We will create a customized NBA dataset tailored to your specific requirements. Data points may include player statistics, team rankings, game scores, player contracts, and other relevant metrics.

Utilize our NBA datasets for a variety of applications to boost strategic planning and performance analysis. Analyzing these datasets can help organizations understand player performance and market trends within the basketball industry, allowing for more precise team management and marketing strategies. You can choose to access the complete dataset or a customized subset based on your business needs.

Popular use cases include: enhancing player performance analysis, refining team strategies, and optimizing fan engagement efforts.

The sample for this study is composed of NBA players from the 1999–2000 season through the 2015–2016 season. Data on the ethnicities of NBA players was manually collected by searching websites such as Wikipedia, Facebook, Google, and Baidu Encyclopedia; where it was impossible to make this judgment based on player data, players’ pictures published on the Basketball Reference website (http://www.basketball-reference.com) were examined to determine ethnicity (Wallace, 1988). Player salaries were collected from the ESPN website (http://www.espn.com/nba/salaries); player characteristics and technical data come from the ESPN website and the Basketball Reference website. Players who changed teams within a season were eliminated from the sample, as were players who made less than two appearances on the court within a season.

The database contains several datasets and files with NBA statistical data spanning four seasons (2015-2016 to 2018-2019). These datasets were procured from the Basketball Reference database (https://www.basketball-reference.com/), a publicly accessible source of NBA data.

The main file, `dat.cleaned.csv`, includes the Win/Loss records for all thirty NBA teams, along with box scores and advanced statistics. The data captured over the four seasons correspond to about 4,920 regular-season games. A distinguishing feature of this dataset is the repeated measurements per player within a team across the seasons. However, it's important to note that these repeated measurements are not independent, necessitating the use of hierarchical modelling to properly handle the data.

Two sets of additional text files (`per_2017.txt`, `per_2018.txt`, `rpm_2017.txt`, `rpm_2018.txt`) provide specific metrics for player performance. The 'PER' files contain the Athlete Efficiency Rating (PER) for the years 2017 and 2018. The 'RPM' files contain the ESPN-developed score called Real Plus-Minus (RPM) for the same years.

However, potential biases or limitations within the datasets should be acknowledged. For instance, the Basketball Reference website might not include data from some matches or may exclude certain variables, potentially affecting the quality and accuracy of the dataset.

NBA Regular Season Data 1950-2021

This data is obtained from basketball-reference.com using a self-written webcrawler. It contains detailed game data and player specific stats for each game of the respective season.

Content

Data for each season is arranged in two csv-files. The first file season_XXXX_basic.csv contains basic data for each game of the season, such as the date, time, scores and attendance. The second file season_XXXX_detailed.csv contains additional statistics for each player participating in a specific game, such as the minutes played, field goals made and field goals attempted. A lot of data is missing for older seasons, since it wasn't recorded and is not listed on basketball-reference.com.

Inspiration

It would be interesting to see what statistics changed over the course of time when the game evolved and teams focused more on 3PT shots for example.

Analysis of ‘NBA Players’ provided by Analyst-2 (analyst-2.ai), based on source dataset retrieved from https://www.kaggle.com/justinas/nba-players-data on 28 January 2022.

--- Dataset description provided by original source is as follows ---

Update 02-08-2021: The data now includes 2020 season and metrics for 2019 have been updated.

Update 08-03-2020: The data now includes 2017, 2018 and 2019 seasons. Keep in mind that metrics like gp, pts, reb, etc. are not complete for 2019 season, as it is ongoing at the time of upload.

Context

As a life-long fan of basketball I always wanted to combine my enthusiasm for the sport with passion for analytics 🏀📊. So, I utilized the NBA Stats API to pull together this data set. I hope it will prove to be as interesting to work with for you as it has been for me!

Content

The data set contains over two decades of data on each player who has been part of an NBA teams' roster. It captures demographic variables such as age, height, weight and place of birth, biographical details like the team played for, draft year and round. In addition, it has basic box score statistics such as games played, average number of points, rebounds, assists, etc.

The pull initially contained 52 rows of missing data. The gaps have been manually filled using data from Basketball Reference. I am not aware of any other data quality issues.

Analysis Ideas

The data set can be used to explore how age/height/weight tendencies have changed over time due to changes in game philosophy and player development strategies. Also, it could be interesting to see how geographically diverse the NBA is and how oversees talents have influenced it. A longitudinal study on players' career arches can also be performed.

