Research Library

Do shift-derived ice time minutes improve shots-on-goal predictions? (2026-10-05) 2026-10-05 · 1kb

Data: NHL shift charts 2021-22..2025-26 (6,936 games, ~5.3M shifts; 57 2024-25 games missing from the NHL feed) → player_games (TOI by EV/PP/PK + SOG). Regular season only. Scored 2022-23..2025-26: 169,298 player-games with ≥ 5 prior games. Every prediction is…

backtests/nhl_eval/FINDINGS_SOG_TOI.md

NHL Stacking v3 — De-Snooping Campaign Findings · 16kb

Model: nhl_stacking_v3 (production's only currently-profitable model) Scope: honest, de-snooped performance measurement + hygiene-fix evaluation — NOT a search for new alpha Data: [redacted], 17,155 regular-season games, 2008–2024 (nhl_games join …

backtests/nhl_eval/FINDINGS.md

College hockey betting angles backlog (2026-09-29) 2026-09-29 · 3kb

Context. The model loses to the market (FINDINGS_MODEL_VS_MARKET.md): log loss 0.625 vs 0.603. Fading it also loses. Anything that squeezes more prediction out of the same stats is dead. These angles are timing ones, or use information the line may not have.

backtests/college_hockey_eval/ANGLES_BACKLOG.md

Pre-registration: roster turnover vs the October market (2026-27) 2026-27 · 3kb

Frozen 2026-09-29, before the season's first puck drop on 2026-10-02. The commit containing this file, forward_2026_team_ratings.json and roster_turnover_forward.py is the record. Nothing in them changes after 2026-10-02. Any later change goes in an "Amendment…

backtests/college_hockey_eval/PREREG_ROSTER_TURNOVER_2026.md

College hockey model vs the betting market (first comparison, 2026-09-29) 2026-09-29 · 2kb

The market is better than the model, and the model adds nothing to it.

backtests/college_hockey_eval/FINDINGS_MODEL_VS_MARKET.md

Is a Left-Handed Quarterback Worth Anything Over a Right-Handed One? · 9kb

Short answer: there's no measurable value either way, and the data can't settle it. Handedness produces one large, specific, measurable difference — lefties throw to the left side of the field much more — but that difference doesn't turn into efficiency, and r…

backtests/qb_handedness/FINDINGS.md

Do the Injury-Aware Multipliers Actually Improve Projections? 2026-09-26 · 6kb

Validation of commit 02fba14, which replaced the projection engine's injury multiplier table using results from backtests/nfl_context_signals/FINDINGS.md.

backtests/fantasy_eval/FINDINGS_INJURY_MULTIPLIERS.md

If an Injured Player Suits Up, What Does He Score? shipped · 9kb

Follow-up to FINDINGS_INJURY_MULTIPLIERS.md, which shipped an expected-value injury multiplier and left the conditional one — "if he is active, what should I expect?" — as an aside: ~0.82 / 0.92 / 0.97 relative to healthy for DNP / Limited / Full. Nothing in t…

backtests/fantasy_eval/FINDINGS_INJURY_CONDITIONAL.md

Depth-chart multiplier damp — re-measured after the input fix (2026-09-12) 2026-09-12 · 2kb

Verdict: keep 0.4. Mean error is flat across the damp; what moves is bias.

backtests/fantasy_eval/FINDINGS_DEPTH_DAMP.md

Snap Counts + Depth Charts Close ~30% of the ECR Gap 2026-07-19 · 13kb

Date: 2026-07-19 · Season: 2025, weeks 7–17 · Harness: snap_depth_experiment.py → snap_depth_experiment_results.json · Seed: 20260719

backtests/fantasy_eval/FINDINGS_SNAP_DEPTH.md

Cross-player usage redistribution: the effect is real, the projection gain is not rejected 2026-08-31 · 3kb

Date: 2026-08-31 · Verdict: ❌ REJECTED — usage_redistribution = False

backtests/fantasy_eval/FINDINGS_USAGE_REDISTRIBUTION.md

Backup QB: shade the receivers, not the quarterback shipped 2026-08-31 · 2kb

Date: 2026-08-31 · Verdict: ✅ SHIPPED, receiving only

backtests/fantasy_eval/FINDINGS_BACKUP_QB.md

Train / dev / holdout: what the accuracy numbers are actually worth 2026-08-30 · 2kb

