The NetEase LeiHuo UX Data Team creates practical data‑modeling solutions for gaming, offering comprehensive analysis and insights to enhance user experience and enable precise marketing for development and operations. This account shares industry trends and cutting‑edge data knowledge with students and data professionals, aiming to advance the ecosystem together with enthusiasts.
This article introduces the k‑means clustering algorithm and its major variants—k‑means++, k‑medoids, k‑medians, k‑modes, and k‑prototype—explaining their characteristics, step‑by‑step procedures, and provides a practical R implementation with code examples for data analysis.
This article explains how linear congruential generators produce pseudo‑random numbers, demonstrates their use with step‑by‑step examples, visualizes the distribution of generated values, and applies the method to design a simple gacha system while discussing its statistical properties and practical limitations.
This article provides a comprehensive introduction to Docker, explaining what containers are, how they differ from virtual machines, the role of Linux namespaces and cgroups, and includes step‑by‑step practices for limiting container resources using CPU quotas and task assignment.
The article introduces Netease Thunderfire UX's big data team and its multidisciplinary approach to game user experience, covering topics such as mathematics, engineering, product practice, AI, visualization, platform development, data analysis, and tool creation for game data professionals.
This article explains MySQL's three‑layer logical architecture, the roles of binary log, redo log, and undo log, how they interact during data updates, and the configuration options that affect durability and performance.
The State Council’s notice issues the 14th Five-Year Plan for Digital Economy Development, outlining China’s current digital economy status, strategic goals, infrastructure upgrades, data governance, industry digitalization, security measures, and international cooperation to drive high‑quality, inclusive growth through data and technology.
This article explains three frequent mistakes in churn analysis—misinterpreting churn rates, falling into Simpson's paradox, and incorrectly inferring causality—illustrated with game‑related examples and emphasizes the need to combine multiple metrics for accurate conclusions.