--- Original source retains full ownership of the source dataset ---

Source of the data: Sportsradar API (https://developer.sportradar.com/docs/read/basketball/NBA_v8)

  NBA Play-by-Play Data Extraction and Analysis





  Overview

This project aims to retrieve play-by-play data for NBA matches in the 2023 season using the Sportradar API. The play-by-play data is fetched from the API, saved into JSON files, and then used to extract relevant features for analysis and other applications. The extracted data is saved in Parquet files for easy access… See the full description on the dataset page: https://huggingface.co/datasets/farazjawed/NBA_PLAY_BY_PLAY_DATA_2023.

Context

This dataset was collected to work on NBA games data. I used the nba stats website to create this dataset.

You can find more details about data collection in my GitHub repo here : nba predictor repo.

If you want more informations about this api endpoint feel free to go on the nba_api GitHub repo that documentate each endpoint : link here

Content

You can find 5 datasets :

• games.csv : all games from 2004 season to last update with the date, teams and some details like number of points, etc.
• games_details.csv : details of games dataset, all statistics of players for a given game
• players.csv : players details (name)
• ranking.csv : ranking of NBA given a day (split into west and east on CONFERENCE column
• teams.csv : all teams of NBA

Acknowledgements

I would like to thanks nba stats website which allows all NBA data freely open to everyone and with a great api endpoint.

Inspiration

• Predict NBA games winner

Enjoy it ! Nathan

The NBA SportVU dataset contains player and ball trajectories for 631 games from the 2015-2016 NBA season. The raw tracking data is in the JSON format, and each moment includes information about the identities of the players on the court, the identities of the teams, the period, the game clock, and the shot clock.

Teams in Major League Baseball were estimated at an average franchise value of just over 2.3 billion U.S. dollars in 2023. Meanwhile, the average value of National Football League franchises reached a high of over 5.1 billion U.S. dollars in 2023.

NBA data ranging from 1996 to 2024 contains physical attributes, bio information, (advanced) stats, and positions of players.

No missing values, certain data preprocessing will be needed depending on the task.

Data was gathered from the nba.com and Basketball Reference - starting with the season 1996/97 and up until the latest season 2023/24.

A lot of options for EDA & ML present - analyzing the change of physical attributes by position, how the number of 3-point shots changed throughout years, how the number of foreign players increased; using Machine Learning to predict player's points, rebounds and assists, predicting player's position, player clustering, etc.

The issue with the data was that the data about player height and weight was in Imperial system, so the scatterplot of heights and weights was not looking good (around only 20 distinct values for height and around 150 for weight, which is quite bad for the dataset of 13.000 players). I created a script in which I assign a random height to the player between 2 heights (let's say between 200.66 cm and 203.2 cm, which would be 6-7 and 6-8 in Imperial system), but I did it in a way that 80% of values fall in the range of 5 to 35% increase, which still keeps the integrity of the data (average height of the whole dataset increased for less than 1 cm). I did the same thing for the weight: since difference between 2 pounds is around 0.44 kg, I would assign a random value for weight for each player that is either +/- 0.22 from his original weight. Here I observed a change in the average weight of the whole dataset of around 0.09 kg, which is insignificant.

Unfortunately the NBA doesn't provide the data in cm and kg, and although this is not the perfect approach regarding accuracy, it is still much better than assigning only 20 heights to the dataset of 13.000 players.

Complete record of all basketball players in NBA history with career statistics and biographical information

Analysis of ‘NBA Player Stats (2019-20)’ provided by Analyst-2 (analyst-2.ai), based on source dataset retrieved from https://www.kaggle.com/nicklauskim/nba-per-game-stats-201920 on 28 January 2022.

--- Dataset description provided by original source is as follows ---

Context

The 2019-20 NBA season is now officially over, closing the books on a season that has been truly remarkable in so many ways. As an avid basketball fan, I watched this season very closely and seeing as I haven't yet seen a complete, compiled set of statistics for the 2020 season, I went about creating this dataset!

Content

This dataset contains several files, each pertaining to a different type of statistic (basic, advanced, per 36 mins, etc.) for all players for the 2019-20 NBA regular season. This dataset contains all kinds of basic and advanced stats, from points and rebounds to box plus-minus and VORP.

Inspiration

These stats can be used for a variety of visualization tasks and exploratory data analysis to show trends and oddities in the numbers these players produced this season. Some example questions to ponder:

• Who were the most efficient scorers in the league this season? Where were these players most effective?
• What numbers are the biggest indicators of a player's contributions to his team's success?
• How were certain stats distributed by position? Are there any outliers, such as Nikola Jokić's assist averages at center or Ben Simmon's three-point numbers as an All-NBA point guard?
• Which players are similar to each other?

