Rebound: Centralised Sports Data System

Rebound: Centralised Sports Data System

1st Dr. R Siva

Department of Computational Intelligence School of Computing, College of Engineering &

Technology SRM Institute of Science and Technology Kattankulathur-603203, India

sivar@srmist.edu.in

3rd Anshita Srivastava

Department of Computational Intelligence

School of Computing, College of Engineering & Technology SRM Institute of Science and Technology

Kattankulathur-603203, India as1840@srmist.edu.in

AbstractSystematic performance analysis in sports requires structured and accessible performance data. However, amateur athletes are not offered suitable means of efciently recording their game statistics. This means that their performance is not well documented. The study seeks to create a centralized game logging system that is effective in analyzing performance data. The system is intended to offer a unied platform that can be used in documenting game events, recording statistics, and retrieving analysis based on aggregated data. The system is based on a mobile platform that ensures performance tracking is consistent. The studys ndings highlight the need for centralized game log- ging in performance documentation and analysis. By integrating a mobile interface with a cloud-based data infrastructure, the platform supports consistent performance tracking and improved accessibility of sports data. The results demonstrate tcentralisedi- zed game logging can enhance performance documentation and provide meaningful analytical insights for athletes and coaches.

Keywords Sports analytics; athlete performance tracking; game logging; sports data management; athlete performance analysis

1. Introduction

   Data-driven analysis plays a critical role in modern sports performance evaluation. Professional sports organizations rely on analytical platforms to monitor athlete performance, eval- uate strategies, and support long-term player development. These systems use structured datasets and analytical tools to generate insights for training optimization and match preparation. However, access to such advanced performance tracking technologies remains largely limited to elite sports environments.

   Athletes participating in amateur or semi-professional sports often lack accessible tools to systematically document their sporting activities. Match records, player statistics, and game outcomes are frequently maintained informally or remain undocumented. The absence of structured performance records limits the ability of athletes and coaches to analyze trends, monitor improvement, and maintain a comprehensive history of athletic participation.

   2nd Akshita Sharma

   Department of Computational Intelligence School of Computing, College of Engineering &

   Technology SRM Institute of Science and Technology Kattankulathur-603203, India

   as0568@srmist.edu.in

   1. Background and Motivation

      Recent digital platforms demonstrate the potential of cen- tralized data systems to support structured sports data man- agement. By allowing athletes and coaches to record match statistics, player contributions, and game outcomes in a unied system, fragmented records can be transformed into organized datasets suitable for analysis. Centralized game logging en- ables athletes to maintain detailed histories of matches, teams, and statistical contributions.

      Analytical tools integrated into such platforms can further generate visual insights from recorded data. Metrics such as average points, rebounds, and assists can be presented through graphs and statistical summaries, enabling athletes and coaches to evaluate performance trends and identify areas for improvement.

   2. Problem Statement

      Despite the increasing importance of sports analytics, ath- letes outside professional ecosystems face several challenges:

      • Lack of centralized platforms for recording game statis- tics

      • Limited access to tools for evaluating athlete and team performance

      • Absence of structured digital portfolios documenting ath- letic progress

        Existing sports analytics platforms primarily target profes- sional leagues or organized teams, leaving amateur athletes with limited options for systematic performance documenta- tion.

   3. Research Gap

      Current sports performance systems typically address iso- lated aspects of athlete management, such as match statistics recording or social interaction features. Few platforms inte- grate structured game logging, performance analytics, athlete portfolio generation, and team-level analysis within a single

      accessible system. This limitation highlights the need for a unied platform capable of organizing and analyzing sports performance data.

   4. Proposed Approach

      To address these limitations, this work presents Athlinix, a centralized sports performance tracking and analytics platform designed for athletes and coaches. The system enables struc- tured recording of game events, player statistics, and match outcomes while generating analytical insights from collected data. By integrating game logging, performance visualization, team analytics, and athlete prole management within a unied environment, Athlinix supports consistent performance track- ing and documentation.

   5. Contributions

      The primary contributions of this work are:

      • Development of a centralized platform for recording games and player statistics

      • Integration of analytical tools for athlete and team per- formance evaluation

      • Support for digital athlete portfolios documenting sport- ing activities

      • Unied analysis of both individual and team performance metrics

2. Related Work

   The increasing use of data analytics in sports has led to the development of technologies that capture and analyze athlete performance. Professional sports organizations rely on analyti- cal systems that utilize structured datasets, statistical modeling, and player tracking technologies to evaluate performance and support strategic decision-making. These approaches highlight the importance of structured performance data in improving training outcomes and competitive strategies.

