Model accuracy + full history, in public

Our probabilities, measured in public.

We don't sell a betting edge — we sell accurate analysis. So we measure what actually matters for a decision-support tool: how well our fair-value probabilities match real outcomes (calibration), shown below in full. Our earlier +EV-pick experiment is kept underneath as a labeled archive — including the honest finding that the playable market is too thin to beat. Nothing hidden, nothing cherry-picked.

Model calibration

Are our probabilities accurate?

✓ Beats the base-rate baseline (significant)

Predicted (avg)

45.7%

Actual win rate

43.9%

Brier score

0.218

lower is better

Base-rate baseline

0.246

beat this = informative

Across 392 settled predictions our fair value said 45.7% on average and 43.9% actually happened — the model's probabilities track real outcomes, and its Brier score beats the base-rate baseline beyond statistical noise — it adds real information. This measures accuracy, not profit: we're a decision-support tool, not a tipster.

PredictedPredicted vs actualn

0.0%–10.0%

pred 7.9%

actual 0.0%

10.0%–20.0%

pred 15.1%

actual 16.7%

20.0%–30.0%

pred 25.5%

actual 24.2%

30.0%–40.0%

pred 34.7%

actual 28.6%

40.0%–50.0%

pred 44.9%

actual 45.1%

50.0%–60.0%

pred 53.7%

actual 51.2%

127

60.0%–70.0%

pred 64.8%

actual 64.7%

70.0%–80.0%

pred 74.5%

actual 75.0%

80.0%–90.0%

pred 84.0%

actual 83.3%

90.0%–100.0%

pred 92.3%

actual 100.0%

Research-phase archive (retired) — our earlier +EV-pick experiment

Below is the full result history from when we tested publishing +EV betting picks. We've since found the playable market for our users (~2 GGL-licensed sportsbooks) is too thin to sustain a betting edge, so we repositioned to analytics. We keep every result here — wins, losses, and the finding itself — because deleting losers is what tipsters do. It is NOT how we measure the tool (see model accuracy above), and it is reported as independent decisions, not per-book rows.

n=1121· early-stage data

Equity curve · All time

-27.13u cumulative

1121 settled · May 17 → Jun 13

Each point is a settled pick's contribution to cumulative net profit in stake units. Wins lift the line, losses drop it. No deletions, no smoothing, no cherry-picking.

Last updated: 2026-06-13 06:01:33 UTC

n=1121· early-stage dataEvery settled result published — wins and losses

Track record builds with each settled pick — current depth: n=1121.

Lock-in significance threshold: 1500 picks. We publish every result regardless of sample size — the receipts are the product.

Returns · live from the ledger

n=1121· early-stage data

7-day ROI

−12.5%

218 settled picks

30-day ROI

−1.8%

1121 settled picks

All-time ROI

−1.8%

1121 settled picks

Longest win run

15 settled picks

Longest lose run

22 settled picks

Units staked

1508

Profit (u)

−27.13u

Hit rate

43.4%

Avg odds

3.10

Avg CLV vs close

−6.7%

our honest edge metric · n=1092 · 12% beat close

Per-sport models

ROI by sport — every model in public.

Each row is the cumulative ROI of every settled pick for that sport. No cherry-picking — losing models are visible too.

Football (Soccer)

n=631 · 34.2% win

−4.9%

Basketball

n=276 · 63.4% win

+14.7%

Baseball

n=202 · 45.0% win

−12.2%

Ice Hockey

n=12 · 41.7% win

−22.3%

Archive note: rows are logged per (match × selection × bookmaker), so the same decision often appears at several books. The honest count is independent decisions, not rows — and most of these book-prices were never playable for a DE user in the first place. Kept in full for transparency.