I look forward to seeing some of your insights! Have fun with it, NBA fans!

--- Original source retains full ownership of the source dataset ---

The National Basketball Association has one of the highest percentages of African American players from the big four professional sports leagues in North America. In 2023, approximately **** percent of NBA players were African American. Meanwhile, ethnically white players constituted a **** percent share of all NBA players that year. After the WNBA and NBA, the National Football League had the largest share of African Americans in a professional sports league in North America. How do other roles in the NBA compare? When it comes to African American representation in the NBA, no other role in the NBA is as well represented by African Americans as players. Meanwhile, on the opposite end of the scale, less than **** percent of team governors in the NBA were African American in 2023. During the 2022/23 season, the role with the second-highest share of African Americans was head coach, with a share of ** percent. That season, the number of African American head coaches in the NBA exceeded the number of white head coaches for the first time. African Americans in the NFL In 2022, the greatest share of players by ethnicity in the NFL were African American, with more than half of all NFL players falling within this group. The representation of African Americans in American Football extended beyond the playing field, with **** percent of NFL assistant coaches being African American in 2022 as well. However, positions such as vice presidents and head coaches were less representative of the African American population, as less than ** percent of the individuals fulfilling these roles in 2022 were African American.

Fantasy sports, particularly the daily variety in which new lineups are selected each day, are a rapidly growing industry. The two largest companies in the daily fantasy business, DraftKings and Fanduel, have been valued as high as $2 billion. This research focuses on the development of a complete system for daily fantasy basketball, including both the prediction of player performance and the construction of a team. First, a Bayesian random effects model is used to predict an aggregate measure of daily NBA player performance. The predictions are then used to construct teams under the constraints of the game, typically related to a fictional salary cap and player positions. Permutation based and K-nearest neighbors approaches are compared in terms of the identification of “successful” teams—those who would be competitive more often than not based on historical data. We demonstrate the efficacy of our system by comparing our predictions to those from a well-known analytics website, and by simulating daily competitions over the course of the 2015–2016 season. Our results show an expected profit of approximately $9,000 on an initial $500 investment using the K-nearest neighbors approach, a 36% increase relative to using the permutation-based approach alone. Supplementary materials for this article are available online.

This paper examines the impact of lagged performance on free agent contracts for players in the National Basketball Association. The main approach of the paper is twofold. The first piece investigates how past performance affects future performance in the two seasons after contract year and compares it to the impact previous performance has on contract terms for free agent players. The second piece investigates the rationality of free agent contracts in their entirety by comparing the impact of lagged performance on total accumulated production and total dollar value paid. The goal is to determine if performance prior to contract year is underweighted in contract decision-making relative to its predictive power of future performance. There is evidence that performance in years prior to contract year is overlooked in contract determination decisions by NBA general managers, and there is mild evidence that performance data two years prior to contract year are underweighted given their predictive power of future performance.

Comprehensive box score statistics and player performance metrics from the Lakers vs Grizzlies game including points, rebounds, assists, field goal percentages, plus-minus ratings, and advanced statistics.

The NBA Market report segments the industry into By Revenue Streams (Broadcasting Rights, Sponsorship and Advertising, Merchandising, Other (Ticket Sales and Digital Media)), By Fans (Local Fans, National Fans, Global Fans), and Geography (North America, Europe, Asia Pacific, South America, Middle East). Get five years of historical data alongside five-year market forecasts.

An average of **** million viewers tuned in to watch NBA regular season games across ABC, ESPN and TNT in the 2024/25 season. This marked a slight decline in the number of viewers from the previous season.

The Basketball NBA market represents a dynamic segment of the global sports industry, characterized by a passionate fanbase, lucrative sponsorship deals, and an ever-expanding digital presence. As one of the premier professional basketball leagues worldwide, the NBA has cultivated a significant market size, boasting

The NBA Draft Combine is an annual showcase for basketball players. It is held in May, shortly before the NBA Draft. Athletes are invited to display their skills, and participants are measured. This data set includes anthropometric, strength, and agility statistics.

Starting from 2000, this data set includes over 1,600 players. All data were sourced from NBA Stats.

Not included are: - shooting stats - scrimmage games stats - medical tests - Draft results

A few players were invited twice. In these cases, only data from the latest draft combine were retained. Players, who participated but were not measured, were excluded as well.