This dataset contains data for last 10 seasons of German Bundesliga including current season. The data is updated on weekly basis via Travis-CI. The dataset is sourced from http://www.football-data.co...

From a young age, hopeful talents devote time, money, and training to the sport. Yet, while the next superstar is guaranteed to start off in youth or semi-professional leagues, these leagues often have the fewest resources to invest. This includes resources for the collection of event data which helps generate insights into the performance of the teams and players.

****About Dataset:**** This dataset with 460 training and test videos in 2 folders was collected by dataset of competition videos. All videos are in MP4 format.

** Please note that the number of videos in each folder is different

Version 1 --> 460 MP4 file in 2 Folder + .CSV file Version 2 --> Coming Soon!

competition page: https://www.kaggle.com/competitions/dfl-bundesliga-data-shootout

wish you all the best

Bundesliga Videos dataset from Kaggle competition: https://www.kaggle.com/competitions/dfl-bundesliga-data-shootout

Here are a few use cases for this project:

1. Soccer Match Analysis: Using the "Bundesliga Data Shootout" model to analyze player performances, ball possession, and team strategies during soccer matches, offering insights to coaches and teams for improved tactics and decision-making.

2. Player Tracking and Positioning: The model can be used for tracking individual player movements, identifying offside positions, and generating heatmaps of player actions throughout a match, aiding coaches in understanding player contribution and effectiveness.

3. Augmented Reality Applications: Leveraging this model for augmented reality applications, enabling fans at home or in-stadium to identify players, receive real-time statistics, and view additional information by simply pointing their smartphone at the scene.

4. Broadcast Enhancements: Integrating the "Bundesliga Data Shootout" model into live sports broadcasts, allowing graphics to more accurately follow the ball, overlay player information, and highlight key moments, providing a more engaging viewer experience.

5. Injury Prevention and Rehabilitation: Utilizing the model to monitor player movements and biomechanics during matches or training, helping to identify potential injury risks, optimizing rehabilitation programs, and managing player loads to maintain peak physical condition.

Detailed report looking over the German Bundesliga for the 2020-21 season, taking a closer look at the league's sponsorship and media landscape. Read More

