Live possession value model
A computing system receives a plurality of game files corresponding to a plurality of games across a plurality of seasons. The computing system generates a prediction model configured to generate a possession value for an event. The computing system receives a target event, in real-time or near real-time, from a tracking system monitoring a target game. The computing system generates target features for the target event based on target event data associated with the target event. The computing system generates, via the prediction model, a target possession value for the target event based on the target event data and the target features. The target possession value represents a likelihood that a team with possession will score within a following x-seconds after the target event.
1. A method comprising:
receiving, by a computing system, one or more event indications corresponding to one or more events of a game from a tracking system, wherein each of the one or more event indications corresponds to an on-ball event, and wherein each of the one or more event indications include event data, and wherein the game includes one or more teams, and wherein the one or more teams include one or more players;
generating, by the computing system, one or more features for each of the one or more events based on the corresponding event data;
generating, by the computing system, via a prediction model, a possession value metric for each of the one or more events based on the event data and the one or more features, wherein the possession value metric includes a numerical representation corresponding to a likelihood that a possession team will score within a time period after the one or more events;
aggregating, by the computing system, the possession value metric for each of the one or more events to generate a momentum metric for each of the one or more teams;
generating, by the computing system, a visual representation corresponding to the momentum metric; and
outputting, by the computing system, the visual representation to a display of a device.
2. The method of claim 1 , the method further comprising:
generating, by the computing system, an aggregate possession value for one or more categories for each of the one or more players.
3. The method of claim 2 , wherein the one or more categories include one or more of: a successful pass category, an unsuccessful pass category, a losing ball possession category, or a gaining ball possession category.
4. The method of claim 1 , the method further comprising:
identifying, by the computing system, a target player of the one or more players on a first team of the one or more teams in at least one of the one or more events;
identifying, by the computing system, a subset of additional events that involve the target player;
generating, by the computing system, a subset of additional target possession values based on the subset of additional events; and
generating, by the computing system, a plurality of metrics for the target player based on the subset of additional target possession values.
5. The method of claim 1 , wherein generating, via the prediction model, the possession value metric for each of the one or more events based on the event data and the one or more features includes:
generating, by the computing system, via the prediction model, a plurality of decision trees; and
analyzing, by the computing system, the plurality of decision trees to determine the possession value metric for each of the one or more events.
6. The method of claim 1 , wherein the one or more features may include at least one of: an event outcome, an event location, event cross data, event header data, free kick event data, corner kick event data, penalty kick event data, throw-in event data, an event end location, goal distance data, goal angle data, goal location data, event distance data, an event type identifier, previous event distance data, total speed data, or event direction speed data.
7. The method of claim 1 , wherein the on-ball event includes at least one of: a pass event, a throw-in event, a corner kick event, a free-kick event, a cross event, a headed-pass event, an off-side pass event, a take-on event, a foul event, a tackle event, an interception event, a clearance event, an aerial event, a ball recovery event, a bad ball handling event, a 50/50 ball event, a blocked pass event, a rebound event, a turnover event, or a screen event.
8. A system, comprising:
a processor; and
a memory having programming instructions stored thereon, which, when executed by the processor, causes the system to perform operations, comprising:
receiving one or more event indications corresponding to one or more events of a game from a tracking system, wherein each of the one or more event indications corresponds to an on-ball event, and wherein each of the one or more event indications include event data, and wherein the game includes one or more teams, and wherein the one or more teams include one or more players;
generating one or more features for each of the one or more events based on the corresponding event data;
generating, via a prediction model, a possession value metric for each of the one or more events based on the event data and the one or more features, wherein the possession value metric includes a numerical representation corresponding to a likelihood that a possession team will score within a time period after the one or more events;
aggregating the possession value metric for each of the one or more events to generate a momentum metric for each of the one or more teams;
generating a visual representation corresponding to the momentum metric; and
outputting the visual representation to a display of a device.
9. The system of claim 8 , wherein the operations further comprise:
generating an aggregate possession value for one or more categories for each of the one or more players.