Date: 2026-08-30 · Report: scripts/report_split_accuracy.py (re-runnable)

backtests/fantasy_eval/FINDINGS_EVAL_SPLIT.md

Two dead knobs: one was worth fixing, one was worth measuring and leaving off shipped 2026-08-30 · 2kb

Date: 2026-08-30 · Harness: evaluate_fantasy_mae.py --set <knob>=true

backtests/fantasy_eval/FINDINGS_PACE_AND_ROSTERS.md

Start/sit accuracy of the shipped surface shipped 2026-08-30 · 1kb

Date: 2026-08-30 · Harness: start_sit_live_accuracy.py (re-runnable)

backtests/fantasy_eval/FINDINGS_START_SIT_LIVE.md

Floor/ceiling were covering half the outcomes they claimed 2026-08-30 · 2kb

Date: 2026-08-30 Verdict: ✅ FIXED — empirical residual quantiles replace the simulated band

backtests/fantasy_eval/FINDINGS_INTERVALS.md

The team+position "soup" is not a bug — it beats the clean matcher rejected 2026-08-30 · 2kb

Date: 2026-08-30 Harness: scripts/evaluate_fantasy_mae.py --set unified_player_matching=true|false Verdict: ❌ REJECTED — keep unified_player_matching = False

backtests/fantasy_eval/FINDINGS_PLAYER_MATCHING.md

Volume features: do they add anything on top of the snap re-ranker? shipped 2026-08-30 · 3kb

Date: 2026-08-30 Harness: backtests/fantasy_eval/volume_features_experiment.py (re-runnable) Verdict: ✅ SHIPPED — small but consistent incremental gain

backtests/fantasy_eval/FINDINGS_VOLUME_FEATURES.md

TD models: not unpredictable, just pointed at the wrong output 2026-08-30 · 3kb

Date: 2026-08-30 Harness: backtests/fantasy_eval/td_probability_experiment.py (re-runnable) Verdict: ✅ PARTIAL — ships for rushing and receiving TDs, NOT for passing TDs

backtests/fantasy_eval/FINDINGS_TD_PROBABILITY.md

Our Fantasy Projections vs FantasyPros Expert Consensus (ECR) 2026-07-19 · 9kb

Our side is the strict walk-forward regeneration from scripts/evaluate_fantasy_mae.py --dump-projections (2,438 player-weeks): the engine is fed one historical week at a time and may only use data from before the week it projects. Unlike the 2024 db rows, this…

backtests/fantasy_eval/FINDINGS_VS_ECR.md

The Close Band Can Be Improved (+2.5pp, ~half the ECR gap) 2026-07-20 · 3kb

Date: 2026-07-20 · Harness: close_band_experiment.py · Sample: 12,510 close pairs of 56,046, 2025 weeks 5–17 · Seed: 20260719

backtests/fantasy_eval/FINDINGS_CLOSE_BAND.md

Start/Sit Decision Accuracy — 2025 2026-07-19 · 3kb

Date: 2026-07-19 · Harness: start_sit_accuracy.py · Sample: 64,150 within-(week, position) pairs, 2025 weeks 5–17 · Seed: 20260719

backtests/fantasy_eval/FINDINGS_START_SIT.md

Game quality — opponent-adjusted EPA, 2016–2025 shipped 2026-09-14 · 4kb

2026-09-14. validate.py → validate_results.json. Shipped as /nfl/game-quality (scripts/nfl/build_game_quality.py → [redacted]).

backtests/nfl_game_quality/FINDINGS.md

How well does the public pick? — field baseline, 2014–2025 2026-09-13 · 4kb

2026-09-13. field_baseline.py → field_baseline_results.json (gitignored). Source: NFL Pickwatch per-game pick shares, captured by scripts/nfl/capture_pickwatch.py into [redacted] (weekly cron, Tue 14:00 UTC). Lines and results come from nflverse, not…

backtests/pickem/FINDINGS_FIELD_BASELINE.md

Winning a 30-Person Confidence Pool 2026-07-20 · 11kb

Date: 2026-07-20 · Harness: pool_strategy_sim.py → pool_strategy_sim_results.json · 6,000 simulated seasons per regime · Seed: 20260720

backtests/pickem/FINDINGS_POOL_2026.md

Testing "always pick the favorite" — and why a Monte Carlo can't do it 2026-08-12 · 5kb

