According to a 2025 survey, the age group with the largest share of individuals with an online sports betting acount in the United States was ********-years-old. In total, ** percent of U.S. adults belonging to this demographic had an account with an online sportsbook.

Sports Betting Predictive Analysis Dataset

This comprehensive synthetic dataset contains 1,369 rows and 10 columns specifically designed for predictive modeling in sports betting analytics. The dataset provides a rich foundation for machine learning applications in the sports betting domain, featuring realistic match data across multiple sports with comprehensive betting odds, team information, and outcome predictions.

Dataset Overview Table

Key Applications

Machine Learning Use Cases

• Outcome Prediction Models: Train classification algorithms to predict match winners
• Odds Analysis: Analyze betting market efficiency and identify value bets
• Feature Engineering: Create derived features for advanced predictive models
• Model Validation: Compare predicted vs actual outcomes for performance metrics
• Risk Assessment: Evaluate betting strategy performance and risk management

Data Science Applications

• Exploratory Data Analysis: Understand patterns in sports betting markets
• Statistical Modeling: Build probabilistic models for outcome prediction
• Time Series Analysis: Analyze temporal trends in betting odds and outcomes
• Comparative Analysis: Study performance differences across sports and teams
• Visualization Projects: Create interactive dashboards for betting analytics

Research Applications

• Academic Research: Study sports betting market dynamics
• Algorithm Development: Test new machine learning approaches
• Benchmarking: Compare different predictive modeling techniques
• Educational Projects: Learn data science concepts with realistic data
• Portfolio Development: Demonstrate skills in sports analytics domain

Data Characteristics

Realistic Market Simulation

• Betting odds within industry-standard ranges (1.2 - 5.0)
• Sport-specific logic (draws only applicable for Football and Hockey)
• Strategic null value placement to simulate real-world data gaps
• Temporal consistency across 2-year historical period
• Unique match identifiers for easy reference and tracking

Comprehensive Coverage

• Multi-Sport Analysis: Five major sports for diverse modeling scenarios
• Balanced Distribution: Even representation across all sports categories
• Team Diversity: Unique city-based team names preventing data leakage
• Outcome Variety: Includes wins, losses, and draws where applicable
• Prediction Comparison: Both model predictions and actual results included

According to a survey conducted in January 2025, Latinos were the most likely ethnic group to have engaged in betting on sports events in the United States. Specifically, ** percent of Latinos had participated in sports betting at least once in their lives.

Dataset Card: Soccer Stats Database

  Dataset Summary

The Soccer Stats Database is a structured dataset built for analyzing and optimizing profits in football betting. The dataset includes historic and upcoming match results, team statistics, betting odds, model inference results, and optimization outcomes. It is designed to provide comprehensive data for exploring and implementing models for sports betting optimization, as discussed in the accompanying article on my blog.… See the full description on the dataset page: https://huggingface.co/datasets/JulienDelavande/soccer_stats.

The global sports betting data service market size was valued at USD 1.3 billion in 2025 and is projected to grow from USD 1.5 billion in 2026 to USD 3.1 billion by 2033, exhibiting a CAGR of 10.4% during the forecast period. The increasing popularity of sports betting and the growing demand for data-driven insights to make informed betting decisions are driving the growth of the market. Furthermore, the advancements in technology, such as artificial intelligence (AI) and machine learning (ML), are enabling the provision of more accurate and personalized data, which is further fueling the market growth. The market is segmented into various applications including sports media, sports teams, sponsor brands, and others. The sports media segment held the largest market share in 2025 and is expected to continue its dominance throughout the forecast period. This is attributed to the increasing demand for sports betting data by media companies to enhance their coverage and provide value-added services to their viewers. Other key segments include sports teams, which use data to analyze player performance and make strategic decisions, and sponsor brands, which use data to measure the effectiveness of their campaigns and optimize their marketing strategies. Geographically, North America accounted for the largest market share in 2025 and is projected to maintain its dominance during the forecast period. The region's high adoption of sports betting and the presence of major sports leagues are driving the growth of the market. Europe and Asia Pacific are other key regions with significant market potential due to the growing popularity of sports betting and the increasing investment in data analytics. Introduction The global sports betting data service market has witnessed a surge in demand as the legalization of sports betting expands across jurisdictions. These services provide valuable data and insights to sportsbooks, media companies, and other stakeholders to enhance their operations and engage audiences.

