What is a prediction market?
A prediction market lets participants express views about whether a future event will happen. Prices are often interpreted as a rough crowd estimate, not a guarantee.
Forecasting basics for people who want the reasoning, not hype.
PredictionMarket-AI is built around education first: clear definitions, visible uncertainty, and scorekeeping that makes bot mistakes easier to inspect.
What is market-implied probability?
Market-implied probability translates a sample market price into a percentage. If a contract is priced near 40 cents, the simple implied probability is about 40% before fees and market details.
What is Brier score?
Brier score grades probability forecasts after the outcome is known. A 70% forecast on an event that happens scores better than a 40% forecast, while confident wrong forecasts are penalized more.
What is calibration?
A calibrated forecaster is right about 70% of the time when it says 70%, about 30% when it says 30%, and so on across many resolved events.
What is bot consensus?
Bot consensus is the average or summarized view across the static bot forecasts. It helps compare one bot's opinion with the group, but it is not a recommendation.
Why paper forecasts are not financial advice
These forecasts are educational samples for learning how probability estimates are scored. They do not tell anyone what to buy, sell, trade, or wager on.
Beginner notes
How to read the scoreboard without overreading it.
Forecast accuracy vs paper-only score
Forecast accuracy asks whether probabilities matched resolved outcomes. The paper-only score is a static teaching score based on forecast quality, not a money result.
Why a bot can rank well and still be poorly calibrated
A bot can look good in a small sample by being directionally right on a few disagreements while still using probabilities that are too extreme. Calibration checks whether confidence levels are reliable across many events.
Why markets can be wrong
Market prices can reflect thin liquidity, stale information, crowd narratives, or unclear resolution criteria. They are useful signals, but they are not guaranteed truth and should be compared against evidence.
Why AI explanations should be audited
AI explanations can sound confident while missing context, citing stale signals, or justifying a probability after the fact. The safer pattern is to log the reasoning, compare it with outcomes, and review mistakes openly.
Paper trading keeps the feedback loop clean.
The safest way to test forecasting systems is to separate analysis from execution. This MVP focuses on explanations, simulated forecasts, and transparent scoring before any read-only data research is considered.