The article dissects Milvus 3.0's Function Chain, explaining how fine‑grained ranking is moved into the engine with a two‑stage L0 early‑prune and L2 post‑reduction design, native XGBoost scoring, typed protobuf pipelines, and the trade‑offs revealed by source‑code analysis and community discussions.
The Kuaishou technology team reports that several of its papers were accepted at the prestigious ICML 2026 conference—including a spotlight paper on metaphor video understanding, works on causal discovery for irregular time series, image super‑resolution, large‑scale notification dispatch, full‑order ranking, phase‑aware MoE for RL, end‑to‑end e‑commerce search, spatial‑reasoning rewards, a unified SWE benchmark, video temporal grounding, and interpretable transformers—while also inviting attendees to visit their booth B101 in Seoul.
SORT re‑architects industrial‑scale ranking by shifting to a request‑centric data paradigm, integrating sparse and MoE optimizations into a Transformer backbone, and delivering significant CTR‑AUC, FLOPs, and online metric improvements while maintaining high training and inference efficiency.
The May 15 open‑source release of X’s For‑You recommendation system reveals a full pipeline—from query hydration and candidate sourcing to multi‑stage scoring—showing that the platform predicts a range of user actions, emphasizes content‑level signals, and offers creators concrete guidance to improve visibility.
The 2026 MCM/ICM competition, the largest ever with over 32,000 teams and 94,000 participants, saw Xi'an Jiaotong University top the overall leaderboard with 603 points while Tsinghua University slipped to 90th, and the analysis breaks down award distributions, school rankings, per‑problem top performers, and notable trends across the six contest problems.
This article walks through more than ten common Redis scenarios—including caching, distributed sessions, locks, global IDs, counters, rate limiting, bitmap statistics, shopping carts, timelines, message queues, lotteries, likes, product tagging, filtering, follow/fan relationships, and ranking—showing concrete command examples and code snippets for each.
This article explores sixteen practical Redis applications—including caching, distributed sessions, locks, global IDs, counters, rate limiting, bitmaps, shopping carts, timelines, message queues, lotteries, likes, product tags, filtering, follow relationships, and ranking—demonstrating how Redis can serve as a versatile data store beyond simple caching.
This article examines the challenges of applying large language models in enterprise settings and presents a detailed, three‑layer RAG architecture—including offline ingestion, hybrid retrieval, multi‑stage ranking, and prompt‑engineered generation—along with practical insights, model choices, and deployment Q&A.
This article examines the practical challenges of deploying Retrieval‑Augmented Generation in enterprise settings, outlines a layered RAG architecture with offline document processing and online query handling, and details the hybrid retrieval, multi‑stage ranking, knowledge filtering, and generation techniques that improve accuracy and reduce hallucinations.
This article reviews MySQL's GROUP BY fundamentals, highlights its limitations and execution order, then demonstrates how window functions—including ROW_NUMBER, RANK, DENSE_RANK, cumulative totals, moving averages, and TOP N techniques—can overcome those gaps for richer analytical queries.
This article details the evolution of a news‑app comment backend, covering early thread‑based displays, the transition to sharded databases and mixed adjacency‑path models, current hot‑comment ranking strategies, an in‑house experiment platform, topic aggregation via Kafka, and future AI‑driven architectural enhancements.
OneSug introduces an end‑to‑end generative framework that unifies recall, coarse‑ranking, and fine‑ranking for e‑commerce query suggestion, addressing the limitations of traditional multi‑stage cascades and dramatically improving relevance, efficiency, and business metrics in real‑world deployments.
Gaode Maps and Tongyi DeepResearch unveil ArenaRL, an open‑domain reinforcement‑learning framework that replaces absolute scoring with relative ranking, uses self‑play and a linear‑complexity tournament, and demonstrates measurable gains on POI ranking and complex travel‑planning tasks.
Tencent's ad tech team redesigned its ad ranking system by adding a parallel user‑experience‑optimized pipeline and evolving from manual CEM tuning to DDPG‑based reinforcement learning, achieving 10‑20% improvements in CTR, repeat‑view rates, and other experience metrics while maintaining overall spend.