   Several commercial platforms support sports performance tracking. Applications such as Strava focus on endurance sports by allowing users to record activities, monitor tness metrics, and analyze performance trends. Similarly, wearable devices and mobile tness trackers monitor physiological parameters such as heart rate, distance, and training intensity. While these platforms are effective for individual tness mon- itoring, they provide limited support for structured recording of game events in team sports.

   Other platforms such as Hudl and GameChanger offer tools for match statistics recording and gameplay analysis. Hudl focuses primarily on video analysis for tactical evaluation, while GameChanger provides scorekeeping and basic statis- tical tracking for organized teams. However, these platforms are generally designed for structured leagues and emphasize team management or video analysis rather than long-term performance tracking for individual athletes.

   Despite these developments, accessible systems that enable athletes to record and analyze structured game statistics across multiple matches remain limited. The system proposed in this

   study addressesthis gap by introducing a centralized game log- ging platform that integrates statistical tracking, performance analytics, and athlete portfolio generation within a unied framework.

3. System Architecture

   The proposed platform enables athletes and coaches to record match information and player statistics through a mo- bile application. Users can create teams, log games, and access analytical summaries derived from stored performance data. The backend maintains a centralized repository containing athlete proles, team information, game records, and statistical metrics.

   The architecture ensures that performance data entered through the mobile interface is stored in a centralized database and processed to generate analytical insights.

   1. User Interface Layer

      The user interface layer provides access to the system through a mobile application. Athletes and coaches can create proles, record match information, log player statistics, and view analytical dashboards. The interface supports features such as game logging, team management, performance visu- alization, and athlete prole management.

   2. Application Logic Layer

      The application logic layer manages core system function- ality. It processes user inputs, validates data, and coordinates interactions between the mobile interface and backend ser- vices. Key operations include creating game records, updating player statistics, and retrieving historical performance data for analysis.

   3. Data Management Layer

      The data management layer stores information related to athletes, teams, games, and player statistics in a centralized cloud database. Entities include user proles, teams, game logs, and player performance records. These structured rela- tionships allow the system to track athlete performance across multiple matches and support efcient retrieval of historical data.

   4. Analytics and Visualization Module

      The analytics module converts recorded game statistics into performance insights for athletes and teams. Statistical com- putations are applied to structured game logs to generate key performance indicators (KPIs), which are visualized through dashboards and graphical summaries.

      1. Athlete Performance Metrics: Athlete-level analytics evaluate performance trends across multiple games. A player impact score is calculated to represent overall contribution in a match:

         ImpactScore = Points+Rebounds+Assists+StealsFouls

         (1)

         This metric allows the system to identify standout perfor- mances and analyze long-term player development.

      2. Team Performance Metrics: Team-level analytics evalu- ate collective performance using scoring statistics and match outcomes. Performance consistency is measured using the standard deviation of point differentials across games:

   r1 1 Ln

   = t n

   i=1

   (Diffi )2 (2)

   A team stability score is derived from this variation:

   Stability = max(0, min(100, 100 3)) (3)

   These metrics allow the system to evaluate team consistency and performance trends across multiple matches.

4. Database Design

   The system uses a relational database architecture to manage structured sports data related to athletes, teams, games, and player performance statistics. The schema follows a normal- ized model to ensure data integrity, maintain clear entity relationships, and support efcient querying for performance analytics.

   Fig. 1. Relational Database Schema for the Proposed Sports Data Manage- ment System

   1. Core Entities

      The database consists of several primary entities including Users, Athlete Proles, Coach Proles, Teams, Team Member- ships, Games, and Player Game Statistics.

      The Users table stores core identity information such as username, email, and role. Athlete and coach proles extend the user entity with role-specic attributes such as playing position and experience. The Teams entity represents sports teams, while Team Memberships models the many-to-many relationship between users and teams. The Games entity stores match-level information including participating teams and match results, and Player Game Statistics records individual athlete performance for each game.

      Fig. 2. High-level entity relationship diagram of the Rebound database architecture

   2. Entity Relationships

      The database structure supports performance tracking across multiple games. Users may have either an athlete or coach prole depending on their role. Users and teams are connected through the teammemberships table, while each game links two teams and multiple player statistics records. This structure enables the system to maintain match histories and track athlete performance over time.