10. The system of claim 9 , wherein the one or more categories include one or more of: a successful pass category, an unsuccessful pass category, a losing ball possession category, or a gaining ball possession category.
11. The system of claim 8 , wherein the operations further comprise:
identifying a target player of the one or more players on a first team of the one or more teams in at least one of the one or more events;
identifying a subset of additional events that involve the target player;
generating a subset of additional target possession values based on the subset of additional events; and
generating a plurality of metrics for the target player based on the subset of additional target possession values.
12. The system of claim 8 , wherein generating, via the prediction model, the possession value metric for each of the one or more events based on the event data and the one or more features includes:
generating via the prediction model, a plurality of decision trees; and
analyzing the plurality of decision trees to determine the possession value metric for each of the one or more events.
13. The system of claim 8 , wherein the one or more features may include at least one of: an event outcome, an event location, event cross data, event header data, free kick event data, corner kick event data, penalty kick event data, throw-in event data, an event end location, goal distance data, goal angle data, goal location data, event distance data, an event type identifier, previous event distance data, total speed data, or event direction speed data.
14. The system of claim 8 , wherein the on-ball event includes at least one of: a pass event, a throw-in event, a corner kick event, a free-kick event, a cross event, a headed-pass event, an off-side pass event, a take-on event, a foul event, a tackle event, an interception event, a clearance event, an aerial event, a ball recovery event, a bad ball handling event, a 50/50 ball event, a blocked pass event, a rebound event, a turnover event, or a screen event.
15. A non-transitory computer readable medium including one or more sequences of instructions that, when executed by one or more processors, causes a computing system to perform operations comprising:
receiving, by a computing system, one or more event indications corresponding to one or more events of a game from a tracking system, wherein each of the one or more event indications corresponds to an on-ball event, and wherein each of the one or more event indications include event data, and wherein the game includes one or more teams, and wherein the one or more teams include one or more players;
generating, by the computing system, one or more features for each of the one or more events based on the corresponding event data;
generating, by the computing system, via a prediction model, a possession value metric for each of the one or more events based on the event data and the one or more features, wherein the possession value metric includes a numerical representation corresponding to a likelihood that a possession team will score within a time period after the one or more events;
aggregating, by the computing system, the possession value metric for each of the one or more events to generate a momentum metric for each of the one or more teams;
generating, by the computing system, a visual representation corresponding to the momentum metric; and
outputting, by the computing system, the visual representation to a display of a device.
16. The non-transitory computer readable medium of claim 15 , the operations further comprising:
generating, by the computing system, an aggregate possession value for one or more categories for each of the one or more players.
17. The non-transitory computer readable medium of claim 15 , wherein the one or more features may include at least one of: an event outcome, an event location, event cross data, event header data, free kick event data, corner kick event data, penalty kick event data, throw-in event data, an event end location, goal distance data, goal angle data, goal location data, event distance data, an event type identifier, previous event distance data, total speed data, or event direction speed data.
18. The non-transitory computer readable medium of claim 15 , wherein the on-ball event includes at least one of: a pass event, a throw-in event, a corner kick event, a free-kick event, a cross event, a headed-pass event, an off-side pass event, a take-on event, a foul event, a tackle event, an interception event, a clearance event, an aerial event, a ball recovery event, a bad ball handling event, a 50/50 ball event, a blocked pass event, a rebound event, a turnover event, or a screen event.
19. The non-transitory computer readable medium of claim 15 , the operations further comprising:
identifying, by the computing system, a target player of the one or more players on a first team of the one or more teams in at least one of the one or more events;
identifying, by the computing system, a subset of additional events that involve the target player;
generating, by the computing system, a subset of additional target possession values based on the subset of additional events; and
generating, by the computing system, a plurality of metrics for the target player based on the subset of additional target possession values.
20. The non-transitory computer readable medium of claim 19 , wherein generating, via the prediction model, the possession value metric for each of the one or more events based on the event data and the one or more features includes:
generating, by the computing system, via the prediction model, a plurality of decision trees; and
analyzing, by the computing system, the plurality of decision trees to determine the possession value metric for each of the one or more events.