VectorChord‑BM25 is a PostgreSQL extension that adds native BM25 ranking and tokenization, delivering up to three‑fold query‑per‑second improvements over ElasticSearch while maintaining comparable relevance scores, and includes detailed installation, usage examples, and performance analysis.
This study builds a comprehensive evaluation model for Chinese historical drama series, defining four primary and nine secondary indicators, standardizing data, applying weighted calculations and a time‑compensation factor to score 127 candidates and produce a TOP‑100 ranking that highlights the influence of audience reputation, market impact, professional recognition, and historical value.
This article details the EMER framework—a Transformer‑based, end‑to‑end multi‑objective ranking system that replaces handcrafted formulas with a learnable AI model, introduces relative‑satisfaction signals and dynamic loss weighting, and demonstrates significant offline and online performance gains in Kuaishou's short‑video recommendation pipeline.
This article explains the limitations of current pointwise in‑context learning methods, introduces a novel ranking‑based approach called SeDPO that learns preference orders among examples, and demonstrates its superior performance across multiple NLP tasks through extensive experiments and ablation studies.
Learn how MySQL window functions—row_number, rank, and dense_rank—can efficiently rank and rank‑tie data such as class scores or sales amounts, with clear syntax examples, differences in handling duplicate values, and practical SQL queries illustrated with real‑world scenarios.
Kuaishou has had eight cutting‑edge papers accepted at the International Conference on Machine Learning 2025, covering breakthroughs in multimodal emotion modeling, monotonic probability learning, causal effect generalization, cascade ranking, multimodal LLM alignment, ultra‑low‑rate image compression, and visual autoregressive super‑resolution, with links to each work and accompanying code repositories.
This article explores how to build a scalable, high‑performance leaderboard for hundreds of millions of users by comparing traditional database ORDER BY approaches with Redis sorted sets, addressing challenges such as hot keys, memory pressure, persistence risks, and presenting a divide‑and‑conquer implementation strategy.
This article examines six different leaderboard implementation strategies—from simple database sorting and cache‑plus‑scheduled tasks to Redis sorted sets, sharded Redis clusters, pre‑computed layered caches, and real‑time stream processing with Flink—detailing their suitable scenarios, advantages, disadvantages, and architectural diagrams to help engineers choose the most appropriate solution.
In 2024 the advertising team deployed an end‑to‑end AIGC pipeline that automatically creates high‑quality ad images, uses the multimodal Reliable Feedback Network and the million‑size RF1M dataset to filter outputs, builds rich offline and online multimodal representations with contrastive and list‑wise learning, and optimizes ranking architecture to deliver scalable, personalized creative selection.
Tech Insight presents concise overviews of ten JD retail technology papers accepted at top AI conferences in 2024, covering topics such as open‑vocabulary object detection, multi‑scenario ranking, diversity‑aware re‑ranking, a diversified product search dataset, semi‑supervised query classification, plug‑in CTR models, and methods to mitigate LLM hallucinations.
The article reviews the STAR framework, a training‑free recommendation approach that leverages large language model embeddings and collaborative co‑occurrence scores to retrieve and rank items, and evaluates its performance, hyper‑parameter effects, and ablation studies against existing LLM‑based recommender methods.
Booking.com’s ranking platform uses sophisticated machine‑learning models and a multi‑cluster backend architecture to deliver personalized hotel search results, detailing data pipelines, feature engineering, service components, performance challenges, and optimization techniques such as static fallback, multi‑stage ranking, and model inference acceleration.
This article describes the definition, architecture, and practical applications of explainability in JD's retail recommendation system, covering ranking, model, and traffic explainability, system challenges, data infrastructure, and specific techniques such as SHAP and Integrated Gradients for interpreting model decisions.
This article introduces Retrieval‑Augmented Generation (RAG) as a solution to the hallucination, freshness, and data‑privacy issues of large language models, details its modular architecture, explains the layered system design and hybrid retrieval pipeline, and shares the practical challenges and engineering tricks encountered when deploying RAG in enterprise office scenarios.
