INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue X, October 2025
www.ijltemas.in Page 162
Fit Track: A Gym Member Monitoring System with Predictive
Analytics for Almo Fitness Gym
Roberto Acepcion Jr, Jerie Vale P. Bautista, Rizza Ann Espartinez, Frencis Windell Mancera, Allan Jay Magdael,
Shannen C. Sabado
Arellano University, Pasig Campus
DOI: https://doi.org/10.51583/IJLTEMAS.2025.1410000022
Abstract: A Web-Based Gym Member Monitoring System Using Predictive Analytics and Decision Tree Algorithm focuses on
enhancing gym operations and member management through data-driven automation. The system integrates QR code attendance
tracking, automated payment processing, and predictive analytics to improve efficiency, accuracy, and decision-making at Almo
Fitness Gym in Taguig City. The Linear Regression algorithm in the Almo Fitness Gym system can predict future attendance trends
and revenue based on members’ historical usage patterns. Logistic Regression helps classify members as active or at risk of
cancellation by analyzing their visit frequency and payment behavior. Meanwhile, Random Forest and K-Means Clustering enhance
predictive analytics by improving the accuracy of retention forecasts and grouping members into segments for targeted fitness
programs and personalized promotions. The platform’s web-based interface allows both administrators and members to access real-
time information on attendance, payments, and progress tracking. The development process followed the Agile methodology,
ensuring flexibility, user feedback integration, and iterative improvements across system modules. Evaluation was conducted using
ISO 25010 software quality standards, focusing on functionality, reliability, usability, efficiency, and security. Results from 50
respondents comprising 30 gym users and 20 IT experts showed that the system performed excellently in reliability, efficiency, and
security, confirming its effectiveness and user-friendliness. Users found the interface intuitive and responsive, while experts
validated its compliance with standard software design principles. Findings demonstrated that predictive analytics and the Decision
Tree algorithm are effective in optimizing gym operations, supporting data-informed decisions, and personalizing fitness
management. Overall, FitTrack serves as both a technological and operational solution that transforms manual gym processes into
an intelligent, automated system. The study recommends further development through mobile integration, offline functionality, and
enhanced security measures to ensure scalability, accessibility, and long-term system sustainability.
Keywords: FitTrack, Predictive Analytics, Decision Tree Algorithm, Gym Member Monitoring, QR Code Attendance, ISO 25010,
Agile Methodology, Web-Based System
I. Introduction
The growing demand for technology-driven fitness management systems has transformed how gyms handle operations and improve
member engagement. Fitness centers today face challenges in monitoring attendance, managing payments, and understanding
member activity patterns. Traditional manual systems often result in delays, errors, and inefficiencies in handling gym data. To
overcome these issues, organizations are now adopting intelligent systems that combine automation and data analytics. Gym
monitoring systems integrated with predictive analytics provide a structured way to turn raw data into useful insights that enhance
operational performance and member satisfaction.
The Gym Member Monitoring System with Predictive Analytics for Almo Fitness Gym integrates multiple algorithms to improve
data-driven management and member retention. Linear Regression is utilized to forecast gym attendance, membership growth, and
revenue trends based on historical usage data, enabling the management to plan staffing and facility resources effectively. Likewise,
Logistic Regression classifies members according to their likelihood of renewal or dropout by analyzing variables such as
attendance frequency, duration of membership, and payment consistency, allowing the gym to proactively address potential
cancellations (Kaur & Kumari, 2022; Zhang et al., 2021; Patel & Sharma, 2020; Singh et al., 2022).
Random Forest enhances predictive accuracy by combining multiple decision trees to identify key factors influencing member
satisfaction and engagement. The K-Means Clustering algorithm segments members into groups—such as highly active, moderately
active, and inactive—to help personalize fitness programs and promotional offers (Ahmed et al., 2023; Lee & Park, 2021; Rivera
& Gomez, 2022; Thompson & Li, 2023). These algorithms collectively support Almo Fitness Gym in implementing a smart
monitoring system that enhances service quality, operational efficiency, and customer loyalty. Through predictive analytics, the
system transforms raw data into actionable insights that foster continuous improvement and sustainable growth.
The proposed system, FitTrack: A Web-Based Gym Member Monitoring System Using Predictive Analytics, aims to modernize
the operations of Almo Fitness Gym by automating attendance through QR codes, tracking payments, and analyzing data for
performance prediction. The system’s design follows the ISO 25010 software quality model to ensure functionality, usability, and
reliability. By adopting an agile methodology, the development process promotes flexibility, continuous improvement, and user-
centered design.
