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 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.

cmdbench-nba

CMDBench-NBA is a multimodal NBA datalake that consists of a Neo4j knowledge graph, a PostgreSQL relational database, and a MongoDB document collection. It is originally proposed in the CMDBench paper but has been updated with higher quality data (up to Feburary 2025). Contact: yanlin@megagon.ai

  Deploying the databases

First, clone the repository with git lfs installed.

Make sure git-lfs is installed (https://git-lfs.com)

git lfs install

git clone… See the full description on the dataset page: https://huggingface.co/datasets/megagonlabs/cmdbench-nba.

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

This project analyzes historical NBA data (2012-2024, sourced from Kaggle) using a multi-output Random Forest model (scikit-learn) to predict key player statistics (points, rebounds, etc.). The experiment emphasizes reproducibility and FAIR data practices, producing the trained model, evaluation metrics, visualizations, FAIR4ML metadata, and this DMP as outputs. This work is part of the TU Wien Data Stewardship lecture.

Github: https://github.com/bubaltali/nba-prediction-analysis/

DBRepo: https://test.dbrepo.tuwien.ac.at/database/2e167490-c803-4a9a-a317-6e274c6b3a37/info

TUWRD. https://handle.test.datacite.org/10.70124/ymgzs-z3s43

The data was taken from: https://www.kaggle.com/datasets/shivamkumar121215/nba-stats-dataset-for-last-10-years/data

Dataset

This dataset was created by Jose Jatem

Contents

The standardized regressions results from pooled top scorers data.

Probability of making a hot game conditioned on the outcome of previous games.

Semi- partial correlations between the defensive, offensive and opportunity-adjusted MSEs across games.

The Digital Basic Landscape Model (ATKIS Base DLM) is a digital, object-structured vector dataset. It determines the topographical objects of the real world by location and shape, names and characteristics. Furthermore, object-related material data are linked in such a way that the database can be used in a GIS application. In order to achieve a nationwide content uniformity of the data, the basic DLM is defined by means of an object type catalog derived from the AAA application scheme (ATKIS-OK Basic DLM), which contains regulations on the content and modelling of topographic information for the AdV basic data base and the country solutions. In addition to the objects of the object category groups ‘Siedlung’, ‘Transport’, ‘Vegetation’, ‘Waters’, ‘Administrative territorial units’ and ‘Relief Forms’, the contents also include structures and facilities on settlement areas and for traffic, as well as specific information on the waters. The position accuracy for the main linear objects (road axes, road axes, railway lines and water axes) is ± 3 m. When using a database, the ATKIS data can be submitted either completely or as user-related inventory data update (NBA) according to the customer’s desired time cycles. The data is provided free of charge via automated procedures or by self-collection. When using the data, the license conditions must be observed.

The digital basic landscape model (ATKIS-Basis-DLM) is a digital, object-structured vector database. It determines the topographical objects of the real world by location and shape, by name and properties. Furthermore, object-related factual data is linked in such a way that the database can be used in a GIS application. In order to achieve nationwide uniformity of the content of the data, the basic DLM is created with the help of an object type catalog (ATKIS-OK basic DLM) derived from the AAA application schema, the regulations for the content and for modeling the topographical information for the AdV basic data stock and which contains country solutions. In addition to the features of the feature type groups 'Settlement', 'Traffic', 'Vegetation', 'Water', 'Administrative Area Units' and 'Relief Shapes', the content also includes buildings and facilities on settlement areas and for traffic, as well as special information on water bodies. The positional accuracy for the main linear objects (road axes, lane axes, railway lines and water bodies) is +/- 3m. When using a database, the ATKIS data can either be submitted completely or as a user-related inventory data update (NBA) according to the time cycles desired by the customer. The data is provided free of charge via automated procedures or by self-extraction. When using the data, the license conditions must be observed.

Pearson correlations between different shooting performance measurements among players.

Runs test.

Track the status of more than $200 billion in sports rights deals across eight professional and college sports and 10 platforms. The Information's Sports Rights Database shows who controls the most important streaming deals and when they are up for renegotiation.

See our stories NBA Wants More in Sports Deals: Media and Tech Firms Are Resistant and Amazon in Talks With Disney About ESPN Streaming Partnership

For training purpose the playoff data of before 2023-2024 season has been created

NBA player statistics of the regular season in the 2022-2023