This article summarizes Meituan's content search system, detailing the challenges of heterogeneous, high‑frequency local content, the multi‑modal tagging and representation pipeline, recall and ranking optimizations, satisfaction metrics, multi‑objective fusion, heterogeneous mixing, and future directions for improving user experience in local life services.
This report analyzes performance bottlenecks caused by serialization in a search‑recommendation system, presents detailed measurements of request latency, evaluates multiple optimization strategies—including Redis caching, lazy metric handling, and custom byte‑array serialization—and documents the resulting latency reductions and implementation considerations.
This article presents JD.com’s multimodal recommendation system architecture, covering content understanding, multimodal ranking and recall models, practical deployment pipelines, and future research directions such as large‑model integration and supply‑side generation, all illustrated with detailed diagrams and Q&A.
The latest TIOBE index shows Python surpassing 18% for the first time, overtaking Java's historic high, while PHP drops sharply, and the report explains the methodology, historical trends, and potential challengers like Rust and Kotlin.
In real‑time bidding advertising, a multi‑path recall framework quickly filters billions of ads using parallel non‑personalized and personalized strategies—such as hot‑item rules, collaborative‑filtering, skip‑gram vectors, and GraphSAGE embeddings—while respecting targeting constraints, before a ranking stage optimizes eCPM, with effectiveness measured offline and online and future extensions planned with large language models.
This article presents ten crucial intermediate‑to‑advanced SQL concepts—including CTEs, recursive queries, temporary functions, CASE pivots, EXCEPT vs NOT IN, self‑joins, ranking functions, delta calculations, cumulative totals, and date‑time manipulation—each explained with clear examples and code snippets.
This article presents ten essential advanced MySQL concepts—including CTEs, recursive CTEs, temporary functions, CASE‑WHEN pivots, EXCEPT vs NOT IN, self‑joins, ranking window functions, delta calculations, running totals, and date‑time manipulation—each explained with clear examples and practical SQL snippets.
The article details a comprehensive architecture for high‑concurrency services—including a Redis‑backed ranking system, distributed locking, Bloom‑filter nickname deduplication, Netty‑based reliable messaging, IoT MQTT/REST integration, live‑streaming pipelines, layered performance tuning, and automated traffic‑replay testing to ensure scalability and robustness.
The advertising engine uses a five‑stage funnel—retrieval, recall, coarse ranking, fine ranking, and re‑ranking—each optimized with specialized indexes, multi‑channel recall, multi‑objective twin‑tower models, deep CTR/CVR predictors, and cold‑start paths, delivering up to 33 % spend growth, 6 % eCPM lift and lower latency while maintaining diversity.
This article reviews the evolution of JD’s recommendation advertising ranking mechanism, covering its economic auction origins, challenges of multi‑material valuation, user interest uncertainty, and multi‑item auction fairness, and describes AI‑driven solutions such as deep auction models and reinforcement‑learning‑based ListVCG.
The article analyzes JD.com's recommendation advertising ranking auction mechanism, detailing its objectives, challenges in traffic value estimation, user interest exploration, and multi‑item auction fairness, and describing the technical evolution from traditional auctions to deep‑learning‑driven solutions.
This article investigates how large language models can be applied to recommendation tasks, describing two usage strategies, various ranking approaches, experimental evaluations on multiple datasets, comparisons with traditional models, and analyses of prompt design, cost, and cold‑start capabilities.
This article outlines Meituan’s end‑to‑end content‑intelligent distribution pipeline, detailing challenges of massive multimodal search, supply labeling, semantic and personalized recall, multi‑objective ranking with distillation and MMoE/PPNet, heterogeneous mixing, and future plans for automated detection and large‑language‑model integration.
This article explains the fundamental concepts of search engine technology—including forward and inverted indexes, tokenizers, stop words, synonym handling, ranking algorithms, and NLP integration—and provides a concise Go implementation with code examples and performance testing.