2026-08-12. calibration_test.py, 6,937 REG games, 1999–2025.

backtests/pickem/FINDINGS_CALIBRATION_2026.md

Season Prize vs Weekly Prize: Shoot for the Season 2026-07-20 · 5kb

Date: 2026-07-20 · Harness: pool_ev_analysis.py → pool_ev_analysis_results.json · 4,000 simulated seasons per regime · Seed: 20260720

backtests/pickem/FINDINGS_EV_2026.md

Best Pick'em Strategy for 2026: Pick Every Favorite 2026-07-20 · 6kb

Date: 2026-07-20 · Harness: strategy_search_2026.py → strategy_search_2026_results.json · Data: 2,119 REG games, 2018–2025 · Seed: 20260720

backtests/pickem/FINDINGS_STRATEGY_2026.md

Confidence Pick'em — Honest Rebuild (2018–2025) 2026-07-20 · 4kb

Date: 2026-07-20 · Harness: backtest_pickem.py → backtest_pickem_results.json · Sample: 2,119 completed regular-season games · Seed: 20260720

backtests/pickem/FINDINGS.md

Pick'em tiebreakers: what to actually guess 2026-09-09 · 4kb

2026-09-09. 2,895 games and 192 full weeks, 2015-2025, against closing lines.

backtests/pickem_tiebreak/FINDINGS.md

Can we build our own WAR? What the data will and won't support 2026-09-08 · 8kb

2026-09-08. 227,398 scrimmage plays, 2019-2025.

backtests/nfl_war/FINDINGS.md

What injuries and suspensions actually cost (NFL) 2026-09-08 · 5kb

2026-09-08. 2,176 team-weeks, 2022-2025, from nflverse weekly rosters joined to snap counts and closing lines.

backtests/injury_impact/FINDINGS.md

What does transferring actually do? (college hockey) 2026-09-08 · 5kb

2026-09-08. 5,494 skater and 307 goalie player-season pairs, 2020-2024, from college_hockey_player_game_stats joined to the transfer sheet ingested in e5746b5. A pair is a player who appears in season N and again in N+1, so both sides of a move are observed.

backtests/player_movement/FINDINGS_TRANSFERS.md

Detecting departures without an early-departure list 2026-09-08 · 3kb

2026-09-08. We have no historical early-departure data, so the working premise was: read departures off game-1 rosters instead, accepting that we only learn them once the season starts and so cannot forecast with them.

backtests/player_movement/FINDINGS.md

What is worth borrowing from Silver's ELWAY post no edge 2026-09-08 · 5kb

2026-09-08. Assessment of the free portion of natesilver.net/p/2026-elway-nfl-ratings-projections-playoff-odds, pasted by the user (the page is paywalled and renders as a JS shell from this server).

backtests/elway_review/FINDINGS.md

Kicker and DST fantasy projections — feasibility study 2026-09-07 · 5kb

2026-09-07. 3,614 kicker-games and 3,648 defense-games, 2019-2025 regular season, built from nflverse play-by-play; closing lines from load_schedules (100% coverage). Scoring: standard K (FG <40 = 3, 40-49 = 4, 50+ = 5, miss = -1, XP = 1) and standard DST (poi…

backtests/kicker_dst/FINDINGS.md

Fantasy/prop model audit — what is measurable, what is predictable, what to build 2026-08-30 · 8kb

2026-08-30. Four parallel investigations: published literature, evaluation methodology, current engine features, and available data. Verdict up front:

backtests/fantasy_model_audit/FINDINGS.md

Betting late beats betting early — ~+0.9pp CLV, NCAAB moneylines 2026-08-28 · 3kb

2026-08-28. The pipeline alerts whenever it finds an edge, at any distance from kickoff, and nothing has ever checked whether that distance matters.