This is environmental data for each match of the German Bundesliga (seasons 2014-21) and Australian A-League (seasons 2016-20). Environmental conditions in the form of temperature and WBGT were collated retrospectively for each match. Whereas temperature refers to the commonly known and easily accessible ambient air temperature, WBGT is a feels-like temperature adding the influence of relative humidity, wind, and solar radiation, for a more detailed interpretation of the observed heat stress. The use, advantages, and disadvantages of WBGT have been described extensively in previous research.1-3 Despite its widespread use, the black globe temperature (radiative heat gain) and natural wet-bulb temperature (evaporative heat loss) measurements are criticized as not representing human thermoregulation, thereby underestimating heat stress in many settings.1,4 It should also be mentioned, that WBGT is a heat stress index and is not validated for colder conditions. Therefore, to interpret the effects of colder environments on injury occurrence temperature was also used in our analyses. Although more modern and sophisticated thermal indexes exist 4,5, WBGT remains widely used, especially in sports federation heat policies. Specifically, this index is also used in the heat policy introduced by FIFA, which recommends the use of drinking breaks at 32 °C WBGT6. For Bundesliga matches, weather data was obtained from Meteostat.net.7 This is an open-source service, providing hourly meteorological data for any given coordinates. Data is obtained as a weighted interpolation depending on the distance and elevation difference from the four closest weather stations to a geological location. They provide the following data: temperature, relative humidity, dew point, wind speed, air pressure, total precipitation, and the current weather condition. Based on this, WBGT can be estimated in a variety of ways according to previous research.2 We used the estimation developed by Liljegren et al. (2008).3 This is validated and reliable in different environmental settings and is described as the best estimate for WBGT from different methods.8 The R code needed to implement these calculations has been provided and used in previous research.9 Wind speed was assumed to be a minimum of 1 m/s, as moving players generate airflow of at least equivalent to that. Solar radiation was estimated using the solar angle at the time and location of the match10. As Meteostat.net provides hourly data, two time points (the kick-off time and one hour later) were used per match and averaged. If the match did not start at a full hour, but at 15 or 30 minutes past the hour, the previous full hour was used as a starting point and the following hour as a second time point. For A-League matches, environmental conditions were provided by UBIMET.com.11 This commercial provider uses artificial intelligence and data input from multiple weather stations, radar, and satellite data, to estimate meteorological data at given ground locations. They provide temperature, relative humidity, solar radiation, and WBGT measurements for the starting times of the first and second half, which were then averaged to create one value per match. To validate the WBGT data based on Meteostat.net data, the WBGT estimation method used for the Bundesliga data was also performed with the A-League data. As internal validation, results were then compared to the WBGT reported from UBIMET.com. There was a very good linear association (correlation coefficient r = 0.93). 1. Brocherie F, Millet G. Is the Wet-Bulb Globe Temperature (WBGT) Index Relevant for Exercise in the Heat? . Sports Med. 2015;45:1619-1621. 2. Lemke B, Kjellstrom T. Calculating Workplace WBGT from Meteorological Data: A Tool for Climate Change Assessment. Ind Health. 2012;50:267-278. 3. Liljegren J, Carhart RA, Lawday P, Tschopp S, Sharp R. Modelling the Wet Bulb Globe Temperature Using Standard Meteorological Measurements. J Occup Environ Hyg. 2008;5(10):645-655. 4. Blazejczyk K, Epstein Y, Jendritzky G, Staiger H, Tinz B. Comparison of UTCI to selected thermal indicies. Int J Biometeorol. 2012;56:515-535. doi:https://doi.org/10.1007/s00484-011-0453-2 5. Jendritzky G, de Dear R, Havenith G. UTCI - Why another thermal index? Int J Biometeorol. 2012;56:421-428. doi:https://doi.org/10.1007/s00484-011-0513-7 6. Brown H, Chalmers S, Topham T, et al. Efficacy of the FIFA cooling break heat policy during an intermittent treadmill football simulation in hot conditions in trained males. Br J Sports Med. 2024;doi:10.1136/bjsports-2024-108131 7. Meteostat.net. The Weather’s Record Keeper. https://meteostat.net/en/ 8. Patel T, Mullen SP, Santee WR. Comparison of Methods for Estimating Wet-Bulb Globe Temperature Index From Standard Meteorological Measurements. Military Medicine. 2013;178(8):926-933. 9. HeatStress. Casanueva, A; 2019. https://zenodo.org/records/3264930 10. Duffie J, Beckman W. Solar Engineering of Thermal Processes. 4th ed. John Wiley & Sons, Inc.; 2013. 11. UBIMET GmbH. UBIMET WEATHER MATTERS. https://www.ubimet.com/en/

Skill-based vs. effort-based performance data of football Bundesliga teams in ghost and regular matches of the 2019/2020 season

Categories of situational and environmental (independent) variables and performance indicators (dependent variables) and its definition and/or collection procedures.

Scraped player stats per game from Understat from 2014/2015 to 2024/2025 (still in progress) seasons.

This contains more detailed information than the dataset from https://www.kaggle.com/datasets/codytipton/understat-data, which includes the individual player stats per game for the English Premier League, La Liga, Bundesliga, Serie A, Ligue 1, and the Russian Football Premier League. In particular, it contains each player's xG, xGBuildup, goals, and shots per game. Furthermore, it has the events for each shot in the events table, clubs and their stats per season in the clubs table, and each game with who lost, won, shots, possession, probabilities of who wins, ect..

