Designing an Intelligent Framework for Real-Time Recommendation Based on Momentary User Behavior Analysis in Online Platforms
Keywords:
real-time recommender systems, momentary user behavior, adaptive personalization, sequential modeling, online platformsAbstract
The objective of this study was to design and empirically evaluate an intelligent real-time recommender framework that leverages momentary user behavior analysis to enhance recommendation relevance, engagement, and system responsiveness in online platforms. This study employed a quantitative, applied research design with a developmental orientation. The population consisted of active users of large-scale online platforms in Tehran, selected based on continuous platform usage and availability of real-time interaction data. Behavioral data were collected through system-level logging mechanisms that captured fine-grained, time-stamped interaction signals, including click behavior, dwell time, navigation patterns, and session dynamics. These data were complemented by contextual indicators related to usage conditions. The proposed framework integrated real-time analytics, sequential behavior modeling, and adaptive learning mechanisms to generate recommendations dynamically during active sessions. Data preprocessing, feature engineering, and model training were conducted to support continuous inference under real-world latency constraints. Inferential analyses indicated that the proposed real-time intelligent framework significantly outperformed rule-based, collaborative filtering, and static machine learning models across key performance indicators. The framework achieved higher click-through rates, longer engagement durations, and greater recommendation acceptance, reflecting improved alignment with users’ immediate preferences. Real-time model adaptation following short-term behavioral changes led to statistically meaningful increases in session depth and reductions in bounce behavior. High short-term preference prediction accuracy was achieved alongside low inference latency, confirming the framework’s effectiveness and operational feasibility in dynamic online environments. The findings demonstrate that incorporating momentary user behavior analysis into an adaptive real-time recommendation framework substantially improves personalization quality and user engagement, supporting the shift toward behavior-aware intelligent recommender systems in modern online platforms.
References
Z. Li, L. Zhang, C. Lei, X. Chen, J. Gao, and J. Gao, "Attention With Long-Term Interval-Based Deep Sequential Learning for Recommendation," Complexity, vol. 2020, pp. 1-13, 2020, doi: 10.1155/2020/6136095.
X. Xia, H. Yin, J. Yu, Q. Wang, L. Cui, and X. Zhang, "Self-Supervised Hypergraph Convolutional Networks for Session-Based Recommendation," Proceedings of the Aaai Conference on Artificial Intelligence, vol. 35, no. 5, pp. 4503-4511, 2021, doi: 10.1609/aaai.v35i5.16578.
P. Nitu, J. Coelho, and P. Madiraju, "Improvising Personalized Travel Recommendation System With Recency Effects," Big Data Mining and Analytics, vol. 4, no. 3, pp. 139-154, 2021, doi: 10.26599/bdma.2020.9020026.
Y. Luo, Q. Liu, and Z. Liu, "STAN: Spatio-Temporal Attention Network for Next Location Recommendation," pp. 2177-2185, 2021, doi: 10.1145/3442381.3449998.
S. Jiang, W. He, L. Cui, Y. Xu, and L. Liu, "Modeling Long- And Short-Term User Preferences via Self-Supervised Learning for Next POI Recommendation," Acm Transactions on Knowledge Discovery From Data, vol. 17, no. 9, pp. 1-20, 2023, doi: 10.1145/3597211.
X. Wang, Y. Liu, X. Zhou, Z. Leng, and X. Wang, "Long- And Short-Term Preference Modeling Based on Multi-Level Attention for Next POI Recommendation," Isprs International Journal of Geo-Information, vol. 11, no. 6, p. 323, 2022, doi: 10.3390/ijgi11060323.
Y. Wang, A. Liu, and F. Jiang, "A Category-Aware Network for Next POI Recommendation With Long- And Short-Term Preferences," 2023, doi: 10.21203/rs.3.rs-3249221/v1.
M. Luo, X. Zhang, J. Li, D. Peipei, and S. Lu, "User Dynamic Preference Construction Method Based on Behavior Sequence," Scientific Programming, vol. 2022, pp. 1-15, 2022, doi: 10.1155/2022/6101045.
Y. Guo, Y. Ling, and H. Chen, "A Neighbor-Guided Memory-Based Neural Network for Session-Aware Recommendation," Ieee Access, vol. 8, pp. 120668-120678, 2020, doi: 10.1109/access.2020.3006360.
J. Guo et al., "Learning Multi-Granularity Consecutive User Intent Unit for Session-Based Recommendation," pp. 343-352, 2022, doi: 10.1145/3488560.3498524.
M. B. Hossain, M. S. Arefin, I. H. Sarker, M. Kowsher, P. K. Dhar, and T. Koshiba, "CARAN: A Context-Aware Recency-Based Attention Network for Point-of-Interest Recommendation," Ieee Access, vol. 10, pp. 36299-36310, 2022, doi: 10.1109/access.2022.3161941.
