Methodology

How Pick'em Labs works

Pick'em Labs is a sports analytics tool that combines publicly available fighter statistics, live sportsbook odds, and independent analysis from multiple AI models. This page explains exactly how predictions are generated, what data is used, and where the current limitations are.

How Pick'em Labs works

For every fight on an upcoming card, Pick'em Labs pulls three independent inputs and combines them into a single analysis view.

  1. 01
    Fighter data is collected

    Career records, physical attributes, and detailed fight statistics are sourced from publicly available UFC data. This includes striking accuracy, takedown rates, submission attempts, and finish percentages.

  2. 02
    Sportsbook odds are fetched

    Live moneyline odds are pulled from multiple major sportsbooks via The Odds API. These are converted into implied probabilities to represent what the betting market currently believes about each fighter's chances of winning.

  3. 03
    AI models analyse the matchup

    Three AI models — Claude, GPT-4, and Gemini — independently evaluate the matchup using fighter statistics and odds context. Each model produces a predicted winner, a confidence score, and a structured breakdown covering key advantages, risks, and a likely fight script.

  4. 04
    Results are surfaced

    The three model outputs are compared to produce a consensus pick and an average confidence score. The AI win probability is then shown alongside the market-implied probability so you can see where they agree and where they diverge.

AI models

Pick'em Labs currently uses three large language models. Each model receives the same structured prompt containing fighter statistics and odds data. They analyse the matchup independently — no model sees another's output before producing its prediction.

Claude

Developed by Anthropic. Known for careful, structured reasoning and nuanced risk assessment. Claude tends to produce detailed fight scripts and explicit breakdowns of counter-arguments.

GPT-4

Developed by OpenAI. Broadly capable across sports analysis tasks and draws on extensive training data covering MMA history, fighter profiles, and fighting styles.

Gemini

Developed by Google DeepMind. Provides a third independent perspective on each matchup, helping to identify cases where model agreement is strong versus cases where predictions diverge significantly.

Data sources

Pick'em Labs currently draws from two primary data sources.

Fighter statistics

Career and per-fight metrics are sourced from publicly available UFC statistical data. This includes significant strike rates, accuracy, takedown data, submission attempts, and win/loss records. Statistics reflect career averages and may not capture very recent fights until data is updated.

Sportsbook odds

Moneyline odds are fetched in real time from The Odds API, which aggregates lines from multiple major sportsbooks. Odds are displayed in American format. Implied probabilities are calculated from these odds and used as an input to the AI analysis prompt.

Confidence scores

Each AI model returns a confidence score between 0 and 100 alongside its predicted winner. This score represents the model's self-assessed certainty in its own prediction given the data it was provided.

The consensus confidence shown in the Multi-Model Consensus panel is the arithmetic average of the three individual model scores. It is not a probability of the predicted fighter winning — it is a measure of how certain the models are collectively in their pick.

A high consensus confidence combined with a pick that disagrees with the betting market is typically the most analytically interesting signal Pick'em Labs surfaces.

AI vs market

The Value Analysis panel compares the AI consensus win probability against the market-implied probability derived from sportsbook odds. The difference between these two numbers is displayed as a value edge.

A positive value edge means the AI models collectively assign a higher win probability to a fighter than the market does. A negative value edge means the market is more confident in that fighter than the AI models are.

This comparison is informational. It is intended to surface disagreements between AI analysis and market consensus, not to imply that either the AI or the market is correct.

Current limitations

Pick'em Labs is an early-stage tool. There are several known limitations to be aware of when interpreting its output.

  • Statistical recencyFighter statistics reflect career averages. Recent form, injuries, coaching changes, and camp reports are not systematically incorporated into the data layer.
  • AI knowledge cutoffsLarge language models have training cutoffs. Fights, results, and fighter developments that occurred after a model's cutoff date may not be reflected in its analysis.
  • No fight-by-fight granularityThe current data layer uses aggregate career statistics rather than round-by-round or fight-by-fight breakdowns. Stylistic trends that have emerged recently may not be captured.
  • Model variabilityAI model outputs are not deterministic. The same prompt may produce slightly different predictions across separate requests. Predictions should be treated as one analytical input, not a definitive forecast.