This is for educational purposes in our data science bootcamp project.

lineup_stats

• match_id: the id for the match they played
• goals: number of goals for this match
• own_goals: number of own goals for this match
• shots: number of shots for this match
• xG: players xG for this match
• **time*: total amount of time this player played in this match
• player_id: player id
• team_id: id for the players team
• position: players position in this match (SUB means they were substituted in)
• player: player's name
• h_a: 'h' if they are in the home team and 'a' if they are in the away team
• yellow_card: number of yellow cards for this match
• red_card: number of red cards for this match
• **roster_in*: (there is roster information in another table that I did not get, will update later)
• roster_out: (same as roster_in)
• key_passes: number of key passes for this match
• assists: number of assists for this match
• xA: expected assists for this match
• xGChain: total xG for every possession the player is involved in this match
• xGBuildup: Total xG for every possession the player is involved in without key passes and shots in this match
• positionOrder: ordering in the lineup

general_game_stats

• id: this game id
• fid: not sure what this is
• h_id: home team id
• a_id: away team id
• date: date of this game
• league_id: id for the league
• season: which season which game was for
• h_goals: number of goals for the home team
• a_goals: number of goals for the away team
• team_h: home team name
• team_a: away team name
• h_xg: home xG
• a_xg: away xG
• h_w: home win probability
• h_d: home draw probability
• h_l: home loss probability
• league: league name
• h_shot: number of shots by the home team
• a_shot: number of shots by the away team
• h_shotOnTarget: number of shots on target by the home team
• a_shotOnTarget: number of shots on target by the away team
• h_deep:home team passes completed within an estimated 20 yards of goal (crosses excluded) -deap_allowed: opponent passes completed within an estimated 20 yards of goal (crosses excluded)
• a_deep: away team passes completed within an estimated 20 yards of goal (crosses excluded) -deap_allowed: opponent passes completed within an estimated 20 yards of goal (crosses excluded)
• h_ppda: home team passes allowed per defensive action in the opposition half.
• a_ppda:away team passes allowed per defensive action in the opposition half.

game_events

• id: id for event
• minute: minute the event happend
• result: result (blocked shot, saved shot, ect..)
• X: x-coordinate where the player took the shot
• Y: y-coordinate where the player took the shot
• xG: the xG for the shot
• player: player's name
• h_a: h for home team or a for away team
• player_id: player's id
• situation: situation where this shot happend (direct free kicks, set piece, open play, ect..)
• season: the match season
• shotType: what type of shot (left foot, right foot, head, ect..)
• ** match_id**: id for the match
• h_team: home team name
• ** a_team**: away team name
• ** h_goals**: number of home goals at this time
• ** a_goals**: number of away goals at this time
• date: date of the match
• ** player_assisted**: player who assisted
• lastAction: the last action before this shot

clubs

• club_id: id for the club
• ** club**: club name
• ** league_id** : league id
• ** league**: league name
• ** season**: which season these stats are from
• ** wins**: number of wins that season
• ** draws**: number of draws that season
• ** losses**: number of losses that season
• ** pts**: number of points for that season
• ** avg_xG**: average xG throughout the season
• ** total_goals**: total amount of goals for this season
• total_goals_cond: total amount of goals conceded this season

The displayed data on interest in Bundesliga clubs shows results of the Statista European Football Benchmark conducted in England in 2018. Some * percent of respondents stated that they are interested in the Bundesliga Club Borussia Dortmund.

Complete database of football players with most titles including Champions League, La Liga, Premier League, Serie A, Bundesliga, and international tournaments

The novel Passau-Spontaneous Football Coach Humor (Passau-SFCH) dataset consists of press conference recordings of 10 different German Bundesliga football coaches collected in 2017. The data provided here only includes segments in which the respective coach is speaking, accounting for about 11 hours of data.

There are three continuous annotations (2 Hz rate): Humour, as well as sentiment and direction (self- vs. others-directed) as proposed in the Humor Style Questionnaire by [1].

For a detailled description of the data, see [2].