Z. Li, X. Huang, L. Gong, K. Yuan, and C. Liu, "Modeling Long and Short Term User Preferences by Leveraging Multi-Dimensional Auxiliary Information for Next POI Recommendation," Isprs International Journal of Geo-Information, vol. 12, no. 9, p. 352, 2023, doi: 10.3390/ijgi12090352.
D. Wang, C. Chen, C. Di, and M. Shu, "Exploring Behavior Patterns for Next-Poi Recommendation via Graph Self-Supervised Learning," Electronics, vol. 12, no. 8, p. 1939, 2023, doi: 10.3390/electronics12081939.
Y. Sun and J. Wang, "CLSAN:category-aware Long-and Short-termAttention Network for SequentialRecommendation," 2023, doi: 10.21203/rs.3.rs-2981023/v1.
D. Wang, X. Zhang, Z. Xiang, D. Yu, G. Xu, and S. Deng, "Sequential Recommendation Based on Multivariate Hawkes Process Embedding With Attention," Ieee Transactions on Cybernetics, vol. 52, no. 11, pp. 11893-11905, 2022, doi: 10.1109/tcyb.2021.3077361.
M. He, B. An, J. Wang, and H. Wen, "CETD: Counterfactual Explanations by Considering Temporal Dependencies in Sequential Recommendation," Applied Sciences, vol. 13, no. 20, p. 11176, 2023, doi: 10.3390/app132011176.
B. He, X. He, Y. Zhang, R. Tang, and C. Ma, "Dynamically Expandable Graph Convolution for Streaming Recommendation," pp. 1457-1467, 2023, doi: 10.1145/3543507.3583237.
Y. Zha, Y. Zhang, Z. Liu, and Y. Dong, "Self-Attention Based Time-Rating-Aware Context Recommender System," Computational Intelligence and Neuroscience, vol. 2022, pp. 1-10, 2022, doi: 10.1155/2022/9288902.
T. Huang, X. Pan, X. Cai, Y. Zhang, and X. Yuan, "Learning Time Slot Preferences via Mobility Tree for Next POI Recommendation," Proceedings of the Aaai Conference on Artificial Intelligence, vol. 38, no. 8, pp. 8535-8543, 2024, doi: 10.1609/aaai.v38i8.28697.
Z. Zhang, H. Zhang, Z. Zhang, and B. Wang, "Context-Embedded Hypergraph Attention Network and Self-Attention for Session Recommendation," Scientific Reports, vol. 14, no. 1, 2024, doi: 10.1038/s41598-024-66349-7.
N. Tintarev, B. P. Knijnenburg, and M. C. Willemsen, "Measuring the Benefit of Increased Transparency and Control in News Recommendation," Ai Magazine, vol. 45, no. 2, pp. 212-226, 2024, doi: 10.1002/aaai.12171.
S. Pourkhajouei, F. Toffano, P. Viappiani, and N. Wilson, "An Efficient Non-Bayesian Approach For Interactive Preference Elicitation Under Noisy Preference Models," pp. 308-321, 2023, doi: 10.1007/978-3-031-45608-4_23.
J. Li et al., "Point-of-Interest Recommendations Based on Immediate User Preferences and Contextual Influences," Electronics, vol. 12, no. 20, p. 4199, 2023, doi: 10.3390/electronics12204199.
R. Yuan, S. Meng, R. Dou, and X. Wang, "Modeling Long- And Short-Term Service Recommendations With a Deep Multi-Interest Network for Edge Computing," Tsinghua Science & Technology, vol. 29, no. 1, pp. 86-98, 2024, doi: 10.26599/tst.2022.9010054.
H. Chen, L. Liu, and Z. Chen, "TLSTSRec: Time-Aware Long Short-Term Attention Neural Network for Sequential Recommendation," Intelligent Data Analysis, vol. 29, no. 3, pp. 613-630, 2024, doi: 10.3233/ida-240051.
P. Gu, H. Hu, D. Wang, D. Yu, and G. Xu, "Temporal Diversity-Aware Micro-Video Recommendation With Long- And Short-Term Interests Modeling," Neural Processing Letters, vol. 56, no. 3, 2024, doi: 10.1007/s11063-024-11652-7.
M. Acharya, K. K. Mohbey, and D. S. Rajput, "Long-Term Preference Mining With Temporal and Spatial Fusion for Point-of-Interest Recommendation," Ieee Access, vol. 12, pp. 11584-11596, 2024, doi: 10.1109/access.2024.3354934.
J. Chen et al., "Multi-Temporal Sequential Recommendation Model Based on the Fused Learning Preferences," International Journal of Computational Intelligence Systems, vol. 16, no. 1, 2023, doi: 10.1007/s44196-023-00310-w.
H. Li and J. Li, "Research on Information Recommendation Method of Online Education Platform Based on User Preference Model," p. 225, 2023, doi: 10.1117/12.3006307.
Downloads
Published
Submitted
Revised
Accepted
Issue
Section
License
Copyright (c) 2024 Amir Vaziry
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