backtests/bet_timing/FINDINGS.md

Middles don't clear the vig — not even with perfect hindsight 2026-08-28 · 2kb

2026-08-28. First study enabled by the results join (1936e7d), which attached final scores to the 10-book line history in unified_odds.db. Middling is a structural strategy — bet both sides at different numbers, win both if the result lands between — so it bel…

backtests/middles/FINDINGS.md

Teaser/parlay legs are independent — the correlation worry was unfounded 2026-08-28 · 2kb

2026-08-28. The teaser EV maths multiplies per-leg probabilities, which assumes the legs are independent. That assumption was flagged as unmeasured and it drives a live decision (2-team vs 3-team teaser). Measured it on 11 seasons of NFL schedules (2015–2025, …

backtests/leg_correlation/FINDINGS.md

The `stable` movement filter is unvalidated — and unfalsifiable as deployed shipped 2026-08-28 · 3kb

2026-08-28. ev_finder.py silently discards every opportunity classified movement_class == 'stable' before it can alert. It has done so since ~13 Feb 2026, on the strength of one number: −17.76% ROI, N=411, p=0.0005.

backtests/stable_filter_audit/FINDINGS.md

Pre-registration: per-market CLV judging, 2026-27 season 2026-27 · 12kb

Written 2026-08-24. Locked before the season starts. Status: ACTIVE — no data has been observed under this rule.

backtests/ev_clv_prereg_2026_09/PREREGISTRATION.md

The CLV "line-match bug" is a missing-data problem, not a maths error 2026-08-24 · 10kb

2026-08-24. Investigated because mlb/totals and nba/spreads showed absurd CLV capture coverage (39% and 18%) together with anomalously small dispersion — nba/spreads sd 0.93 against nba/h2h sd 3.31 in the same sport. Low coverage plus compressed variance is th…

backtests/clv_line_adjustment/FINDINGS.md

EV Alert Pipeline — Record Review, August 2026 2026-07 · 12kb

Review of the live EV alert record and the config changes made as a result. Data: [redacted], 12,821 alerts (Feb–Aug 2026), 12,718 settled win/loss. This is the deduped store (write-time dedup added 2026-07; history collapsed 34.7k → 12.6k), so rows are…

backtests/ev_record_2026_08/FINDINGS.md

Did the Weather + FTN Features Actually Earn Their Keep? no edge · 8kb

Measurement of commit 7ba65e1, which wired real Open-Meteo weather and trailing FTN charting features into the fantasy projection engine and the betting feature builder.

backtests/weather_ftn_value/FINDINGS.md

Do QBs Have a Persistent "Weather Sensitivity" Trait? · 14kb

One-off study, not a model, not production. Prompted by a film-study claim that QBs with a U-shaped release (Tua) struggle in wind/precipitation while C-shaped releases (Josh Allen) hold up, because of how the throwing motion interacts with weather.

backtests/qb_weather/FINDINGS.md

Four NFL Context Signals: Are They Real, and Are They Already Priced? decisive null · 19kb

One-off study, not a model, not production. Four hypotheses the user raised as interesting: contract-year motivation, referee crew tendencies, injury-report signal, and backup-QB drop-off. Each is tested twice — Stage A: is the effect real? and Stage B: is it …

backtests/nfl_context_signals/FINDINGS.md

Does NFL Preseason Performance Predict Regular-Season Outcomes? · 9kb

One-off study, not a model, not production. Question from [[preseason_signal_todo]]: does preseason performance carry real signal for regular-season outcomes, for teams, rookies, and vets separately? Short answer: no, on all three counts —

backtests/preseason_signal/FINDINGS.md

NFL Hierarchical Usage Model — Evaluation vs Baselines 2026-07-14 · 11kb

Date: 2026-07-14 · Seed: 20260714 · Harness: model_usage.py → results/usage_model_results.json + results/usage_model_predictions.parquet (88,724 walk-forward player-week-prop rows, 88 folds, 2021–2024 test seasons, 3,000 MC samples/row).

