How MatchSense builds predictions
Every number shown in MatchSense comes from a structured pipeline. No black boxes, no vague claims, just data, models, and transparent outputs.
Model Pipeline
XGBoost + LightGBM ensemble with Monte Carlo simulation
Data Sources
Live odds feeds from configured providers
Historical match results and team statistics
Confirmed lineup and availability data
In-play pace, possession, and pressure metrics
Refresh Cadence
Predictions are refreshed at each analysis tier as new data becomes available.
Prematch Early
Generated when match enters catalog
Prematch Lineup
Refreshed when confirmed lineups are available
In-Play
Refreshed on live match state changes
Calibration
Probabilities are calibrated against historical outcomes. A 60% model probability should resolve as correct approximately 60% of the time.
Trust Center
MatchSense is built on verifiable outputs. Every claim on this platform can be traced.
Confidence Bands
Confidence reflects model agreement across ensemble members, not certainty of outcome. High confidence means the models strongly agree, it does not mean the event is guaranteed.
Edge Interpretation
Edge is the gap between the model's estimated probability and the market-implied probability. Positive edge suggests the market may be underpricing the outcome.
Projected Scores
Projected scores are derived from Monte Carlo simulation of thousands of match scenarios. They represent the expected value of the scoreline distribution, not a single outcome prediction.
Tier Refreshes
When new data arrives, predictions are regenerated. The archive shows exactly what changed between each tier so you can trace the model's reasoning evolution.
MatchSense does not guarantee outcomes. All analysis represents the model's best estimate given available data.