Through predictive analytics and automation, the FitTrack system helps gym administrators make informed decisions, improve
service quality, and anticipate member needs. This integration not only streamlines gym operations but also strengthens member
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue X, October 2025
www.ijltemas.in Page 163
relationships and supports long-term efficiency. Predictive analytics thus serves not only as a technical tool but also as a strategic
resource for achieving smart fitness management and organizational growth.
Scope
This study centers on the design and development of FitTrack: A Gym Member Monitoring System, a web-based application
developed to streamline gym operations and improve the overall experience of members at Almo Fitness Gym in Taguig City. The
system provides a centralized and efficient platform for managing essential gym activities, including user management, membership
registration, payment transactions, attendance tracking, progress monitoring, equipment management, posting of announcements,
gathering of feedback, and generation of analytical reports.
The key features integrated into the system include:
QR Code-Based Attendance Tracking – automatically generates a unique QR code for each member to log attendance
efficiently. (Linear Regression algorithm)
Online Payment Module – enables members to submit proof of payment online, which the admin can review and approve
for accuracy.
Progress Tracking Feature – records and monitors workout sessions, body measurements, and individual fitness goals.
(Random Forest algorithm)
Equipment Management Function – allows administrators to update and track the status and availability of gym equipment.
Announcement and Feedback Feature – acts as a communication platform between the gym and its members for sharing
updates and collecting feedback.
Limitation
This study only focuses on creating a web-based system and does not include a mobile app or physical security features such as
RFID or biometric access. The QR code scanning can only be used through a web browser.
The system is made only for Almo Fitness Gym and is not meant to be used in other gym outlets. Its accuracy and performance
depend on the correct data entered by the gym staff and having a stable internet connection for it to work properly.
Theoretical Framework
The Gym Member Monitoring System with Predictive Analytics integrates several machine learning algorithms to improve data-
driven decision-making and member management. The Linear Regression algorithm functions to forecast trends such as attendance
rates, revenue growth, or membership renewals based on historical data, helping the gym anticipate future demands. Meanwhile,
Logistic Regression classifies members according to their likelihood of remaining active or discontinuing their membership by
analyzing behavioral and transactional patterns. Together, these regression models enable the system to provide accurate predictions
that support operational planning and member retention strategies.
In addition, the Random Forest algorithm enhances prediction accuracy by combining multiple decision trees to identify key factors
influencing member satisfaction, progress, and engagement. The K-Means Clustering algorithm groups gym members with similar
fitness behaviors or progress levels, allowing trainers to design targeted workout plans and personalized support. These algorithms
collectively transform raw gym data into actionable insights, promoting a more efficient and responsive management system.
Through this integration, the system achieves its goal of providing intelligent monitoring, predictive analysis, and improved fitness
outcomes for both members and management.
Significance of The Study
This system offers a digital approach to streamline operations such as attendance tracking, membership management, and payment
recording. This is important to the following group of people:
Gym Staff – For employees, the platform provides an easier and faster way to manage member details, post
announcements, and track daily attendance. It lessens repetitive tasks, allowing staff to focus on customer assistance and
service improvement.
Gym Members – Users can conveniently access their attendance records, review payment history, and get instant updates
about schedules and announcements. This transparency promotes better engagement, satisfaction, and loyalty among
members.
Future Researchers and Developers – The study serves as a useful reference for those planning to create or improve web-
based fitness management systems. It demonstrates how integrating algorithms for analytics and decision-making can
enhance both system performance and user experience.
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue X, October 2025
www.ijltemas.in Page 164
II. Review of Related Literature
Zhao, Wang, and Zhu (2023) developed a gym management system using B/S architecture with JSP and MySQL for real-time
booking and analytics, while Sharma, Abhishek, and Esha (2022) created the MyGym website using PHP and MySQL to manage
registration and workout plans securely. Kim and Park (2021) introduced a cloud-based fitness system with AI feedback, and Zhang,
Li, and Wu (2023) applied decision tree algorithms for personalized workouts. Other studies, such as those by Suryawanshi et al.
(2024) and Hadawale et al. (2025), emphasized automation and secure data handling to improve efficiency.
Local research also supports digital innovation in gyms. Olofernes et al. (2021, 2022) developed systems for Groovy Fitness Gym
to manage registration and attendance, while Villanueva, Sevilla, and Verecio (2025) created a QR code-based system for Olympic
Fitness Gym. The E-SIMS study (2018) automated sales and attendance tracking for better accuracy. Overall, these studies show
that web-based systems enhance gym operations, inspiring the FitTrack system to combine automation, predictive analytics, and
user-focused design for improved management and member satisfaction.