   3. Analytical Data Support

   To support performance analysis, the system utilizes database views and materialized views that aggregate player and team statistics. These structures enable efcient retrieval of metrics for dashboards and analytical queries. Foreign key constraints and indexing ensure referential integrity, prevent duplicate records, and maintain consistency across game logs and player statistics.

5. Results and Analysis

The proposed centralized game logging system was eval- uated by recording and analyzing basketball game statistics within the platform. The obtained data was applied to deter- mine how the system could keep the structured records of the performance, as well as produce analytical information based on the acquired game logs.

1. Structured Game Documentation

   The use of centralized game logs helped in the systematic storage of match details such as teams involved in the matches, match result, and the performance of individual players. Each recorded game generated a structured dataset linking athletes, teams, and statistical contributions within a single match record. This structure allowed the system to maintain a complete match history for athletes across multiple games.

   The central repository of the game logs helped to improve consistency of the performance records as compared to in- formal forms of tracking the performance and ensured that the statistical data were arranged into a coherent and easily accessible form.

2. Athlete Performance Analysis

   Using the recorded player statistics, the system generated analytical metrics that summarized individual athlete perfor- mance over time. Key performance indicators such as average points per game, rebounds, assists, and shooting perfor- mance were computed from aggregated game statistics.

   Fig. 3. Athlete Performance Analysis System

   These metrics were visualized through analytical dash- boards that displayed performance trends across multiple matches. The graphical representation of statistical data al- lowed users to identify patterns such as improvements in scor- ing efciency or consistency in specic performance metrics.

3. Team-Level Insights

   Fig. 4. Team-Level Analysis in Sports Analytics

   In addition to individual analysis, the system aggregated player statistics to generate team-level insights. The analysis

   enabled the identication of top-performing players within teams, most valuable players in specic matches, and stand- out individual game performances. These insights provided additional context to individual performance metrics and con- tributed to a broader understanding of team dynamics.

4. System Effectiveness

The results demonstrate that centralized game logging en- ables efcient organization of performance data and supports analytical evaluation of athlete contributions. By maintaining structured datasets and generating automated performance metrics, the system simplies the process of tracking athlete development across multiple games.

Overall, the evaluation indicates that centralized sports data management can signicantly improve performance documen- tation and enable meaningful analysis for athletes and coaches operating in amateur sports environments.

References

1. A. Ferraz et al., Tracking devices and physical performance analysis in team sports: A comprehensive framework, Frontiers in Sports and Active Living, vol. 5, 2023.

2. H. R. Thornton, J. A. Delaney, G. M. Duthie, and B. J. Dascombe, Developing athlete monitoring systems in team sports: Data anal- ysis and visualization, International Journal of Sports Physiology and Performance, vol. 14, no. 2, pp. 230240, 2019. :contentRefer- ence[oaicite:1]index=1

3. A. Aydn, Development of a low-cost team performance tracking system for sports analytics, Journal of Sports Engineering, 2025.

   :contentReference[oaicite:2]index=2

4. X. Tang, B. Long, and L. Zhou, Real-time monitoring and analysis of track and eld athletes based on edge computing, IEEE Access, 2024.

   :contentReference[oaicite:3]index=3

5. V. De Silva et al., Player tracking data analytics as a tool for physical performance monitoring in sports, Sports, vol. 6, no. 4, pp. 130145, 2018. :contentReference[oaicite:4]index=4

6. Y. Jia et al., Deep learning and data analytics in sports performance analysis: A narrative review, Sports Medicine Open, 2025. :contentRe- ference[oaicite:5]index=5

7. Player tracking data in sports, Annual Review of Statistics and Its Ap- plication, vol. 10, pp. 124, 2023. :contentReference[oaicite:6]index=6

8. J. L. Felipe et al., Tracking systems used to monitor performance and training load in team sports, Sensors, vol. 21, no. 24, 2021.

   :contentReference[oaicite:7]index=7

9. Q. Jianjun et al., Predictive athlete performance modeling with machine learning and biometric data, Scientic Reports, 2025. :contentRefer- ence[oaicite:8]index=8

10. X. Tang et al., Real-time monitoring and analysis of track and eld athletes using edge computing, IEEE Internet of Things Journal, 2024.

11. Nacsport video analysis software, Sports performance analysis plat- form, 2023. :contentReference[oaicite:9]index=9