A Survey of User Lifelong Behavior Modeling: Perspectives on Efficiency and Effectiveness

In industrial-scale recommender systems, the continuous accumulation of user interactions gives rise to large-scale and heterogeneous behavior sequences, posing significant challenges to both computational efficiency and storage scalability. To support user lifelong behavior modeling (ULBM) under stringent industrial constraints, extensive research efforts have been devoted to balancing efficiency and effectiveness. This survey presents a systematic review of ULBM methods that have been widely adopted in real-world recommender systems and demonstrated substantial practical value. We organize existing studies around the central industrial challenge of efficiency–effectiveness trade-offs. Specifically, efficiency is examined from both algorithmic and system-level perspectives, while effectiveness is discussed in terms of enhanced modeling of intrinsic sequential dependencies and the incorporation of external contextual signals. We further highlight how the synergy between efficiency-oriented and effectiveness-oriented designs continually improves the return on investment in large-scale recommender systems. Finally, we summarize publicly available datasets for ULBM research and outline several promising directions for future investigation, aiming to provide insights and guidance for subsequent studies. To support ongoing research, we maintain a living repository tracks emerging literature and reference implementations: https://github.com/Kuaishou-RecModel/Survey of ULBM