INTELLIGENT OFFICE SPACE MANAGEMENT SYSTEM BASED ON USER BEHAVIOR ANALYSIS

Abstract

The article discusses modern approaches to the use of artificial intelligence for analyzing user behavior in office
space management systems. Particular attention is paid to artificial intelligence methods for predicting patterns of
workplace bookings, analyzing the frequency and preferences of users for specific work areas, as well as automatic
notification of re-booking of the same place. Practical examples of modern solutions on the market, such as Spacewell,
Smartway2 and ti&m Places, are considered, which demonstrate the integration of machine learning algorithms to
optimize the use of office space, increase the efficiency of bookings and reduce conflicts between users. Special attention
is paid to issues of privacy and ethical aspects of data collection, as well as methods for ensuring user confidentiality
when using sensor technologies and systems for monitoring the occupancy of work areas. Approaches to collecting and
processing data on the presence of employees in the office environment are considered, taking into account the
requirements of security and transparency of information use. The paper also describes behavioral models and algorithms
for building user-oriented predictive models, in particular the BehavDT approach, which allows taking into account
historical booking data, time patterns of workplace use, and individual user behavior. The use of such models allows for
recommendations on choosing the optimal workplace, increasing the efficiency of office infrastructure use, and reducing
the overload of individual work areas. Based on the results of theoretical analysis and a formalized model for predicting
office space occupancy, the software architecture of an intelligent workplace reservation management system was
developed. The architectural solution is based on a microservice approach, which provides modularity, horizontal
scalability, and the ability to independently update individual system components without disrupting the functioning of
others. The results of testing and modeling confirm the operability of the proposed architecture and algorithms for
medium-scale office space management systems and identify areas for optimization for scaling to the level of large
organizations.
Keywords: artificial intelligence, office space management, user behavior analysis, workplace reservation
systems, automatic notification, pattern prediction, behavioral models, intelligent systems, space optimization, data
privacy.

References
1. Вербівська Л. В. Штучний інтелект в управлінні підприємством: переваги та виклики. Problems of
Modern Transformations. Series: Economics and Management, (10). 2023. DOI: https://doi.org/10.54929/2786-5738-
2023-10-04-06.
2. Timothy Callemein, Kristof Van Beeck, Toon Goedemé. Anyone here? Smart embedded low-resolution
omnidirectional video sensor to measure room occupancy. Computer Vision and Pattern Recognition. 2020. DOI:
https://doi.org/10.48550/arXiv.2007.04934.
3. Iqbal H. Sarker, Alan Colman, Jun Han, Asif Irshad Khan, Yoosef B. Abushark, Khaled Salah. BehavDT: A
Behavioral Decision Tree Learning to Build User-Centric Context-Aware Predictive Model. Machine Learning. 2019.
DOI: https://doi.org/10.48550/arXiv.2001.00621.
4. Sebastian Smeenk. Smart Offices: The Future of Workspaces in a Digital Economy. EDGE Workspaces. 2024.
URL: https://www.edgeworkspaces.com/smart-offices-the-future-of-workspace.
5. Office Space Reservation System – Workplace. Spacewell. 2025. URL: https://spacewell.com/workplacemanagement-software/office-space-reservation-system.
6. Violeta Motuzienė, Jonas Bielskus, Vilūnė Lapinskienė and Genrika Rynkun. Office building’s occupancy
prediction using extreme learning machine model with different optimization algorithms. Environmental and Climate
Technologies. 2021. Volume 25. Issue 1. Р. 525 - 536. DOI: https://doi.org/10.2478/rtuect-2021-0038.
7. Zhou X., Cao J., Qu S., Chen X., Zhang H. Occupancy prediction using deep learning approaches across
multiple space types: A minimum sensing strategy. Building and Environment. 2022. Volume 226. 109689. DOI:
https://doi.org/10.1016/j.buildenv.2022.109689.
8. Wang W., Chen J., Hong T. Occupancy prediction through machine learning and data fusion of environmental
sensing and Wi‑Fi sensing in buildings. Automation in Construction. 2018. Volume 94. Р. 233-243. DOI:
https://doi.org/10.1016/j.autcon.2018.07.007.
9. Tao Li, Xiangyu Liu, Guannan Li, Xing Wang, Jiangqiaoyu Ma, Chengliang Xu, Qianjun Mao. A systematic
review and comprehensive analysis of building occupancy prediction. Renewable and Sustainable Energy Reviews. 2024.
Volume 193. 114284. DOI: https://doi.org/10.1016/j.rser.2024.114284.
10. The Benefit of AI in Desk Booking. ti&m Places. 2024. URL: https://www.ti8m.com/en/blog/Der-Nutzenvon-KI-bei-der-Arbeitsplatzbuchung-Places.
11. Як сучасний офіс підвищує продуктивність та ефективність команди. AIN.UA. 2025. URL:
https://ain.ua/2025/04/04/yak-suchasniy-ofis-pidvishhuje-produktivnist-komandy-forum-group.
12. Замрій І.В., Собчук А.В., Лаптєв С.О., Лаптєва Т.О., Копитко С.Б. Алгоритм контролю та
прогнозування функціональної стійкості складних інформаційно-технічних систем. Телекомунікаційні та
інформаційні технології, 2022, №1 (74). С. 4-14. DOI: http://doi.org/10.31673/2412-4338.2022.010414.
13. Irfanullah Khan, Ouarda Zedadra, Antonio Guerrieri, Giandomenico Spezzano. Occupancy Prediction in IoTEnabled Smart Buildings: Technologies, Methods, and Future Directions. Sensors, 2024. 24(11), 3276. DOI:
https://doi.org/10.3390/s24113276.
14. Aya Nabil Sayed, Sakib Mahmud, Faycal Bensaali, Muhammad E. H. Chowdhury, Yassine Himeur.
Optimizing energy efficiency through precise occupancy detection: A tailored CNN architecture for smart buildings and
beyond. Neural Computing and Applications, 2025. Volume 37. Р. 16487–16503. DOI: https://doi.org/10.1007/s00521-
025-11348-6.
15. Chamari L., Petrova E., Pauwels P. An End-to-End Implementation of a Service-Oriented Architecture for
Data-Driven Smart Buildings. IEEE Access, vol. 11, pp. 117261-117281, 2023. DOI: https://doi.org/10.1109/ ACCESS.
2023.3325767.
16. Freire G., Paucar H., Estrella Jú. A distributed software architecture based on reactive microservices for the
Smart Building context. LADC '23: Proceedings of the 12th Latin-American Symposium on Dependable and Secure
Computing. 2023. P. 168 – 169. DOI: https://doi.org/10.1145/3615366.3622790.
17. Domenico Santoro, Tiziana Ciano, Massimiliano Ferrara. A comparison between machine and deep learning
models on high stationarity data. Scientific Reports. 2024. 14, Article number: 19409. DOI: https://doi.org/10.1038/
s41598-024-70341-6.