III. Methodology of The Study
The study “A Gym Member Monitoring System with Predictive Analytics” is a Developmental (Applied) Research type that focuses
on designing and creating a technological solution to improve gym operations and member management. It applies predictive
analytics and machine learning algorithms such as Linear Regression, Logistic Regression, Random Forest, and K-Means
Clustering to forecast trends and categorize member behavior. This research aims to enhance decision-making and service efficiency
through data-driven insights.
Data Gathering and System Evaluation
Before system creation, data were gathered through surveys, interviews, and observation of gym operations to identify problems in
tracking attendance, monitoring member progress, and managing renewals. After development, the system was evaluated using the
ISO 25010 software quality model, focusing on Accuracy, Reliability, Efficiency, Security, and Portability to measure its
performance and usability. Respondents, including gym staff and members, rated each criterion using a 5-point Likert scale: 5 –
Strongly Agree, 4 – Agree, 3 – Neutral, 2 – Disagree, and 1 – Strongly Disagree. The collected data were interpreted through
weighted mean analysis to determine the overall system effectiveness and user
Figure 2: SDLC Agile Model
The FitTrack system follows the Agile Model of the System Development Life Cycle (SDLC), which emphasizes flexibility,
collaboration, and continuous improvement. This model is chosen because it allows the team to build the system in small,
manageable parts (called sprints), ensuring that feedback from users and staff is regularly applied before moving to the next phase.
The database design of the FitTrack system is created to store and manage gym-related data efficiently and securely. It includes
both the logical and physical structure of the database, supporting core features such as member registration, attendance tracking,
payment processing, and reporting.
The database maintains proper relationships between tables to ensure data consistency and accuracy across all system functions.
Shown below is an illustration of the context diagram of the FitTrack System.
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue X, October 2025
www.ijltemas.in Page 165
Figure 3: Context Diagram of the FitTrack System
Figure 3 shows how the main users members, admins, payment gateways, and notification services interact with the
system.
Members use the system to register, log in, record attendance, make payments, and receive updates or reminders.
Admin oversees member management, handles reports, and monitors gym operations.
Payment Gateway securely processes transactions and sends back confirmation details.
Notification Service delivers important alerts and reminders to users.
This interaction ensures smooth communication, accurate data processing, and a more efficient workflow for Almo Fitness Gym.
Respondents of The Study
The respondents of the study are divided into two groups: (a) user respondents and (b) technical experts. A total of fifty (50)
participants are involved, consisting of thirty (30) active members, staff, and trainers from Almo Fitness Gym and twenty (20)
technical experts with backgrounds in information technology and software development. The user respondents are chosen through
purposive sampling since they directly interact with gym operations such as attendance, membership management, and payments.
They evaluated the system in terms of usability, accessibility, and satisfaction. Meanwhile, the technical experts assessed the
system’s functionality, reliability, and compliance with ISO 25010 software quality standards.
Development and Evaluation Procedure
The development of “FitTrack: A Gym Member Monitoring System” is guided by the Agile methodology, allowing the system to
evolve through continuous feedback and testing. The researchers used several programming languages and development tools to
ensure that the system is functional, user-friendly, and efficient. Each tool played an important role in building and testing both the
frontend and backend components.
The main development tools include:
HTML5: Structured the system’s web pages and interface layouts.
CSS (Tailwind CSS): Designed a responsive, modern, and user-friendly interface for both administrators and members.
JavaScript: Added interactivity, enabling form validation, dynamic content, and smooth navigation.
PHP: Served as the main backend language responsible for handling logic, user authentication, and database interaction.
MySQL: Functioned as the database system for storing user records, attendance logs, and payment transactions.
phpqrcode Library: Generated unique QR codes for each member to support real-time attendance tracking.
Font Awesome: Enhanced the visual presentation by adding icons for menus, buttons, and status indicators.
XAMPP: Provided the local testing environment integrating Apache, MySQL, and PHP.
Visual Studio Code: Used as the main programming editor for writing and managing code.
The evaluation procedure followed a structured approach to determine the system’s functionality, usability, and reliability. The
assessment is based on the ISO 25010 software quality standard, which evaluates the following aspects:
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue X, October 2025
www.ijltemas.in Page 166
1. Accuracy: Verifies that the system records and processes data correctly.
2. Reliability: Ensures consistent performance and data stability.
3. Efficiency: Measures how quickly and effectively the system performs tasks.
4. Security: Examines how well user data and transactions are protected.
5. Portability: Determines compatibility across multiple devices and browsers.
Data Analysis Plan
The evaluation of the system is guided by the ISO/IEC 25010 Software Quality Model. This model is chosen because it aligns with
the objectives of FitTrack in ensuring functionality, security, and usability for both gym administrators and members.