Date	Match	Pick	Odds	Stake	Result	Bankroll
2026-06-02	Cincinnati Reds vs Kansas City Royals Baseball	home FanDuel	1.53	1u	lost-1.00u	+20.05u
2026-06-02	Washington Nationals vs Miami Marlins Baseball	under_8.5 Sportsbet AU	1.93	1u	lost-1.00u	+21.05u
2026-06-02	Tampa Bay Rays vs Detroit Tigers Baseball	home FanDuel	1.62	1u	lost-1.00u	+22.05u
2026-06-02	Cincinnati Reds vs Kansas City Royals Baseball	home TAB AU	1.52	1u	lost-1.00u	+23.05u
2026-06-02	Washington Nationals vs Miami Marlins Baseball	under_8.5 Unibet	1.93	1u	lost-1.00u	+24.05u
2026-06-02	Washington Nationals vs Miami Marlins Baseball	away Betfair	2.28	1u	won+1.28u	+25.05u
2026-06-02	Cincinnati Reds vs Kansas City Royals Baseball	away Betfair	2.88	1u	won+1.88u	+23.77u
2026-06-02	Washington Nationals vs Miami Marlins Baseball	under_8.5 FanDuel	1.95	1u	lost-1.00u	+21.89u
2026-06-02	Tampa Bay Rays vs Detroit Tigers Baseball	home Betfair	1.64	1u	lost-1.00u	+22.89u
2026-06-01	Los Angeles Dodgers vs Philadelphia Phillies Baseball	away Betfair	3.05	1u	lost-1.00u	+23.89u
2026-05-31	Chicago White Sox vs Detroit Tigers Baseball	under_8 FanDuel	1.91	1u	won+0.91u	+24.89u
2026-05-31	Golden State Valkyries vs Las Vegas Aces Basketball	away BetMGM	1.80	1u	won+0.80u	+23.98u
2026-05-31	Golden State Valkyries vs Las Vegas Aces Basketball	away FanDuel	1.82	2u	won+1.64u	+23.18u
2026-05-31	Golden State Valkyries vs Las Vegas Aces Basketball	away Betsson	1.78	1u	won+0.78u	+21.54u
2026-05-31	Golden State Valkyries vs Las Vegas Aces Basketball	away Betway	1.80	1u	won+0.80u	+20.76u
2026-05-31	Tampa Bay Rays vs Los Angeles Angels Baseball	away Betway	2.75	1u	lost-1.00u	+19.96u
2026-05-31	Golden State Valkyries vs Las Vegas Aces Basketball	away Ladbrokes AU	1.80	1u	won+0.80u	+20.96u
2026-05-31	Golden State Valkyries vs Las Vegas Aces Basketball	away NordicBet	1.78	1u	won+0.78u	+20.16u
2026-05-31	Pittsburgh Pirates vs Minnesota Twins Baseball	home Betfair	1.69	1u	won+0.69u	+19.38u
2026-05-31	Golden State Valkyries vs Las Vegas Aces Basketball	away Bovada	1.80	1u	won+0.80u	+18.69u
2026-05-31	Houston Astros vs Milwaukee Brewers Baseball	home Betfair	2.68	1u	lost-1.00u	+17.89u
2026-05-31	Texas Rangers vs Kansas City Royals Baseball	under_7.5 FanDuel	2.00	1u	lost-1.00u	+18.89u
2026-05-31	Tampa Bay Rays vs Los Angeles Angels Baseball	away Betfair	2.80	2u	lost-2.00u	+19.89u
2026-05-31	Golden State Valkyries vs Las Vegas Aces Basketball	away Betfair	1.80	1u	won+0.80u	+21.89u
2026-05-31	Golden State Valkyries vs Las Vegas Aces Basketball	away Sportsbet AU	1.82	2u	won+1.64u	+21.09u
2026-05-31	Cincinnati Reds vs Atlanta Braves Baseball	home Betfair	2.22	1u	won+1.22u	+19.45u
2026-05-31	Golden State Valkyries vs Las Vegas Aces Basketball	away DraftKings	1.80	1u	won+0.80u	+18.23u
2026-05-31	Golden State Valkyries vs Las Vegas Aces Basketball	away Unibet	1.80	1u	won+0.80u	+17.43u
2026-05-31	New York Mets vs Miami Marlins Baseball	away Betfair	2.46	1u	lost-1.00u	+16.63u
2026-05-31	Seattle Mariners vs Arizona Diamondbacks Baseball	under_7 Betsson	1.90	1u	won+0.90u	+17.63u
2026-05-31	Seattle Mariners vs Arizona Diamondbacks Baseball	away TAB AU	2.40	1u	lost-1.00u	+16.73u
2026-05-31	Seattle Mariners vs Arizona Diamondbacks Baseball	under_7 Unibet	1.89	1u	won+0.89u	+17.73u
2026-05-31	Seattle Mariners vs Arizona Diamondbacks Baseball	under_7 NordicBet	1.90	1u	won+0.90u	+16.84u
2026-05-31	Athletics vs New York Yankees Baseball	home Betfair	2.36	1u	won+1.36u	+15.94u
2026-05-31	Seattle Mariners vs Arizona Diamondbacks Baseball	under_7 FanDuel	1.91	1u	won+0.91u	+14.58u
2026-05-31	Oklahoma City Thunder vs San Antonio Spurs Basketball	home Matchbook	1.71	1u	lost-1.00u	+13.67u
2026-05-31	Portland Fire vs Indiana Fever Basketball	away DraftKings	1.22	1u	lost-1.00u	+14.67u
2026-05-31	Portland Fire vs Indiana Fever Basketball	away Betway	1.22	1u	lost-1.00u	+15.67u
2026-05-31	Portland Fire vs Indiana Fever Basketball	away Bovada	1.22	1u	lost-1.00u	+16.67u
2026-05-31	St. Louis Cardinals vs Chicago Cubs Baseball	away Betfair	1.79	1u	won+0.79u	+17.67u
2026-05-31	Portland Fire vs Indiana Fever Basketball	away Ladbrokes AU	1.24	2u	lost-2.00u	+16.88u
2026-05-31	Portland Fire vs Indiana Fever Basketball	away BetMGM	1.22	1u	lost-1.00u	+18.88u
2026-05-31	Portland Fire vs Indiana Fever Basketball	under_175.5 FanDuel	1.91	2u	lost-2.00u	+19.88u
2026-05-31	Oklahoma City Thunder vs San Antonio Spurs Basketball	home Betfair	1.71	1u	lost-1.00u	+21.88u
2026-05-31	Oklahoma City Thunder vs San Antonio Spurs Basketball	away Matchbook	2.40	1u	won+1.40u	+22.88u
2026-05-31	Portland Fire vs Indiana Fever Basketball	under_175.5 Bovada	1.91	2u	lost-2.00u	+21.48u
2026-05-31	Oklahoma City Thunder vs San Antonio Spurs Basketball	away Betfair	2.40	1u	won+1.40u	+23.48u
2026-05-31	Portland Fire vs Indiana Fever Basketball	under_175.5 BetMGM	1.91	2u	lost-2.00u	+22.08u
2026-05-31	Portland Fire vs Indiana Fever Basketball	under_175.5 Sportsbet AU	1.90	1u	lost-1.00u	+24.08u
2026-05-31	Connecticut Sun vs Los Angeles Sparks Basketball	under_167.5 BetMGM	1.95	1u	won+0.95u	+25.08u