The article details how Autohome tackled the cold‑start problem for newly generated content by redesigning the recommendation pipeline, introducing multi‑path recall, refining ranking and re‑ranking formulas, and applying strategic controls, resulting in a rise of cold‑start success rate from 27% to over 99% and a CTR increase from 5% to 14%.
This article investigates how large language models can be applied to recommendation tasks, presenting two usage strategies, experimental evaluations on multiple datasets, comparisons with traditional baselines, and analyses of prompting methods, cost, and cold‑start performance.
This article presents a comprehensive design for Zhuanzhuan's home‑page recommendation pipeline, detailing the system architecture, challenges of traffic efficiency and diversity, and a two‑stage solution that applies Proximal Policy Optimization reinforcement learning in the re‑ranking module and Determinantal Point Process optimization in the coarse‑ranking and traffic‑pool stages, followed by offline simulation, online deployment, and evaluation metrics.
The October TIOBE Index shows Java slipping out of the top three while C# gains ground, sparking speculation that C# could surpass Java soon and highlighting how licensing changes and Kotlin’s rise are reshaping programming language popularity.
This article presents Baidu's commercial multimodal understanding framework and AIGC innovations, detailing rich-media multimodal perception, the VICAN‑12B multimodal representation‑generation model, scenario‑specific fine‑tuning, feature quantization for ranking, and practical applications such as marketing content generation, digital‑human video creation, and poster synthesis.
This article provides a concise overview of recommendation systems, covering their definition, core framework of recall, ranking, and re‑ranking, various recall strategies including multi‑path and vector‑based methods, similarity calculations, and practical implementation details such as AB testing and code examples.
This article provides a comprehensive overview of recommendation systems, covering their definition, basic framework, request flow, AB testing, recall strategies (both non‑personalized and personalized), collaborative‑filtering methods, vector‑based retrieval, wide‑and‑deep models, and the MMR re‑ranking algorithm with code examples.
The paper presents a unified word‑distribution platform that delivers personalized bottom‑words, hot‑words, and drop‑down suggestions across e‑commerce domains, detailing its preprocessing, recall, fusion, ranking, and re‑ranking pipelines, C++ engine migration, script hot‑deployment, visual configuration tools, and stability mechanisms for scalable, low‑maintenance guide services.
Meituan’s food‑delivery team built a novelty‑focused recommendation pipeline—combining dual‑tower recall, novelty‑aware ranking, personalized mixed‑ranking weights, and reinforcement‑learning insertion—to surface merchants unseen by users, achieving 19% higher exposure novelty, 25% more order novelty, and improved ratings while keeping RPM loss under 0.5%.
This article explains the design, implementation, and iterative optimization of Boss Circle's recommendation engine, covering the initial simple ranking, the introduction of Elasticsearch‑based scoring, multi‑pool data sources, machine‑learning experiments, real‑time feature handling, and future personalization challenges.
This article explains how Xianyu’s product recommendation system tackles massive data, diverse business scenarios, and engineering challenges by designing a unified recommendation middle‑platform that abstracts data, recall, ranking, and re‑ranking stages, enabling rapid scene onboarding and scalable model iteration.
This article explains how MySQL 8.x window functions such as OVER, PARTITION BY, and ORDER BY can simplify complex ranking and aggregation queries, demonstrates creating a sample scores table, and provides practical examples of functions like ROW_NUMBER, RANK, DENSE_RANK, NTILE, LAG, and LEAD with their results.
This article outlines the recent full‑cycle iterations of JD’s search Explore‑Exploit (EE) system, covering adaptive dynamic detection models, upgraded scenario modeling, two‑stage scoring and insertion consistency, end‑to‑end dynamic insertion, and context‑aware brand‑store dimension detection, with detailed methodology, experiments, and online results.
The Joint Optimization of Ranking and Calibration (JRC) model introduces a two‑logit generative‑discriminative architecture that jointly minimizes LogLoss for calibration and a listwise ranking loss, delivering superior GAUC and CTR performance across Alibaba’s display‑ad system, especially for sparse long‑tail users, while remaining simple to train and deploy.
