The article explains how AI product managers can avoid costly product failures by designing a comprehensive, multi‑dimensional evaluation framework that guides development, quantifies progress, and builds trust with users and stakeholders.
The article reveals that many AI product managers can talk about AIGC and agents but stumble when asked to design a rigorous evaluation system, illustrating the problem with a chatbot case study and presenting a detailed 1+3 multi‑dimensional framework to guide product definition, development, and iteration.
This paper introduces IAK, a unified multi‑domain recommendation paradigm that treats the system as a large model, leveraging pre‑training and fine‑tuning with an information‑aware adaptive kernel to capture rapid user interest shifts while reducing training costs and improving online performance.
The article explains the core challenges of real‑time bidding, reviews Kuaishou's evolution from PID to MPC to reinforcement learning, and introduces generative reinforcement‑learning methods (GAVE and CBD) that combine decision transformers or diffusion models with value‑guided exploration and score‑based RTG, achieving significant offline and online performance gains.
The article presents a CIKM‑2024 paper that introduces MODRL‑TA, a multi‑objective deep reinforcement learning system combining multi‑objective Q‑learning, a cross‑entropy‑based decision‑fusion algorithm, and a progressive data‑augmentation pipeline to dynamically allocate search traffic on JD.com, with both offline and online experiments showing substantial gains in CTR, CVR, and overall platform performance.
This article presents a two‑stage constrained actor‑critic (TSCAC) algorithm that models short‑video recommendation as a constrained reinforcement‑learning problem, details its theoretical formulation and optimization loss, and validates its superiority through extensive offline and online experiments, followed by a multi‑task reinforcement‑learning framework (RMTL) that further improves multi‑objective recommendation performance.
The paper models short‑video recommendation as a constrained Markov decision process and introduces a two‑stage constrained actor‑critic algorithm that jointly maximizes watch time while satisfying multiple interaction constraints, demonstrating superior offline and online performance on the KuaiRand dataset and Kuaishou app.
HiNet, a hierarchical information extraction network combining a scenario‑aware attentive layer and a customized gate‑control layer, jointly learns shared and scenario‑specific representations for multiple recommendation tasks, delivering consistently higher CTR and CTCVR performance across six Meituan restaurant scenarios than strong baselines in both offline and online evaluations.
The paper introduces Sliding Spectrum Decomposition (SSD), a tensor‑based method that quantifies feed diversity through singular‑value volume within sliding windows, integrates quality‑exploration trade‑offs, and employs a hybrid CB2CF model for item embeddings, achieving superior offline and online performance versus DPP in Xiaohongshu’s feed.