To interpret the responses gathered from the evaluation forms, the researchers utilized appropriate statistical tools that helped
analyze and validate the system’s performance. These methods provided a clear and structured understanding of the overall user
perception of the system’s effectiveness.
Weighted Mean: This tool is used to determine the overall level of agreement among respondents for each ISO 25010
criterion. It allowed the researchers to identify how strongly users and technical experts agreed on the quality aspects of
the system.
Frequency Percentage: This statistical tool presented the distribution of responses in percentage form, providing a visual
understanding of how often a particular rating was chosen.
A four-point Likert Scale is employed to evaluate respondents’ level of satisfaction with the system’s usability, efficiency, and
reliability. This scale provided a structured way for users to express their perception of system quality.
The scale ranged from 1 to 4, representing Strongly Disagree (1), Disagree (2), Agree (3), and Strongly Agree (4).
Each statement in the evaluation form corresponded to one of the ISO 25010 characteristics, enabling the researchers to
assess each software quality attribute objectively.
Responses are then interpreted statistically to determine the overall level of satisfaction and system acceptability.
This rating approach ensured that the evaluation results of the FitTrack system are presented objectively and could be analyzed to
measure how effectively the system fulfilled its intended functions based on user and technical feedback.
The System
The FitTrack Gym Member Monitoring System is a web-based platform designed to enhance the efficiency of gym management
by integrating key functions such as membership management, attendance tracking, payment processing, and announcements in
one system. It enables members to check in using QR codes and view their membership details, while administrators can easily
organize records, monitor activities, and generate accurate reports. The system also uses a Decision Tree algorithm to predict
attendance trends and member behavior, helping admins make better operational decisions. Developed using PHP, JavaScript,
Tailwind CSS, it incorporates Chart.js for visual reports and Font Awesome for icons. Assessed under the ISO 25010 standards,
the system ensures reliability, security, accuracy, efficiency, and portability.
Figure 4: Member Profile Interface
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue X, October 2025
www.ijltemas.in Page 167
This interface shows the Member Profile Dashboard, where members can view and manage their personal and fitness information.
It includes their profile picture, attendance QR code, demographics, emergency contact, and membership details. It also displays
fitness analytics, goals, and personalized recommendations to help track progress and improve engagement.
Figure 5: Admin Members Interface
This interface shows the Members Dashboard in Admin page, where admins can track and manage all gym members. It displays
total members, active members, check-ins, and membership status. The Member List provides quick access to each member’s
details, activity, and actions to view or delete records.
Figure 6: Admin Member Details Interface
This interface shows the Member Details, where admins can view a member’s personal information, membership type and status,
payment history, and attendance records. It provides a quick overview of the member’s activity and account status for easy
monitoring.
Figure 7: Member’s attendance Interface
This interface shows the member’s attendance dashboard, where they can track their visits, punctuality, and progress. It displays
total visits, on-time rate, and recent activities, along with detailed attendance records. Members can also filter records by date to
easily monitor their fitness attendance history.
Assessment: Summary of Respondents on The System
The table presents the distribution of respondents involved in the system evaluation, categorized into user and technical groups.
The assessment is conducted following the ISO 25010 Software Quality Model to ensure a fair and reliable evaluation of the
system’s usability and technical performance. This classification provides a clear overview of the participants who contributed
feedback based on their experience and expertise.
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue X, October 2025
www.ijltemas.in Page 168
Table 1: Distribution of the Respondents
Table 1 presents the total number and percentage of participants who took part in evaluating the system. Among the 50 respondents,
30 individuals or 60% are users, and 20 persons or 40% are technical evaluators. This indicates that the majority of the feedback is
gathered from users, while the technical group contributed expert assessments to ensure the system’s functionality and performance
are properly reviewed.
Table 2. Summary of Respondents’ Assessment on the FitTrack System Based on ISO 25010 Standards
Table 2 presents the overall summary and comparison of evaluations from both user and technical respondents based on the ISO
25010 criteria. The user group obtained an overall average mean of 3.62, interpreted as Strongly Agree, while the technical group
achieved an average mean of 3.85, also interpreted as Strongly Agree. Among all the criteria, Portability received the highest rating
from users with a weighted mean of 3.67, whereas Accuracy received the top score from technical respondents with a weighted
mean of 3.93, showing strong confidence in the system’s accessibility and stable performance. Meanwhile, Efficiency earned the
lowest rating from users with a weighted mean of 3.54, indicating slight areas for enhancement in system speed and responsiveness.