The TIOBE June 2023 ranking reveals Python still leading but slipping to 13% share, while AI-driven popularity, emerging languages X++ and Raku, and the steady rise of C, C++, and Java reshape the top‑10 programming language landscape.
Qianchuan is a unified recommendation platform that consolidates numerous low‑traffic, diverse scenarios into a five‑layer architecture—service, access, DPP, algorithm, and infrastructure—addressing challenges of varying products, goals, strategies, recommendation types, and limited resources through flexible product selection, multi‑goal support, advanced recall and ranking models, and extensible, low‑cost algorithms, while planning broader scene coverage, bias reduction, and componentized, reproducible solutions.
The paper introduces a Generator‑Evaluator (GE) architecture that end‑to‑end re‑ranks information‑flow items using a pointer‑network seq2seq generator and a reward‑estimating evaluator, jointly optimizing relevance and business utilities such as diversity, traffic control, inter‑group ordering, and fixed‑slot insertion, achieving over 70% better‑percentage and significant online gains on Taobao.
Daily Good Shop improves e‑commerce recommendations by first ranking products with long‑term user behavior models, assembling top items into cards, then ranking those cards using a shared‑bottom multi‑task network that jointly predicts click, subscription and lead‑IPV, and finally re‑ranking card sequences via beam‑search, yielding over 2 % more clicks, 34 % more subscriptions, 33 % more lead‑IPV and 22 % longer dwell time.
The April 2024 TIOBE index shows a stable top‑20 with Python, C, Java, C++ and C# unchanged, a 4.68% surge for C++, Rust holding its lower‑top‑20 spots, and the newcomer Zig entering the top 50 at rank 46, accompanied by a brief overview of its key features and industry reactions.
At the 2023 Elastic China Developer Conference in Shenzhen, Peng Cheng of Hello Technology will demonstrate how migrating online machine‑learning predictions into Elasticsearch can exploit its distributed architecture to rank thousands of models, expand model types and computational depth, and unlock new growth opportunities for business applications, underscoring the event’s status as China’s premier Elasticsearch open‑source technology forum.
The article surveys recent academic advances in both sparse inverted‑index and dense semantic retrieval for large‑scale search, highlighting key papers on decision frameworks, benchmarks, sparse lexical models, dual encoders, and hybrid techniques, while discussing challenges such as single‑vector limits and proposing multi‑view and hybrid solutions.
This article explains how InstructGPT's reward model is trained by collecting human‑annotated ranking sequences instead of absolute scores, describes the rank‑loss formulation, provides Python code for the model and loss computation, and presents experimental results demonstrating the approach.
The article presents a comprehensive technical roadmap for Alibaba Mama's display advertising cascade ranking system, introducing full‑chain linkage, precise‑value estimation models (PDM, ESDM) and set‑selection approaches (LDM, LBDM), and demonstrates how these innovations jointly improve CTR and RPM while outlining future research directions.
This interview compiles expert opinions on the end‑to‑end recommendation system pipeline—including architecture, data collection, user profiling, content structuring, feature engineering, recall strategies, ranking algorithms, multi‑objective optimization, multi‑modal fusion, re‑ranking, cold‑start solutions, evaluation metrics and real‑world applications—highlighting the technical challenges and practical solutions.
This interview with three recommendation‑system experts explores the technical architecture, data sources, feature engineering, recall and ranking strategies, evaluation metrics, cold‑start solutions, and practical difficulties, offering actionable insights to avoid common pitfalls in real‑world recommender deployments.
The paper details Cloud Music’s video‑search pipeline—query understanding, recall, relevance, ranking and re‑ranking—highlighting challenges such as ambiguous content, timeliness and multi‑objective goals, and describes two deployed models (a twin‑tower aspect relevance network and a click‑graph propagator) that together boost click‑through rate by 1.5 % and effective CTR by 2.3 %.
This article explains the architecture of recommendation and search systems, detailing various recall methods such as collaborative filtering, matrix factorization, and vector‑based approaches, as well as ranking models like LR, FM, and DeepFM, and discusses re‑ranking and traffic control strategies.