Showing 332–381 of 1121 (newest first)

Newer Older

Methodology

How we measure accuracy (calibration + CLV)

Our headline metric is calibration: across our settled predictions, does an outcome we put at probability p actually happen about p of the time? We publish the calibration curve (predicted vs actual) and a Brier score tested against the base-rate baseline, with a statistical-significance gate. It measures accuracy, not profit.

We also show Closing Line Value (CLV) honestly — how our published odds compared to the market's de-vigged close, including when it is negative. Formula: CLV% = (published_odds / closing_odds − 1) × 100

CLV is a transparency receipt from our retired +EV experiment, not a current edge claim: the playable market proved too thin to beat the closing line, so we dropped the profit framing and kept the numbers visible anyway.

Settlement rules

Each pick is settled against one of four outcomes: Won, Lost, Push, or Void.

Won: Selection correct. Profit = (odds − 1) × stake.
Lost: Selection incorrect. Profit = −stake (full loss).
Push: Bet cancelled by bookmaker (e.g. Asian handicap half). Stake refunded. Profit = 0 units.
Void: Match abandoned or selection suspended. Stake refunded. Profit = 0 units.

The pick_results table is database-enforced append-only — UPDATE and DELETE are blocked at the database level, so a settled result cannot be silently amended or removed after the fact.

All profit/loss figures use the tax-neutral formula. If a jurisdiction-specific adjustment applies it appears in the pick's audit page under “Edge (post-tax).”

Sample-size caveat

Statistical significance in sports betting requires a large sample. The conventional threshold for drawing firm conclusions is ~1,500 settled picks — at that depth, a consistently positive ROI is extremely unlikely to be variance alone.

BetEdge launched in May 2026 with a baseline of ~293 free picks. Every result is published regardless of sample depth — the receipts are the product. The n= · early-stage data chip on the dashboard is the honest signal: “real numbers, but interpret ROI with an appropriate confidence interval.”

Lock-in threshold: 1,500 picks. The chip disappears once that milestone is crossed. We do not cherry-pick which results to show.

FAQ

About the track record

How is ROI calculated?

ROI is cumulative profit divided by total stake, expressed as a percentage. Only settled picks are included. Example: if 100 units are staked and 8 units net profit results, ROI is 8%. We report both positive and negative ROI — the ledger is public regardless.

What is CLV?

Closing-Line Value (CLV) is the difference between the odds at which we placed the bet and the closing line at kickoff. Positive CLV means we secured a price the market later agreed was underpriced. It is the sharpest long-term indicator of whether an edge-finding method actually works.

Why does the chart show negative returns sometimes?

Because they happened. We publish every settled pick — winners and losers alike. Variance is real and hiding losing stretches would be dishonest. Full transparency means you see everything, including the drawdowns.

What counts as a settled pick?

A pick where the match has finished and the result was determined by the governing body. Pushes (draws on spread markets) and voids (cancelled matches, walkover results) are excluded from ROI calculations but remain visible in the ledger for completeness.

How do I know these numbers aren't cherry-picked?

Every settled pick is published here with its odds, result, CLV, and profit — winners and losers alike. Results are stored append-only: once a match settles, the row cannot be edited or deleted. We never remove losing picks or hide drawdowns. The complete ledger is on this page exactly as recorded.

BetEdge is an analytics and decision-support tool — not a bookmaker and not a tipster service. We don't accept bets or hold funds. For educational and informational purposes only. 18+.