backtests/nfl_prop_usage/FINDINGS.md

NFL Prop Usage Model — Design Doc (Step 1: data + walk-forward harness) · 6kb

Status: data layer + fold generator only. No model is fit yet. Deterministic seed 20260714. House rules apply: judge downstream models vs devigged closing lines, walk-forward only, cluster bootstraps by game_id / player_week_id, honest negative results are val…

backtests/nfl_prop_usage/DESIGN.md

Home Run Derby: Selection & the "Post-Derby Slump" · 10kb

One-off descriptive study — not a model, not production. All code/data under backtests/hr_derby/. n is tiny (~122 participant-slots over 15 Derbies); everything below is bounded, not proven. Adversarial check verdict: sound (regression-to-the-mean explicitly h…

backtests/hr_derby/FINDINGS.md

College Eval Tracks 1+2 (NCAAB + CFB) — Synthesis, 2026-07-13 2026-07-13 · 18kb

Verification method: independently re-opened the artifact files each build points to (walkforward_regen_results.json, replicate_spike_gate_result.json for CFB; production_clv_results.json for NCAAB) and diffed the build's prose numbers against the JSON on disk…

backtests/COLLEGE_EVAL_TRACKS_1_2_2026_07.md

Calibration Hygiene Campaign — Item 6 Synthesis rejected 2026-07-12 · 9kb

Date: 2026-07-12 | Scope: 5 tracks, adversarially checked | House framing: calibration is hygiene, not alpha — a change ships only if it clears a market-relative gate, never on ECE/log-loss improvement alone.

backtests/CALIBRATION_HYGIENE_2026_07.md

Upgrade Experiments 2026-07 — Item 5 Synthesis 2026-07 · 11kb

Gate discipline reminder (house rule): walk-forward only, log-loss/MAE wins that worsen market-relative numbers don't ship, three clean FAILs would be a perfectly good outcome. All three experiments below cleared their pre-registered gates on the letter of the…

backtests/UPGRADE_EXPERIMENTS_2026_07.md

CFB-2b promotion spec — surface the walk-forward table on `/cfb/performance` null 2026-04-27 · 8kb

Status: SPEC ONLY — not applied. Ground rule for this task forbids editing production files or the route; this is the precise plan for the owner to apply.

backtests/cfb_eval/PROMOTION_SPEC_2b.md

CFB-2a promotion spec — market arm in `scripts/calibrate_models.py` 2022-20 · 9kb

Status: SPEC ONLY — not applied. Ground rule for this task forbids editing production files; this is the precise diff for the owner to apply by hand.

backtests/cfb_eval/PROMOTION_SPEC.md

NCAAB Production-Model CLV Eval — 2026-07-13 rejected 2026-07-13 · 3kb

First market-relative evaluation of the production NCAABPredictionEngine (college-models-review Track 1; plan ~/.claude/plans/keen-bouncing-spark.md). Reuses backtests/stacking_eval/ncaab/ plumbing (closing-line pull, multiplicative devig, name-match, scoring,…

backtests/ncaab_eval/REPORT.md

Tennis Elo Backtest Reconciliation — 2026-07-12 null 2026-07-12 · 16kb

Why: the live tennis_elo_v1 scanner's DEFAULT_MIN_EDGE=5% gate traced to a deleted script (cleanup 7ef5f27) whose +6.25% WTA-grass claim was contradicted by backtests/stacking_eval/tennis. Methodology review action item 3.

backtests/tennis_eval/FINDINGS.md

FDR-Controlled Retrosheet Split Miner -- Findings 2000-20 · 5kb

Data: 4,706,329 plate appearances, seasons 2000-2025. Discovery <= 2018, validation after. BH q=0.05, discovery cell floor=100 per side per outcome. Runtime 462.9s.

backtests/split_miner/REPORT.md

002 12-1 Momentum — Factor Attribution 2015-03 · 2kb

Generated by backtests/common/factor_attribution.py (DATA_SOURCES_ROADMAP.md item #8). Regresses monthly strategy returns on the Fama-French 3 factors (Mkt-RF, SMB, HML) plus momentum (UMD) via data_loader.factor_returns('M'). No P&L impact — this is a measure…

backtests/strategies/002_momentum_12_1_FACTOR_ATTRIBUTION.md

Tennis consensus-stacking evaluation — REJECT (2026-07-04) rejected 2026-07-04 · 1kb

A full historical backtest was possible: [redacted]::tennis_matches (81,622 matches 2010-2026 with embedded closing odds: market average, Pinnacle, best price) + tennis_match_elo (point-in-time pre-match Elo, through 2024-11-17). Joined usable set: 69,090 …

backtests/stacking_eval/tennis/REPORT.md

NCAAB consensus-stacking evaluation — REJECT (2026-07-04) rejected 2026-07-04 · 1kb