The NCAA Division I Basketball Tournament, also known as March Madness, is an annual knockout tournament between the best college basketball teams in the United States. While some fans enjoy just watching the games, others also choose to bet on them with the potential to earn money or goods. In 2025, it was estimated that 3.1 billion U.S. dollars would be bet on March Madness in the U.S., showing a margnial increase when compared to the previous year's estimate. However, it remained way below the figure recorded in 2023.

NBA Betting Lines

NBA Moneyline, Spread and Total Bets

By [source]

About this dataset

This extensive dataset is an absolute must-have for bettors, sports enthusiasts, and data scientists eager to gain insight into the inner workings of professional basketball. It comprises over 100 data points, offering a wealth of information on betting lines from December 2nd 2021 to December 11th 2022, including moneyline, spread, and total bets along with game date, period and team information; plus 1st, 2nd, 3rd and 4th quarter scores; and final scores. This powerful dataset can not only be used to inform bettors on the best betting opportunities available at any given point in time—through uncovering patterns or relationships between outcomes—but also be utilized by research professionals or statisticians to demonstrate how certain events or circumstances impact sporting events across the board. Get ready for a one-of-a-kind experience as you unlock invaluable knowledge about sports betting trends!

More Datasets

For more datasets, click here.

Featured Notebooks

• 🚨 Your notebook can be here! 🚨!

How to use the dataset

This dataset offers an extensive collection of NBA betting trends from December 2nd 2021 to December 11th 2022. With information related to moneyline, spread, and total bets, game date, period, and team information, and scores for each quarter as well as the final score of each game – this data set is valuable tool in your sports betting arsenal.

Analyzing Trends To uncover hidden trends in today’s NBA games – you can use this dataset to compare data points among teams over a given amount of time. Data points such as games won/lost, points scored per game/per period etc... can be compared between two or more teams that are competing against one another during the same time frame. This comparison can then be used to analyze which team should be favored when it comes to making a bet on a particular sporting event or match-up.

Evaluating Odds You can also use this dataset to evaluate the odds which are typically set by bookmakers before any given sporting event takes place. By utilizing data related to money line bets, spreads and totals – you gain something called “value” which describes whether or not there is any chance that you might earn more money if all the factors surrounding a particular bet come up with the expected results . If the value of your bet is greater than what bookmakers expected it would be - then there is an opportunity for profit making if all goes according plan when placing your wager!

Making Effective Wagers 

Using this data set will help you make informed decisions when it comes placing wagers on professional basketball matches. Be sure to analyze available upcoming lines carefully when tilting towards certain players/teams... Taking into consideration how their performance has been within past weeks rather than months could mean find yourself on top with some positive returns already made! Don't forget: Always check out statistical averages prior making bets so that way they give proper decision weighting possibilities (in terms of odds)

Research Ideas

• Discovery of insights into player performance and the factors that affect it, such as playing conditions, fatigue, injuries and opponent strength: by analyzing betting lines before and after key events (e.g. trades, acquisitions) researchers can assess the impact of these events on player performance and team success/failure
• For trend tracking across seasons: by analyzing betting lines over multiple seasons users can identify changes in the market that create favorable plays or unfavorable ones over time
• To better understand line movements between different sports books: this dataset provides an avenue to compare and contrast betting lines from a variety of sports books in order to gain deeper insight into fluctuations in odds between them

Acknowledgements

If you use this dataset in your research, please credit the original authors. Data Source

License

License: CC0 1.0 Universal (CC0 1.0) - Public Domain Dedication No Copyright - You can copy, modify, distribute and perform the work, even for commercial purposes, all without asking permission. See Other Information.

Acknowledgements

If you use this dataset in your research, please credit the original authors. If you use this dataset in your research, please credit .