The package includes:

raw data

segmented videos

segmented audios

manually corrected transcriptions

extracted features, cf. [2]

gold standard labels, cf. [2]

Note that a variant of this dataset has been featured in the Multimodal Sentiment Analysis Challenge (MuSe) 2022 [3,4]. For questions, please contact Lukas Christ at lukas[dot]christ[at]informatik[dot]uni-augsburg[dot]de.

[1] Martin, Rod A., et al. "Individual differences in uses of humor and their relation to psychological well-being: Development of the Humor Styles Questionnaire." Journal of research in personality 37.1 (2003): 48-75.

[2] L. Christ, S. Amiriparian, A. Kathan, N. Müller, A. König, B. W. Schuller, "Multimodal Prediction of Spontaneous Humour: A Novel Dataset and First Results". arXiv preprint at arXiv: 2209.14272

[3] ] L. Christ, S. Amiriparian, A. Baird, P. Tzirakis, A. Kathan, N. Müller, L. Stappen, E.-M. Meßner, A. König, A. Cowen, E. Cambria, and B. W. Schuller, "The Muse 2022 Multimodal Sentiment Analysis Challenge: Humor, Emotional Reactions, and Stress" in MuSe’22: Proceedings of the 3rd Multimodal Sentiment Analysis Workshop and Challenge. Lisbon, Portugal: Association for Computing Machinery, 2022, pp. 5–14, co-located with ACM Multimedia 2022, to appear.

[4] S. Amiriparian, L. Christ, A. König, E.-M. Meßner, A. Cowen, E. Cambria, and B. W. Schuller, “Muse 2022 challenge: Multimodal humour, emotional reactions, and stress,” in Proceedings of the 30th ACM International Conference on Multimedia (MM’22). Lisbon, Portugal: Association for Computing Machinery, October 2022, 3 pages, to appear.

The aim of the study was to examine the impact of the positional role and the individuality on the technical match performance in professional soccer players. From official match data of the Bundesliga season 2018/19, technical performance [short (30 m) passes, dribblings, ball possessions] of all players who played during the season were analyzed (normative data). Five playing positions (center back, full back, central midfielder, wide midfielder and forward) were distinguished. As the contextual factor tactical formation is known to influence match performance, this parameter was controlled for. Further, those players who played at minimum four games in at least two different playing positions were included in the study sample (n = 13). The technical match performance of the players was analyzed in relation to the normative data regarding the extent to which the players either adapted or maintained their performance when changing the playing position. When switching playing positions, positional role could explain 3–6% of the variance in short passes and ball possessions and 27–44% of the variance in dribblings, medium passes, and long passes. Moreover, we observed large interindividual differences in the extent to which a player changed, adapted, or maintained his performance. In detail, five players clearly adapted their technical performance when changing playing positions, while five players maintained their performance. Coaches can use these findings to better understand the technical match performance of single players and further, to estimate the impact of a change in the positional role on the technical performance of the respective player.

The predictions of the goal difference of the second half of the Bundesliga-season 2007/08 for each team, based on the differences of chances for goals of the previous season (3rd column) or, additionally, on the differences of chances for goals of the first 17 matches of the present season (4th column).

This dataset is undertaken to create a predictive model for the transfer values of football players. We will utilize data from football players and construct a model to predict transfer fees based on that data. Player data includes basic information such as age, height, playing position, as well as professional statistics like goal scoring, assists (in 2 season 2021-2022 and 2022-2023), injuries, along with total individual and team awards in their career.

We had gathered information on players competing in several top-tier global football leagues:

11 European leagues, including the Premier League and Championship in England, Bundesliga in Germany, La Liga in Spain, Serie A in Italy, Ligue 1 in France, Eredivisie in the Netherlands, Liga NOS in Portugal, Premier Liga in Russia, Super Lig in Turkey, and Bundesliga in Austria.

4 American leagues, including Brasileiro in Brazil, Major League Soccer in the United States, Primera División in Argentina, and Liga MX in Mexico.

