Docteur Bet
About

Maths behindevery priceValue betting

Docteur Bet looks for odds that pay more than the real risk, and publishes every bet before kick-off — including the ones that lose.

01

Transparency, where it is possible

The model behind the free probabilities is academic and described in full. The value-bet model stays proprietary — its performance can be checked in the track record, losses included.

02

Limits, always stated

A probability is not a certainty, and a streak proves nothing: only volume decides. We repeat it on purpose.

03

Substance before style

A sound, slightly less spectacular figure rather than an impressive, fragile one.

What we do

Docteur Bet does one thing: it spots value bets, odds that pay better than the risk they cover. Odds of 2.50 imply a 40% chance. If our model puts the true probability at 45%, the operator is paying too much — and that gap is what we look for, measure and publish.

The product is the app, on iPhone, on Android and on the web. It follows 24 competitions and compares our probabilities with the odds of the operators licensed in your country. The probabilities for every match are free. What comes with the Premium subscription is the gap between the price and the probability: today's value bets, the expected value of each one, and the minimum odds below which the bet no longer has any value.

A model rather than an opinion

Most of the tips in circulation come from a conviction stated with confidence, not from a method that can be traced. Whoever reads them has no way of knowing whether they are looking at a calculation, an average or an opinion.

We start from a simple principle: apply to sports betting the rigour expected of a model in quantitative finance or actuarial work. Known assumptions, published methods wherever possible, limits owned up to, and performance measured over time rather than on a single call.

That means showing what does not work. A 60% probability is wrong four times in ten. A market where our bets lose stays visible in the track record. A yield measured over a hundred bets proves nothing. These limits are written on the site and in the app, not relegated to a footnote.

A figure that does not say what it is worth is worth nothing. It is the only editorial rule we impose on ourselves, and it decides everything else.

The founder

Docteur Bet was founded and is run by Lucas da Silva, CEO and a doctoral researcher in financial mathematics. He designs and calibrates the product's models, and answers for them.

That background is not a detail: odds are a price, and value betting is a quantitative-finance problem before it is a football problem. Estimating a probability, comparing it with a market price, sizing a stake in the face of variance — these are the questions financial mathematics deals with, applied here to sport.

Our tools are those of applied statistics: count models, constrained estimation, out-of-sample validation, probability calibration. Football is where they are applied, not a pretext for tips.

What we have built

  • A computation chain that follows 24 competitions and refits the model after every matchday played. Without a new result, nothing is recomputed: unchanged figures with a more recent date would suggest a movement that never happened.
  • Two layers of model. The free probabilities rest on an academic model published in 1997, which our methodology describes in full. The value bets come from a proprietary model, built for a different task: finding where a price is wrong.
  • A public track record, bet by bet, since day one. Every value bet is published before kick-off, then settled, market by market — wins and losses.
  • A calibration measure: the probabilities we announce are checked against what actually happens, and the gap is shown, including where we overestimate.
  • An out-of-sample backtest, available next to the real results in the app's Track record tab, no account needed.
  • A free Learning course: eighteen lessons to understand odds, the margin, variance and stake sizing.

What we stand for

Transparency, where it is possible. The model behind the free probabilities is published, and no in-house method is used in it without being described. What stays proprietary — the value-bet model — does so for a reason we own rather than by reflex: it is what carries the product's value. Its performance, though, can be checked in the track record.

Limits, always stated. A probability is not a certainty. A losing streak does not prove the model was wrong, and a winning streak does not prove it right: only volume decides. We repeat it deliberately often, because that is what separates a serious tool from a sales pitch.

Substance before style. We prefer a figure that is right and slightly less spectacular to one that is impressive and fragile. That choice sometimes costs a punchy line; it builds trust over time.

Responsible gambling. Value betting is a method, not a promise of winnings. Sports betting carries a risk of loss and addiction, and is forbidden to minors. If gambling becomes a problem: 18+ · BeGambleAware.org · National Gambling Helpline 0808 8020 133. In France, call Joueurs Info Service on 09 74 75 13 13 (standard rate).

Why “Docteur Bet”

The name owns what we do: applying a research approach — hypotheses, method, verification — to a field where that rigour is rarely visible. It is not wordplay; it is a commitment about how we work.

The company

Docteur Bet is a French company. It operates the app, published on the App Store and on Google Play and available in a browser, the computation chain that feeds it, and this site. Our modelling work for media and clubs continues under a separate brand, Rondo Research.

Where to follow us

Analysis and behind-the-scenes work on building the model are published here, on YouTube and on Instagram. The links are at the foot of every page, and the account depends on the language you are reading.

Join us

We look for people who like to check

What matters here is not the line on a CV but the ability to doubt a figure, trace where it comes from, and write clearly what you found. We work in a small group on demanding subjects, and everyone sees the effect of what they produce.

  • Statistics and modelling — count models, time series, out-of-sample validation.
  • Engineering — Python for the computation chain, TypeScript and Next.js for the site, Node for the API.
  • Writing — telling what a model says without betraying it, in French as in English.

None of these is an open role with a spec and a posted salary: we do not hire continuously. Apply anyway — we read everything, and we reply, including to say no.

No cover letter. Tell us instead what you have built and what was wrong with it: that teaches us more.

Application

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