The Challenge

The online sports gambling industry employs teams of data analysts to build forecast models that turn the odds at sports games in their favour. While several betting strategies have been proposed to beat bookmakers, from expert prediction models and arbitrage strategies to odds bias exploitation, their returns have been inconsistent and it remains to be shown that a betting strategy can outperform the online sports betting market. We designed a strategy to beat football bookmakers with their own numbers:

"Beating the bookies with their own numbers - and how the online sports betting market is rigged", by Lisandro Kaunitz, Shenjun Zhong and Javier Kreiner.

Here, we make the full dataset publicly available to the Kaggle community. We also provide the codes, raw SQL database and the online real-time dashboard that were used for our study on github.

Our strategy proved profitable in a 10-year historical simulation using closing odds, a 6-month historical simulation using minute to minute odds, and a 5-month period during which we staked real money with the bookmakers. We would like to challenge the Kaggle community to improve our results:

• Can your strategy consistently beat the sports betting market over thousands of bets across leagues around the world?
• Do time series odds movements offer insightful information that a betting strategy can exploit?
• Can you outperform the bookmakers’ predictions included in the odds data by creating a better model?

What's inside the Beat The Bookie dataset

10 year historical closing odds:

• 479,440 football games from 818 leagues around the world
• Games from 2005-01-01 to 2015-07-30.
• Maximum, average and count of active odds at closing time (start of the match)
• Betting odds from up to 32 providers
• Details about the match: date and time, league, teams, 90-minute score

14-months time series odds:

• 92,647 football games from 1005 leagues around the world
• Games from 2015-09-01 to 2016-11-22
• Hourly sampled odds time series, from up to 32 bookmakers from 72 hours before the start of each game
• Details about the match: date and time, league, teams, 90-minute score

The dataset was assembled over months of scraping online sport portals.

We hope you enjoy your sports betting simulations (but remember... the house always wins in the end).

Acknowledgements

Ben Fulcher was of great help when we were drafting the paper. Ben has also developed a very nice toolbox for time-series analysis, which might be relevant for the analysis of this dataset.

According to a survey from February 2024, ** percent of adults in the United States who were betting on the Super Bowl were wagering on the Kansas City Chiefs. Meanwhile, ** percent of respondents answered that they were betting on the San Francisco *****.

Paragraph 1: The global sports betting data service market is experiencing significant growth, driven by the rising popularity of sports betting worldwide. The market size, valued at XXX million in 2025, is projected to reach XXX million by 2033, exhibiting a CAGR of XX%. Factors contributing to this growth include increasing internet penetration, legalization of sports betting in various countries, and the growing demand for accurate and up-to-date data from sports enthusiasts, betting companies, and media organizations. Paragraph 2: The market is segmented based on type (live betting data service, pre-match betting data service, historical betting data service) and application (sports media, sports teams, sponsor brands, others). Key players in the market include Sportradar Group, Betradar, OddsMatrix, SportsScore, and Gracenote. The market is characterized by intense competition, with vendors focusing on expanding their data offerings, providing customized solutions, and improving the accuracy and timeliness of their services. Innovations in data analytics and machine learning are expected to drive further growth in the market, providing valuable insights for sports enthusiasts, betting companies, and industry stakeholders.

Incorporating fuzzy logic-based models into sports prediction has generated significant interest due to the intricate nature of athletic events and the many factors influencing their outcomes. This study evaluates the effectiveness of fuzzy logic-based models in predicting sports event outcomes using a hybrid CRITIC-VIKOR approach. The objective is to improve the accuracy and reliability of sports predictions by addressing the complexity and uncertainty inherent in sports data. The study utilizes a comprehensive dataset comprising historical data on team performance, player statistics, and other relevant factors influencing sports outcomes. The CRITIC method determines each criterion’s importance, while the VIKOR method ranks the predictive models to identify the optimal choice. Key findings indicate that the proposed hybrid approach significantly enhances the precision of predictions compared to traditional methods. The best-performing model identified through this approach provides reliable decision support for sports analysts, coaches, and managers. The study recommends incorporating this integrated model into sports analytics for better team management and sports betting decision-making.

