feature platform

High Availability Architecture

Jun 11, 2024 · Artificial Intelligence

Tencent News Recommendation Architecture Upgrade: From Legacy Systems to a Scalable AI-Driven Platform

This article details the evolution of Tencent News from a portal‑style content display to a personalized recommendation engine, describing the legacy architecture problems, the design goals, the new modular and scalable architecture, feature platform improvements, debugging tools, and stability measures that together increased availability to 99.99% and cut costs by over 60%.

AIDebuggingarchitecture

0 likes · 28 min read

Tencent News Recommendation Architecture Upgrade: From Legacy Systems to a Scalable AI-Driven Platform

Bilibili Tech

Jun 27, 2023 · Artificial Intelligence

Design and Implementation of a Real-Time Advertising Feature Platform for CTR Prediction at Bilibili

To eliminate data fragmentation, feature inconsistencies, and multi‑language implementation challenges, Bilibili built a unified real‑time advertising feature platform that aligns offline, hourly, and online pipelines via a shared C++ library and JNI, boosting CTR prediction accuracy, cutting training costs, and increasing ad revenue by over 1 %.

CTR predictionFlinkadvertising

0 likes · 11 min read

Design and Implementation of a Real-Time Advertising Feature Platform for CTR Prediction at Bilibili

DataFunTalk

Feb 25, 2023 · Big Data

T3 Travel’s Modern Data Stack and Feature Platform: Architecture and Practices

This article details T3 Travel’s exploration of the Modern Data Stack, describing its four‑point overview, business scenarios, the initial MDS implementation using Apache Hudi and Kyuubi, and the design of a feature platform that integrates Metricflow, Feast, and other components to support data processing, analytics, and machine‑learning workflows.

Apache HudiBig DataData Lake

0 likes · 22 min read

T3 Travel’s Modern Data Stack and Feature Platform: Architecture and Practices

DataFunTalk

Jul 26, 2022 · Big Data

Feature Platform Architecture and Stream‑Batch Integrated Solutions

This talk presents Shuhe Technology’s feature platform, detailing its four‑layer architecture, feature storage services, stream‑batch integrated processing, event‑center design, consistency models, and four model‑strategy invocation schemes, illustrating data flows from MySQL through Sqoop, Kafka, Flink, HBase and ClickHouse.

Big DataClickHouseData Pipeline

0 likes · 17 min read

Feature Platform Architecture and Stream‑Batch Integrated Solutions

DataFunTalk

Jan 11, 2021 · Big Data

Design and Scaling of Meituan Delivery Real‑Time Feature Platform

This article details how Meituan built a minute‑level, high‑throughput real‑time feature platform for its delivery business, covering the business model, six‑layer architecture, data processing challenges, stability measures, scaling achievements, and future roadmap to support millions of orders per minute with sub‑50 ms latency.

Big DataMeituanReal-time Data

0 likes · 14 min read

Design and Scaling of Meituan Delivery Real‑Time Feature Platform