The best-prior candidate (soft small-conference markets), tested on our largest capture. Verdict: consensus wins everything.

backtests/stacking_eval/ncaab/REPORT.md

MLB consensus-stacking pilot — INSUFFICIENT DATA, leaning REJECT (2026-07-04) rejected 2026-07-04 · 1kb

Question: does blending the pitcher-adjusted Elo v2 prob into the devigged closing consensus (NHL v3 recipe) beat consensus-only?

backtests/stacking_eval/mlb/REPORT.md

NFL consensus-stacking evaluation — REJECT (2026-07-04) rejected 2026-07-04 · 1kb

Question: does the NHL v3 "top-down" recipe (tiny logistic on devigged closing consensus + small orthogonal features) beat the NFL closing moneyline?

backtests/stacking_eval/nfl/REPORT.md

Kelly-sizing simulation across site models — 2026-07-04 2026-07-04 · 2kb

Question: would any model be profitable with Kelly sizing? Method: reproduce each model's walk-forward probabilities, replay against real closing odds, bankroll sims (100u start) under flat / quarter / half / full Kelly, two selection rules (favored-side-alway…

backtests/kelly_sim/FINDINGS.md

NFL Edge Research — July 2026 (offseason build window) no edge 2026-07-02 · 9kb

Date: 2026-07-02. All code in this directory; nothing in production was touched. All results below are graded against closing lines, flat stakes, pushes excluded, one bet per pick (dedup'd). Given the July 2026 track-record audit, every historical "NFL record"…

backtests/nfl_edges/FINDINGS.md

Strategy 002: 12-1 Cross-Sectional Momentum · 3kb

Jegadeesh & Titman, Returns to Buying Winners and Selling Losers (Journal of Finance, 1993). Still one of the most-replicated equity anomalies.

backtests/docs/002_momentum_12_1.md

Strategy 009: Insider Cluster Buying · 2kb

Cohen, Malloy & Pomorski, Decoding Inside Information (Journal of Finance, 2012). Also Lakonishok & Lee (2001), Jeng et al. (2003).

backtests/docs/009_insider_cluster.md

Strategy 008: Sell-in-May Calendar Effect · 2kb

Folk wisdom + Bouman & Jacobsen, The Halloween Indicator, "Sell-in-May-and-Go-Away": Another Puzzle (American Economic Review, 2002). Subsequent decades of replication.

backtests/docs/008_sell_in_may.md

Strategy 007: Short-Term Reversal (1-week loser-winner) · 2kb

Jegadeesh (1990), Lehmann (1990) — the original short-horizon reversal papers. The mirror image of 12-1 momentum: short-term returns reverse at 1-week/1-month horizons, while medium-term (12-1) returns continue.

backtests/docs/007_short_term_reversal.md

Strategy 006: Net-Net (Graham Deep Value) · 2kb

Benjamin Graham, The Intelligent Investor (1949) and Security Analysis (1934). The original quantitative value strategy. Tweedy Browne, Walter Schloss, and others used variants for decades.

backtests/docs/006_net_net.md

Strategy 005: VIX Term Structure · 2kb

Multiple — vol-arbitrage literature 2010s. Notable: Simon (2014), Donninger (2015), the "Hayek" / "Boggs" VIX-term-structure papers. Popularized in retail circles via SVXY / VXX strategies after the 2011 launch of VIX ETPs.

backtests/docs/005_vix_term_structure.md

Strategy 004: Piotroski F-Score · 3kb

Joseph Piotroski, Value Investing: The Use of Historical Financial Statement Information to Separate Winners from Losers (Journal of Accounting Research, 2000).

backtests/docs/004_piotroski.md

Strategy 003: Post-Earnings Announcement Drift (PEAD) · 2kb

Bernard & Thomas, Post-Earnings-Announcement Drift: Delayed Price Response or Risk Premium? (1989). Replicated and refined for ~40 years.

backtests/docs/003_pead.md

Strategy 001: Magic Formula (Greenblatt) · 3kb

Joel Greenblatt, The Little Book That Beats the Market (2006).

backtests/docs/001_magic_formula.md