This article demonstrates how to create a score table in MySQL, insert sample data, and implement ranking of students using both user‑defined variables for pre‑8.0 versions and modern window functions like RANK(), DENSE_RANK() and ROW_NUMBER() to handle ties and gaps.
The November 2022 TIOBE index shows Rust re‑entering the Top 20 with a record 0.70% share, highlights shifts among PHP, SQL, Scratch and other languages, and provides detailed rankings from the top 10 to the 100th position, offering insight into programming language popularity trends.
This article presents a comprehensive retrieval‑based dialogue system designed to assist customer‑service agents by recommending candidate replies, detailing its five‑layer architecture, metric suite, text and vector retrieval modules, ranking strategies, and real‑world deployment results across multiple business scenarios.
This article details Meituan's retrieval‑based dialogue framework for customer service, covering its five‑layer architecture, offline‑to‑online metric system, text and vector recall strategies, ranking models with pre‑training and contrastive learning, and real‑world deployment results across multiple business scenarios.
This article explains why MySQL struggles with large‑scale ranking, introduces Redis sorted sets as a high‑performance alternative, and provides complete Go code examples—including direct command usage and a struct‑based wrapper—to implement, query, and manage ranked data efficiently.
The Keener method assigns numerical ratings to competing teams by linking each team's score to its absolute strength, which depends on relative strength against opponents, and uses linear‑algebraic techniques such as eigenvectors and the Perron‑Frobenius theorem to derive consistent rankings.
The article introduces the Bayesian Personalized Ranking (BPR) algorithm, explains its background in ranking‑based recommendation, details its probabilistic modeling assumptions, optimization objective, gradient‑based learning process, and compares it with matrix‑factorization methods like FunkSVD, providing a concise training workflow.
This article reviews how graph neural networks are applied across the three stages of recommendation systems—recall, ranking, and re‑ranking—detailing novel models such as NIA‑GCN, GraphSAIL, and DGENN, their experimental improvements, and future research directions.
This article presents a comprehensive overview of AI-driven music comment moderation and ranking systems, detailing business scenarios, model architectures, data processing techniques, performance improvements, and future directions for both QQ Music and K‑Song platforms.
The September 2023 DB-Engines ranking update shows Oracle’s steep decline, while MySQL and MongoDB gain points, and presents the top ten databases across relational, key‑value, document, time‑series, and graph categories along with the five metrics used to calculate popularity.
The article outlines how search and recommendation systems have evolved from simple hot‑list displays to sophisticated, data‑driven pipelines comprising recall, fine‑ranking and re‑ranking stages, describes an integrated low‑code engine with standardized features, configurable components and intelligent modules that enable rapid deployment across many scenarios, delivering notable CTR, GMV and engagement gains at 哈啰.
The July 2023 DB-Engines ranking shows Oracle, PostgreSQL and MongoDB slipping, while MySQL and Microsoft SQL Server climb, and provides detailed scores, trend charts, and the methodology behind the monthly popularity scores for the top ten database systems.
This article presents ten core SQL techniques—including CTEs, recursive CTEs, temporary functions, CASE WHEN pivots, EXCEPT vs NOT IN, self‑joins, ranking window functions, delta calculations, cumulative sums, and date‑time manipulation—each explained with clear descriptions and practical query examples to help candidates ace data‑analysis interviews.
The article details the progressive architectural evolution of JD Daojia's search system—starting from a simple, single‑layer ES‑based 1.0 design, through the 2.0 overhaul that introduced full‑recall, independent ranking services, and index disaster‑recovery, to the 3.0 version that adds multi‑path recall, sophisticated ranking models, and automated routing for high availability.
Harbor’s growth engine combines a passive, attribution‑driven traffic‑allocation algorithm with componentized ranking, search, and marketing systems—using pairwise/Listwise models, multi‑task CTR/CVR prediction, and automated strategy triggers—to align short‑term efficiency with long‑term LTV goals while moving toward causal inference and domain‑expert‑driven general models.
