# Football Match Probability Prediction — Data 来源：https://www.kaggle.com/competitions/football-match-probability-prediction/data 本地 Meta Kaggle 快照；不是本次实时页面。 # Dataset Description The data set contains more than 150000 historical world football matches from 2019 to 2021, with more than 860 leagues and 9500 teams. Your goal is to predict the probabilities for each match outcome in the `target` columns: the probabilities of `home` to win, `draw,` and `away` to win. ## Features, Home and Away meaning The features provided are divided into two parts: **the descriptive features** and **the historical features**. Descriptive features are point-in-time descriptions of the match that has to be predicted. Historical features contain past information of the 10 games previously played by the Home and the Away team. Home and Away are used by convention to describe a match between two teams **Home - Away**. For instance **Manchester City - Chelsea**. In this case, Manchester City plays home. For cups, the Home team does not necessarily play home, but the information is not available in the dataset. Note that for historical data, to know which team plays home, please refer to the column of historical data `is_play_home` as the **Home** and the **Away** team can have played home or away in their 10 last matches. ## Files * **train.csv** - the training set * **test.csv** - the test set, does not have the target column. * **sample_submission.csv** - a sample submission file in the correct format * **train_target_and_scores.csv** - contains each match's final score **Home - Away** in addition to the target which is also in the training set. More information [here](https://www.kaggle.com/c/football-match-probability-prediction/discussion/314078). ## Descriptive columns * `target` - The variable you have to predict the probabilities only available in the train set. * `home_team_name` - The name of the **Home** the team. Hidden in test set, see [this discussion](https://www.kaggle.com/competitions/football-match-probability-prediction/discussion/314744) * `away_team_name` - The name of the **Away** the team. Hidden in test set, see [this discussion](https://www.kaggle.com/competitions/football-match-probability-prediction/discussion/314744) * `match_date` - The match date (UTC). * `league_name` - The league name. * `league_id` - The league id. Note that league names can be identical for two differents id. * `is_cup` - If the value is 1 the match is played for a cup compettion. * `home_team_coach_id ` - The id of the **Home** team coach. * `away_team_coach_id ` - The id of the **Away** team coach. ## Historical columns Historical columns contain the key world `history` and are indexed with numbers from 1 to 10 for the last 10 matches played by the two teams. The number **1** means the most recent while **10** is the oldest. Note that the historical matches can have been played in different leagues. For instance `home_team_history_match_date_1` is the date of the last match played by the home team while `home_team_history_match_date_2` is two matches ago. Another example, `home_team_history_is_play_home_3` tells you if the team played home 3 matches ago and `home_team_history_opponent_rating_3` what was the opponent rating. **Historical home team features** * `home_team_history_match_date_{i}` - The date of the last i-th match played by **Home** team. * `home_team_history_is_play_home_{i}` - If 1, the **Home** team played home. * `home_team_history_is_cup_{i}` - If 1, the match was a cup competition. * `home_team_history_goal_{i}` - The number of goals scored by the **Home** team on its last i-th match. * `home_team_history_opponent_goal_{i}` - The number of goals conceded by the **Home** team on its last i-th match. * `home_team_history_rating_{i}` - The rating of the **Home** team on its last i-th match (pre match rating). * `home_team_history_opponent_rating_{i}` - The rating of the opponent team on **Home** team last i-th match (pre match rating). * `home_team_history_coach_{i}` - The coach id of the **Home** team on its last i-th match. * `home_team_history_league_id_{i}` - The league name id by the **Home** team on its last i-th match. **Historical away team features** * `away_team_history_match_date_{i}` - The date of the last i-th match played by **Away** team. * `away_team_history_is_play_home_{i}` - If 1, the **Away** team played home. * `away_team_history_is_cup_{i}` - If 1, the match was a cup competition. * `away_team_history_goal_{i}` - The number of goals scored by the **Away** team on its last i-th match. * `away_team_history_opponent_goal_{i}` - The number of goals conceded by the **Away** team on its last i-th match. * `away_team_history_rating_{i}` - The rating of the **Away** team on its last i-th match (pre match rating). * `away_team_history_opponent_rating_{i}` - The rating of the opponent team on **Away** team last i-th match (pre match rating). * `away_team_history_coach_{i}` - The coach id of the **Away** team on its last i-th match. * `away_team_history_league_id_{i}` - The league name id played by the **Away** on its last i-th match. ## What are the rating features? The rating features are calculated by Octosport. Ratings are meant to give information on the team's relative strength for a given match. For instance, we would expect that a team with a rating of 10.5 beats a team with a rating of 2.3.