Prop Correlations: What Moves Together
correlationsUse this when the user asks which players' stat lines tend to go over or under together in a game, or who a player's outcomes move with (teammates and opponents). Returns, for a game_id, its typical role pairs (typical: the phi and lifts of the players' roles, pooled over earlier seasons) and the game-script splits (script: the roles' over rates on tonight's side of the spread and total); for a player_id, his partners in his next game (partners). Counted over the games both played, before the game asked. With Keel Stats Pro also each pair's own sample (joint counts, lift, phi shrunk to its role pair) and the pairs ranked on their samples (pairs); account.held says when they were left out. A pair's past season does not predict its next well. Not for a player's own lines: use props_research.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"league": "<league>"
},
"name": "correlations"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| stat | No | Optional, with a player_id: his stat to pair (NBA: "pts", "reb", "ast", "tpm"…; NFL: "receiving_yards", "rushing_yards"…). | |
| league | Yes | League ("nba" or "nfl"). | |
| game_id | No | Numeric game ID (from tonight_slate or find_game): the game's pairs. | |
| player_id | No | Numeric player ID (from search): his partners. Ignored with a game_id. |