1 African league, namely the DStv Premiership in South Africa.

4 Asian leagues, comprising J-League in Japan, Saudi Pro League in Saudi Arabia, K-League 1 in South Korea, and A-League in Australia.

Context The dataset is scraped from many resources and edited by me the top website is Infogol Infogol has league tables and statistics from some of the top competitions from all around the world, including the English Premier League, English Championship, Spanish La Liga, Italian Serie A, German Bundesliga, French Ligue 1, US MLS and Brazilian Série A, . Choose the competition you are interested in to get the actual league table, plus expected and forecast positions based on the Infogol model, along with top scorers and betting odds. Content This dataset includes top football leagues scorers their goals ,Country, Club, matches played ,substitution, min ,Goals, xG,... Note : xG & xG Per Avg Match is a statistical value that is supported by the website I scraped the data from (Infogol) Acknowledgements The data in this dataset has been scraped using Selenium from Infogol website Some leagues in some seasons ate not forund right now because the website not supporting it so in the next update all the seasons will be found

This data depicts the average viewing audience of Bundesliga clubs on Sky Deutschland as of the thirty-second match day during the 2019/2020 season. In the period of consideration, an average of roughly **** million television viewers watched the live broadcasts of matches of the Bundesliga club FC Bayern Munich on the pay-TV channel.

The return-to-sport (RTS) process is multifaceted and complex, as multiple variables may interact and influence the time to RTS. These variables include intrinsic factors related the player, such as anthropometrics and playing position, or extrinsic factors, such as competitive pressure. Providing an individualised estimation of time to return to play is often challenging, and clinical decision support tools are not common in sports medicine. This study uses epidemiological data to demonstrate a Bayesian Network (BN). We applied a BN that integrated clinical, non-clinical factors, and expert knowledge to classify time day to RTS and injury severity (minimal, mild, moderate and severe) for individual players. Retrospective injury data of 3374 player seasons and 6143 time-loss injuries from seven seasons of the professional German football league (Bundesliga, 2014/2015 through 2020/2021) were collected from public databases and media resources. A total of twelve variables from three categories (player’s characteristics and anthropometrics, match information and injury information) were included. The response variables were 1) days to RTS (1–3, 4–7, 8–14, 15–28, 29–60, > 60, and 2) injury severity (minimal, mild, moderate, and severe). The sensitivity of the model for days to RTS was 0.24–0.97, while for severity categories it was 0.73–1.00. The user’s accuracy of the model for days to RTS was 0.52–0.83, while for severity categories, it was 0.67–1.00. The BN can help to integrate different data types to model the probability of an outcome, such as days to return to sport. In our study, the BN may support coaches and players in 1) predicting days to RTS given an injury, 2) team planning via assessment of scenarios based on players’ characteristics and injury risk, and 3) understanding the relationships between injury risk factors and RTS. This study demonstrates the how a Bayesian network may aid clinical decision making for RTS.

Description: Predicting the presence of humor in football press conference recordings. Available modalities: audio and video, transcriptions will follow in May.

Labels: windows of 2 seconds are given a binary label, indicating presence and absence of humor. 9 human annotators labelled each video.

Dataset: MuSe-Humor is based on the novel Passau-Spontaneous Football Coach Humor (Passau-SFCH) dataset. It includes press conference recordings of 10 different German Bundesliga football coaches collected in 2017. The data provided here only includes segments in which the respective coach is speaking. The training data set contains recordings of 4 coaches, development and test data each contain recordings of 3 coaches.

General: The 3rd Multimodal Sentiment Analysis Challenge and Workshop (MuSe) 2022 adresses research questions that are of interest to affective computing, machine learning and multimodal signal processing communities and encourages a fusion of their disciplines. The goal of the MuSe workshop and challenge is to gain new insights into the merits of each of the core modalities and to serve as a stimulating environment for the development and evaluation of multimodal affect recognition approaches.

bundesliga betting tips2025-09-17 05:49