TOPSIS (Technique for Order Preference by Similarity to an Ideal Solution) is a widely used multi‑criteria decision‑making method that ranks alternatives by their geometric distance to an ideal positive solution and farthest from a negative solution, with a straightforward seven‑step process from data normalization to final ranking.
This article presents an in‑depth overview of search term recommendation in QQ Browser, covering the various recommendation scenarios, the composition of recommendation items, the multi‑stage algorithm architecture, key technical challenges, evaluation metrics, and future research directions such as multi‑task and session‑aware modeling.
This article explains what SQL window functions are, shows their syntax, and provides step‑by‑step basic and advanced examples—including how to rank rows within groups and reset rankings when key columns change—complete with runnable SQL scripts and result screenshots.
The February 2022 DB‑Engines ranking shows Snowflake’s rapid rise, a sharp decline for Oracle, MySQL and Microsoft SQL Server, stable positions for Elasticsearch, and detailed score trends across relational, key‑value, document, time‑series and graph databases, highlighting five popularity metrics used for the assessment.
The article outlines DeWu’s warehouse‑management recommendation system, which combines an online‑near‑line‑offline architecture to quickly recall viable shelf slots and rank them by space utilization, travel time, and sales potential, enabling automated, constraint‑aware placement that cuts picking time and inventory costs.
RedMonk's Q1 2022 programming language ranking, based on GitHub and Stack Overflow data, lists the top 20 languages, highlights the overall stability of the rankings, and provides detailed commentary on notable shifts for languages such as Python, PHP, C++, TypeScript, Dart, Kotlin, and Rust.
This article presents a comprehensive overview of Huya's live‑streaming recommendation system, covering business background, overall architecture, vector‑based retrieval, detailed ranking pipeline, technical challenges, deployment strategies, scalability, and future outlook.
The article provides a thorough guide to ranking in recommendation systems, detailing the pipeline architecture, sample handling challenges, extensive feature engineering categories, the evolution from collaborative filtering to deep and attention‑based models, and key optimization trade‑offs between memorization, generalization, and efficient user‑interest modeling.
This article presents a comprehensive overview of Huya Live's recommendation system, covering business background, system architecture, vector retrieval techniques, ranking pipeline, technical challenges, implementation details, and future outlook, highlighting scalability and performance optimizations.
This report details how the Search Recommendation team at 58.com upgraded their deep learning ranking model for recruitment by adding multi-valued and semantic vector features, integrating conversion sequences, employing feature‑crossing techniques, optimizing offline data pipelines, and planning future multi‑scene improvements to boost CTR and relevance.
The article details Shopee Chatbot’s end‑to‑end development of a dropdown recommendation feature, describing the retrieve‑then‑rank architecture with BM25 and vector recalls, multilingual pre‑training and distillation, DeepFM‑based ranking, experimental gains in CTR and conversion, deployment infrastructure, business impact, and future enhancements.
The TIOBE Index released its February 2022 ranking, showing the top‑20 programming languages with Python, C and Java each gaining over 1% and highlighting shifts such as PHP re‑entering the top ten, Go climbing to 11th, and detailed listings for positions 21‑100.
This article presents a comprehensive overview of 58 Local Service's recommendation system, detailing the diverse recommendation scenarios, challenges such as information homogeneity and complex user structures, the multi‑stage recall and ranking pipelines, model evolutions from statistical methods to deep learning, and future work to improve data quality and model efficiency.
The IEEE Spectrum 2021 programming language ranking shows Python retaining the top spot across overall and multiple sub‑rankings while Microsoft’s C# jumps from 23rd in 2020 to 6th in 2021, reflecting shifting industry demand and emerging trends.
This talk presents the design and implementation of 58's commercial recruitment recommendation system, covering the business scenario, system architecture, regional and behavior‑based recall methods, various ranking models—including coarse‑ranking, dual‑tower, DIN‑bias, and multitask W3DA—and future optimization directions.
This talk presents the design and implementation of 58’s commercial recruitment recommendation system, covering the characteristics of the app’s recommendation scenario, system architecture, region‑based and behavior‑based recall methods, and coarse‑ and fine‑ranking models with various optimizations and future directions.