In general, both groups agreed that the system satisfies the ISO 25010 standards, reflecting overall confidence in its functionality,
reliability, and ease of use.
Ethical Considerations
The development and use of the Gym Management System prioritizes the privacy, security, and accuracy of member data. All
personal and financial information are handled responsibly, following data protection laws and ethical standards. Developers and
staff ensure that the system is used fairly and transparently, avoiding unauthorized access, misuse of data, or discrimination among
members. Additionally, regular maintenance and updates are done to uphold system integrity, reliability, and trustworthiness,
ensuring that the technology used benefits both gym staff and members ethically and responsibly.
IV. Summary
The Gym Management System is a web-based tool that helps gym staff efficiently manage member attendance, payments, and daily
operations. It features a user-friendly interface accessible on various devices. Based on ISO 25010 standards, the system scored
highly in Reliability, Efficiency, and Security, with minor improvements needed in Accuracy. Overall, it is a reliable, secure, and
easy-to-use system that streamlines gym management.
V. Conclusion
The Gym Management System is a web-based platform that helps staff manage attendance, payments, and daily tasks efficiently.
It is user-friendly, accessible on multiple devices, and rated highly in Reliability, Efficiency, and Security under ISO 25010
standards, with slight improvements needed in Accuracy. Overall, it’s a secure, reliable, and easy-to-use system that simplifies gym
operations.
VI. Recommendation
Future researchers and developers are encouraged to improve and expand the Gym Management System to make it more useful for
gym operations. This could include creating a mobile app for easier access and adding security features like RFID or fingerprint
scanners to improve attendance tracking.
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue X, October 2025
www.ijltemas.in Page 169
To address the limitation of browser-only QR code scanning, future versions could allow the system to work offline or temporarily
store data when the internet is unavailable. Adding automated checks can help ensure attendance and payment records are accurate.
Regular updates, maintenance, and technical support would keep the system running smoothly, and analytics features could help
gym staff track member attendance, payments, and engagement for better management.
References
1. Hadawale, A., Pawar, P., Bhajnawale, P., & Patange, A. (2025). Web-based gym management platforms for improved
user experience and operational productivity. International Journal of Computer Applications, 227(4), 15–22.
2. Kim, J., & Park, S. (2021). Cloud-based fitness tracking system with wearable integration. Journal of Healthcare
Engineering, 2021, Article 8856123. https://doi.org/10.1155/2021/8856123
3. Olofernes, M., Dela Cruz, A., & Santos, R. (2021). Web-based gym management system for Groovy Fitness Gym.
Philippine Journal of Information Systems, 14(2), 45–56.
4. Quinlan, J. R. (1996). Improved use of continuous attributes in C4.5. Journal of Artificial Intelligence Research, 4, 77–90.
https://doi.org/10.1613/jair.279
5. Sharma, P., Abhishek, A., & Esha, R. (2022). Development of MyGym Website: A web-based gym management system.
International Research Journal of Engineering and Technology, 9(6), 1256–1263.
6. Suryawanshi, A., Bokare, N., Bhadre, S., & Lahankar, R. (2024). Web-based gym management system using XAMPP and
MySQL. International Journal of Advanced Research in Computer Science, 15(1), 88–94.
7. Villanueva, K., Sevilla, M., & Verecio, C. (2025). QR-code-based management system for Olympic Fitness Gym. Asia
Pacific Journal of Information Technology, 8(2), 66–75.
8. Zhang, H., Li, Q., & Wu, Y. (2023). Smart fitness tracking system using cloud computing and machine learning. Journal
of Computer Applications in Sport Science, 12(4), 221–235.
9. Zhao, J., Wang, X., & Zhu, L. (2023). Design and implementation of a gym management system based on JSP and MySQL.
International Journal of Information Systems and Technology, 21(3), 55–62.
10. Sobreiro, P. (2021). Predicting fitness centre dropout. PubMed Central (PMC).
https://pmc.ncbi.nlm.nih.gov/articles/PMC8508547/
11. Marqués-Jiménez, D. (2024). A Random Forest clustering to explore the influence of physical fitness level of youth
basketball players on match-related physical performance. SAGE Journals.
https://journals.sagepub.com/doi/abs/10.1177/17543371231200056
12. Van der Zanden, M. (2023). The prediction of membership churn in a large gym club chain (Master’s thesis). Arno
Repository, Tilburg University.https://arno.uvt.nl/show.cgi?fid=172644
13. Niu, Z. (2025). Customer segmentation and management strategy using K-Means clustering for gym customers. ScitePress
https://www.scitepress.org/Papers/2024/132140/132140.pdf