Docteur Bet
Methodology

The modelbehind the value bets

Explaining a result well and finding where a price is wrong are two different tasks. The second one needs a different model, and a different measure of success.

The problem is not the obvious one

The model behind the free probabilities, described in our methodology, answers one question well: given the strength of two sides, what is the probability of each score? That is what you need to read a match or replay a league. It is not what you need to find a value bet.

The Docteur Bet model answers a different question: is this displayed price wrong, and by how much? An odds market already aggregates the information of thousands of participants; it is not easy to beat, and a good result model is not enough. It takes a model built for that particular confrontation.

What that changes in the construction

Three consequences, which can be stated without going into detail.

The target is the full distribution of scores, not the 1X2. A model tuned to name the winner is blind to most markets — total goals, one team's goals, both teams to score. The entire distribution is modelled, and every market is derived from it.

Calibration matters more than average accuracy. Announcing 70% when the event happens 75 times in 100 is a mistake that costs money, even when the favourite named is the right one. A model that is rarely wrong but states its certainties badly is unusable here.

Dependence between markets counts. One side's goal count and its opponent's are not independent, and a model that treats them as such produces prices that contradict each other — and therefore false opportunities.

What you see of it in the app

With the Premium subscription, the Docteur Bet model appears next to every price:

  • today's value bets, sorted, with the exact market, the odds and the expected value of each one;
  • the minimum odds, below which the bet no longer has any value — useful when the price moves before you place your bet;
  • the model's probability against every price, and a colour that tells you at a glance whether a price is generous or short;
  • an alert as soon as a new bet is detected.

Value bets are sought among the operators licensed in your country. The model is refitted after every matchday played, and odds are collected throughout the day.

How its performance is judged

On fixtures later than its fitting, never on those used to build it, and with the same criterion as the rest of our models: the likelihood of the score that actually occurred.

It is set against a benchmark — the public model behind our free probabilities, fitted on the same data and evaluated on the same fixtures. A proprietary model that fails to beat one published in 1997 does not deserve to exist, and that is the first thing we check.

What we publish

The complete track record of the value bets, losses included: every bet published before kick-off, at the odds recorded when it was published, then settled. It is the only verification a user can carry out unaided, and it is the one that counts: a success shown without its denominator proves nothing. See the track record.

Calibration, market by market: what we announce against what happens, including where we overestimate. The out-of-sample backtest, with its margin of uncertainty, next to the real results. Both are in the app's Track record tab, free and with no account needed.

What we do not detail

Its construction. It is what carries the product's value, and writing it down would be giving it away. We therefore publish neither its family of distributions, nor its variables, nor its settings.

That reserve stops where your interest begins: the evaluation criterion, the benchmark, the track record, the calibration and the limits below are public.

The limits

A model better calibrated than an operator on one market is not better on all of them, nor permanently. Prices move, operators adjust, and an edge measured over one period has to be measured again over the next.

None of this guarantees a profit. A probability remains a probability, including when it is correct: a losing run is not proof the model was wrong, and a winning run is not proof of the opposite. Only volume settles it.

And what the data does not contain, the model does not know: a last-minute absence or a change of manager only reaches it through results and odds. Only stake what you can afford to lose.

Today’svalue betsIn your pocket

Model probabilities, operators’ odds, value gaps: it’s all in the app. Seven-day trial, no commitment.

18+ · Gamble responsibly · BeGambleAware.org · National Gambling Helpline 0808 8020 133