Frequently asked questions

No. Closing odds are extraordinarily hard to beat, and we make no such claim.

On the same historical sample of 16,322 matches with Bet365 closing data, our walk-forward backtest trails the Bet365 closing favourite by about 2.16 percentage points of accuracy. We publish that gap rather than hide it. Those figures are backtest results, not a promise about live performance.

No. WinSight publishes statistical information only. It is not betting advice, not tips, and not a guarantee of profit.

If you gamble, that decision and its consequences are yours, and gambling can lead to financial loss. Safeguards and independent help are on the Responsible Gambling page.

Predictions come from a Dixon–Coles model (see glossary). It estimates each team’s attacking and defensive strength, adjusts for home advantage, and builds one grid of scoreline probabilities.

Match result (1X2), total goals over/under 2.5, both teams to score (BTTS), and correct score are all read from that same grid, so the markets stay consistent with one another.

The production model is retrained once a week. Upcoming fixtures are predicted once a day after the evening fixture sync. Recent matches count for more than older ones. A team new to a league starts from comparable teams until its own results take over.

A published probability is an estimate of uncertainty, not a promise that an outcome must happen.

A 60% chance is not a promise. It means that if the same situation played out many times, we would expect it to happen about six times in ten — and fail about four times in ten.

A single high-confidence call going the wrong way is not, by itself, a broken model. A model whose 60% calls only come true 40% of the time is. That difference is what calibration measures (see glossary), which is why we publish a calibration curve on the track record page — not only a headline hit rate.

Free ($0): completed-match reviews, the public track record, and the methodology stay open without a subscription. A signed-in reader can also see basic match-result (1X2) probabilities for the earliest two non-marquee matches in the next seven days. On those free matches, confidence and the other markets stay locked. Guests do not see pre-match probabilities.

Pro: every upcoming match across the four markets (1X2, over/under 2.5, BTTS, correct score), plus the model evidence for every upcoming match.

Current prices and offers are on the pricing page. Applicable taxes may be added at checkout.

WinSight currently covers seven active competitions: Premier League, Championship, La Liga, Bundesliga, Serie A, Ligue 1, and UEFA Champions League.

Eredivisie and Primeira Liga are registered as pending and are not covered yet. Only competitions marked active are published.

Every published prediction is settled after the match and stays online, including mistakes.

• The match-result pick is the home win, draw, or away win with the highest probability.
• Total goals are counted as over 2.5 when that probability is at least one half, and the match is over when the teams score three or more goals.
• Both teams to score is “yes” when that probability is at least one half.
• Correct score is scored against the single most likely scoreline (Top 1), not against other displayed scorelines.
• Cancelled matches are void. A postponed match is voided only after it has stayed unplayed for 14 days past kickoff; if it is rescheduled, it settles on the real result.

On the public record, a match is counted once. Forecast totals count each settled match-result (1X2) call from a non-development model version. Void results are excluded, and the other markets are not added to those headline totals.

Hit rate is wins ÷ (wins + losses) for that model version only. Versions stay separate and are never pooled. A live sample smaller than 100 settled forecasts is marked as not yet strong evidence.

Each Monday, the previous week’s settled predictions are published as a weekly report. A database trigger rejects later updates and deletions of that report.

See the live numbers on the track record page. A CSV of settled match-result calls is available there for download under the site terms.

No. No probability model can guarantee a profit. Historical records and backtests cannot tell you what will happen next.

Many sites highlight wins and quietly drop losses. WinSight’s product promise is the opposite: publish the call, settle it, and leave it on the record.

That public, permanent, never-edited record — right or wrong — is what we ask you to judge us on.

You can cancel at any time on the cancellation page. An ordinary cancellation is accepted automatically, asks for no reason, and stops the next renewal. Unless a refund or mandatory law applies, paid access continues until the end of the current billing period. Cancelling does not itself return money already paid.

Refund eligibility is set out in the Refund Policy. WinSight decides refund requests under that policy; Whop processes checkout and approved refunds where possible.

Use the contact form, or email support@winsightapp.com. Messages are reviewed by a person, not a chatbot.