The global sports betting market size reached USD 103.08 Billion in 2024. Looking forward, IMARC Group expects the market to reach USD 224.12 Billion by 2033, exhibiting a growth rate (CAGR) of 8.56% during 2025-2033. The market is propelled by the rising popularity of e-sports and competitive gaming, increasing adoption of advanced technologies such as virtual reality (VR) and AR, increasing demand for personalized and ergonomic gaming peripherals, rising penetration of internet and smartphones, and cultural enthusiasm among individuals.

IMARC Group provides an analysis of the key trends in each segment of the market, along with forecasts at the global, regional, and country levels for 2025-2033. Our report has categorized the market based on platform, betting type, and sports type.

Source

https://www.football-data.co.uk/

Columns

Div = League Division Date = Match Date (dd/mm/yy) HomeTeam = Home Team AwayTeam = Away Team FTHG and HG = Full Time Home Team Goals FTAG and AG = Full Time Away Team Goals FTR and Res = Full Time Result (H=Home Win, D=Draw, A=Away Win) HTHG = Half Time Home Team Goals HTAG = Half Time Away Team Goals HTR = Half Time Result (H=Home Win, D=Draw, A=Away Win) B365H = Bet365 home win odds B365D = Bet365 draw odds B365A = Bet365 away win odds BWH = Bet&Win home win odds BWD = Bet&Win draw odds BWA = Bet&Win away win odds IWH = Interwetten home win odds IWD = Interwetten draw odds IWA = Interwetten away win odds VCH = VC Bet home win odds VCD = VC Bet draw odds VCA = VC Bet away win odds WHH = William Hill home win odds WHD = William Hill draw odds WHA = William Hill away win odds Unique_ID = Unique ID

Divisions

E0: English Premier League E1: Championship E2: English League 1 E3: English League 2 EC: English Conference

D1: Bundesliga 1 D2: Bundesliga 2

I1: Serie A I2: Serie B

SP1: La Liga Primera Division SP2: La Liga Segunda Division

F1: Le Championnat F2: France Division 2

N1: Eredivisie (Netherlands)

B1: Jupiler League (Belgium)

P1: Liga I (Portugal)

T1: Futbol Ligi 1 (Turkey)

G1: Ethniki Katigoria (Greece)

Explore the burgeoning Sports Analytics Tools market, projected for substantial growth driven by AI, ML, and data-driven insights for performance optimization, fan engagement, and betting. Discover market size, CAGR, drivers, restraints, segments, and key players.

Liga Indo Football Season

Teams, Results, and Statistics

By Irnadia Fardila [source]

About this dataset

This dataset contains information on Liga Indo football matches. It includes such data as the teams playing, the date and time of the match, and the half-time and full-time scores

More Datasets

For more datasets, click here.

Featured Notebooks

• 🚨 Your notebook can be here! 🚨!

How to use the dataset

This dataset can be used to study the 2017 Liga Indo football season. It can be used to analyze team performance, results, and statistics

Research Ideas

• Sports betting
• Predicting the outcome of future matches
• Analyzing team and player performance over time

Acknowledgements

If you use this dataset in your research, please credit the original authors. Data Source

License

See the dataset description for more information.

Columns

File: liga_indo_2017.csv | Column name | Description | |:--------------|:-------------------------------------------| | SEASON | The season of the match. (String) | | DATE_TIME | The date and time of the match. (String) | | TEAM_HOME | The home team. (String) | | TEAM_AWAY | The away team. (String) | | FTG_HOME | The home team's full time goals. (Integer) | | FTG_AWAY | The away team's full time goals. (Integer) | | HTG_HOME | The home team's half time goals. (Integer) | | HTG_AWAY | The away team's half time goals. (Integer) |

File: liga_indo_2019.csv | Column name | Description | |:--------------|:-------------------------------------------| | SEASON | The season of the match. (String) | | DATE_TIME | The date and time of the match. (String) | | TEAM_HOME | The home team. (String) | | TEAM_AWAY | The away team. (String) | | FTG_HOME | The home team's full time goals. (Integer) | | FTG_AWAY | The away team's full time goals. (Integer) | | HTG_HOME | The home team's half time goals. (Integer) | | HTG_AWAY | The away team's half time goals. (Integer) |

