:00
moritsandClaude Opus 5.5 3699944692 Release-week calendar: adjustable window (2-12 weeks, one release-event model each), time-since features moved to the release week, 'too soon' instead of special cases, season index (IFPI 2002-24) in the window; site: Best week tab, live ranking for any release week and window, single new-song view
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-15 12:24:01 +00:00
moritsandClaude Opus 5.5 347680bc9e Release-event model: 'if the artist releases a new song, will DR add it' trained on clean releases (no other release in the 6 weeks before), with its own walk-forward test; ranking defaults to it and leaves out artists who just released; pool note updated
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-15 11:59:58 +00:00
moritsandClaude Opus 5.5 e94601b997 NMF Denmark in the add model (placed in the window, top 10, history), scenario type (release / NMF) for the ranking and the what-if; NMF Denmark export
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-15 11:43:52 +00:00
moritsandClaude Opus 5.5 e6b080246b 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
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-15 11:33:17 +00:00
moritsandClaude Opus 5.5 7d656834fb Docs: pool, releases, NMF, Bauer, recalibration; model commands in the README
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-15 03:36:27 +00:00
moritsandClaude Opus 5.5 33a3c3f2e5 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
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-15 03:05:05 +00:00
moritsandClaude Opus 5.5 bbfb437011 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
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-15 02:54:59 +00:00
moritsandClaude Opus 5.5 eededc7571 Models, first layer: artist × DR channel × week panel with IFPI chart history; NB and logit direct h-step models, Kalman artist form, persistence/popularity baselines; walk-forward backtest (docs/BACKTEST.md) and the ranking (forecasts table)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-15 02:08:48 +00:00
moritsandClaude Opus 5.5 411b55fb9f docs: daily collection
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-15 01:00:58 +00:00
moritsandClaude Opus 5.5 1af37804b3 Collect daily instead of every 6 hours
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-15 01:00:55 +00:00
moritsandClaude Opus 5.5 6e4d2f1585 Collector for DR and Bauer airplay; data sources and modelling plan
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-15 00:42:05 +00:00