File: liga_indo_2018.csv | Column name | Description | |:--------------|:-------------------------------------------| | SEASON | The season of the match. (String) | | DATE_TIME | The date and time of the match. (String) | | TEAM_HOME | The home team. (String) | | TEAM_AWAY | The away team. (String) | | FTG_HOME | The home team's full time goals. (Integer) | | FTG_AWAY | The away team's full time goals. (Integer) | | HTG_HOME | The home team's half time goals. (Integer) | | HTG_AWAY | The away team's half time goals. (Integer) |

File: liga_indo_2021_2022.csv | Column name | Description | |:--------------|:-------------------------------------------| | SEASON | The season of the match. (String) | | DATE_TIME | The date and time of the match. (String) | | TEAM_HOME | The home team. (String) | | TEAM_AWAY | The away team. (String) | | FTG_HOME | The home team's full time goals. (Integer) | | FTG_AWAY | The away team's full time goals. (Integer) | | HTG_HOME | The home team's half time goals. (Integer) | | HTG_AWAY | The away team's half time goals. (Integer) |

Acknowledgements

If you use this dataset in your research, please credit the original authors. If you use this dataset in your research, please credit Irnadia Fardila.

Sports Data Services Market Outlook

The global Sports Data Services market size reached USD 5.4 billion in 2024, according to our latest research. The market is witnessing a robust growth trajectory, with a projected CAGR of 19.2% from 2025 to 2033. By the end of 2033, the Sports Data Services market is forecasted to attain a value of USD 23.7 billion. This remarkable expansion is driven by the increasing digitization of sports, rising demand for real-time analytics, and growing investments in advanced data technologies across the sports ecosystem.

One of the primary growth drivers for the Sports Data Services market is the escalating adoption of data analytics for performance optimization and strategic decision-making. Sports organizations, ranging from professional leagues to grassroots teams, are leveraging advanced analytics platforms to evaluate player performance, monitor health metrics, and devise winning strategies. The integration of wearable technology and IoT devices has further amplified the ability to collect granular data, enabling coaches and analysts to make data-driven decisions that enhance both individual and team outcomes. This trend is particularly pronounced in high-stakes sports such as football, basketball, and cricket, where marginal gains can translate into significant competitive advantages.

Another significant factor contributing to market growth is the surge in fan engagement initiatives powered by data-driven solutions. Sports franchises and media companies are increasingly utilizing real-time statistics, predictive analytics, and interactive platforms to deliver immersive experiences to fans. The proliferation of fantasy sports, personalized content delivery, and augmented reality applications has created new revenue streams and fostered deeper connections between fans and their favorite teams. As digital consumption of sports content continues to rise, the demand for sophisticated data services that can provide actionable insights and engaging storytelling is expected to accelerate further.

The expanding role of sports betting and gambling also plays a pivotal role in the growth of the Sports Data Services market. Accurate, real-time data has become indispensable for betting companies, ensuring fair play and enhancing the transparency of betting activities. Regulatory developments in key markets, such as the legalization of sports betting in parts of North America and Europe, have spurred investments in secure and reliable data infrastructure. This, in turn, has attracted new entrants and increased competition, fostering innovation and driving the adoption of advanced data services in the betting segment.

In the realm of sports betting, the demand for accurate and timely data has never been more critical. Sports Betting Data Feeds play a crucial role in this ecosystem, providing sportsbooks with the real-time information necessary to set odds, manage risks, and ensure compliance with regulatory standards. These data feeds are meticulously curated to deliver up-to-the-minute statistics, player information, and game outcomes, which are essential for both operators and bettors. As the sports betting industry continues to expand, particularly in regions where legal frameworks are evolving, the reliance on robust data feeds is expected to grow, driving further innovation and investment in this segment.

From a regional perspective, North America continues to dominate the Sports Data Services market, accounting for the largest share in 2024, followed closely by Europe. The Asia Pacific region is emerging as a high-growth market, fueled by the rapid digitalization of sports, growing investments in infrastructure, and the rising popularity of international sports leagues. Latin America and the Middle East & Africa are also witnessing increased adoption, albeit at a slower pace, as local sports organizations and broadcasters begin to recognize the value of data-driven insights. The global landscape is characterized by a dynamic mix of established players and innovative startups, each contributing to the ongoing evolution of the market.

A fantasy sport is a type of game, typically played online, where participants put together imaginary or virtual teams composed of proxies of real players of a professional sport. These teams compete based on the statistical performance of those players in actual games. Sometimes money can be wagered and won, depending on the success of the fantasy team. During a survey in May 2021, only *** percent of U.S. respondents aged 65 and over stated that they played fantasy sports. Comparatively, over ** percent respondents between the ages of ** and ** said that they participated in fantasy sports.

Sports Data Low-Latency Feed Market Outlook

According to our latest research, the market size of the global Sports Data Low-Latency Feed Market reached USD 1.47 billion in 2024. Registering robust momentum, the sector is expected to grow at a CAGR of 16.8% during the forecast period, reaching a projected value of USD 4.38 billion by 2033. The primary growth driver is the surging demand for real-time analytics and instant data delivery across sports betting, broadcasting, and team performance analysis, as organizations and platforms compete to deliver the fastest, most accurate, and engaging experiences to their audiences and stakeholders.

A significant growth factor for the Sports Data Low-Latency Feed Market is the exponential rise in digital sports consumption and interactive fan engagement. As live sports streaming and digital platforms proliferate, fans expect instant access to real-time statistics, scores, and play-by-play data. This demand is particularly pronounced in the realm of sports betting and fantasy sports, where split-second data delivery can impact betting outcomes and fantasy league scores. The integration of ultra-low-latency data feeds enables platforms to offer dynamic odds, live in-play betting, and real-time fantasy updates, creating a seamless and immersive user experience. Additionally, the growing adoption of 5G networks and edge computing technologies is further enhancing the speed and reliability of data transmission, thereby fueling market expansion.

Another pivotal growth driver is the increasing integration of advanced analytics and artificial intelligence in sports team performance analysis. Professional teams and coaches are leveraging low-latency feeds to access granular, real-time data on player movements, biometrics, and in-game events. This data-driven approach allows for immediate tactical adjustments, injury prevention, and optimized training regimens, giving teams a competitive edge. The proliferation of wearable sensors and IoT devices in professional sports is generating vast volumes of actionable data, necessitating robust low-latency infrastructure to process and deliver insights instantaneously. This trend is not limited to elite leagues; even amateur and semi-professional teams are adopting these solutions to enhance performance and scouting, broadening the market’s reach.

The evolving regulatory landscape and the expansion of legalized sports betting across various jurisdictions are also propelling market growth. Governments and regulatory bodies are increasingly recognizing the economic benefits of regulated sports betting, leading to broader market access and heightened competition among betting operators. This has intensified the need for reliable, ultra-fast data feeds to ensure transparency, integrity, and fairness in betting activities. Furthermore, partnerships between sports leagues, data providers, and betting companies are becoming more prevalent, fostering innovation and the development of proprietary low-latency solutions tailored to specific sports and markets. The convergence of these factors is creating a fertile environment for sustained growth in the Sports Data Low-Latency Feed Market.

From a regional perspective, North America and Europe currently dominate the market, driven by mature sports ecosystems, high digital penetration, and early adoption of low-latency technologies. However, Asia Pacific is emerging as a high-growth region, fueled by the rapid expansion of digital infrastructure, rising sports viewership, and the legalization of sports betting in key markets. Latin America and the Middle East & Africa are also witnessing increased investment in sports technology, albeit from a smaller base, as sports organizations and broadcasters seek to enhance fan engagement and operational efficiency. The global outlook remains highly positive, with all regions poised to benefit from ongoing technological advancements and evolving consumer preferences.

Component Analysis

The Component&l