BestHub
Sign in
Tagged articles

machine learning

1966 articles · Page 11 of 20
Meituan Technology Team
Meituan Technology Team
Dec 2, 2021 · Artificial Intelligence

Pretraining Techniques for Search Advertising Relevance at Meituan

Meituan improves search‑ad relevance by applying pre‑trained BERT models enhanced with data‑augmented samples, multi‑task learning, keyword extraction and two‑stage knowledge distillation, producing a lightweight distilled model that, when fused with traditional relevance signals, boosts CTR, lowers Badcase@5 and raises NDCG while preserving revenue.

BERTPretrainingadvertising relevance
0 likes · 30 min read
Pretraining Techniques for Search Advertising Relevance at Meituan
21CTO
21CTO
Nov 30, 2021 · Artificial Intelligence

Why Twitter’s New CEO Is Tackling Algorithmic Bias and What It Means for AI

Jack Dorsey stepped down as Twitter CEO, appointing CTO Parag Agrawal—an AI‑focused leader who aims to reduce algorithmic bias, advance open‑source social standards, and drive growth—while the company’s stock rose and broader industry trends in leadership were highlighted.

AI biasCEO transitionParag Agrawal
0 likes · 7 min read
Why Twitter’s New CEO Is Tackling Algorithmic Bias and What It Means for AI
Code DAO
Code DAO
Nov 29, 2021 · Artificial Intelligence

Feature Selection: Reducing Input Variables for Predictive Modeling

This article explains the purpose and types of feature selection, compares supervised and unsupervised, wrapper, filter, and embedded methods, discusses choosing statistical metrics based on variable types, and provides scikit‑learn code examples for regression and classification tasks.

Embedded MethodsFilter MethodsWrapper Methods
0 likes · 12 min read
Feature Selection: Reducing Input Variables for Predictive Modeling
DataFunTalk
DataFunTalk
Nov 28, 2021 · Artificial Intelligence

Fine‑Grained Content Understanding and Operation in QQ Music: Optimizing the Recommendation System

This article presents QQ Music’s end‑to‑end solution for data‑driven content understanding, value evaluation, and fine‑grained operation, detailing offline and real‑time pipelines, neural‑network models, a content middle‑platform, parameter services, and a precise delivery system that boost user engagement while preserving experience.

AI modelscontent understandingdata-driven operation
0 likes · 24 min read
Fine‑Grained Content Understanding and Operation in QQ Music: Optimizing the Recommendation System
DataFunSummit
DataFunSummit
Nov 27, 2021 · Artificial Intelligence

Knowledge Graph Construction, Applications, and Recent Advances in Entity Linking

This article reviews the fundamentals of knowledge graphs, their practical uses in question answering, search and recommendation, and surveys recent research on entity linking—including dual‑encoder retrieval, BERT‑based models, multilingual approaches, and zero‑shot methods—while also outlining modern knowledge‑graph construction pipelines and open challenges.

Knowledge GraphNatural Language Processingentity linking
0 likes · 21 min read
Knowledge Graph Construction, Applications, and Recent Advances in Entity Linking
DataFunTalk
DataFunTalk
Nov 26, 2021 · Artificial Intelligence

Graph Neural Networks for Molecular Networks and Drug Discovery

This presentation by Stanford PhD student Huang Kexin explores the challenges and innovations of applying graph machine learning to molecular and biomedical networks, introducing specialized GNN architectures, actionable hypothesis generation, domain‑scientist interfaces, few‑shot learning, and the Therapeutics Data Commons for accelerating drug discovery.

Graph Neural Networksbioinformaticsbiomedical AI
0 likes · 9 min read
Graph Neural Networks for Molecular Networks and Drug Discovery
iQIYI Technical Product Team
iQIYI Technical Product Team
Nov 26, 2021 · Industry Insights

How iQIYI Built an Unmanned Fault‑Handling System for 99% Reliability

This article details iQIYI's unmanned monitoring platform, covering its design goals, overall architecture, core modules such as real‑time data collection, decision engine, and event‑processing engine, as well as the machine‑learning model used for production‑time prediction and the system's operational results and future roadmap.

Operationsfault automationmachine learning
0 likes · 13 min read
How iQIYI Built an Unmanned Fault‑Handling System for 99% Reliability
G7 EasyFlow Tech Circle
G7 EasyFlow Tech Circle
Nov 24, 2021 · Artificial Intelligence

How G7 Tackles Truck Underwriting Risk: Modeling Challenges & Solutions

This article outlines G7's early-stage exploration of truck underwriting risk modeling, detailing data foundations, modeling objectives, key challenges such as target diversity and claim randomness, and proposes practical solutions across data sampling, feature engineering, model structure, and regionalization to improve risk assessment.

Risk Modelingmachine learningtruck insurance
0 likes · 17 min read
How G7 Tackles Truck Underwriting Risk: Modeling Challenges & Solutions
DataFunSummit
DataFunSummit
Nov 23, 2021 · Artificial Intelligence

Travel Intention‑Aware Out‑of‑Town POI Recommendation (TRAINOR) Framework

This article presents TRAINOR, a travel‑intention‑aware out‑of‑town POI recommendation framework that tackles cold‑start, interest‑drift, and geographical gaps by jointly modeling hometown preferences with graph neural networks, neural topic models for travel intention, and matrix‑factorization‑based out‑of‑town preference transfer, and validates its superiority through extensive cross‑city experiments.

Graph Neural NetworkPOI recommendationcold start
0 likes · 16 min read
Travel Intention‑Aware Out‑of‑Town POI Recommendation (TRAINOR) Framework
DataFunSummit
DataFunSummit
Nov 21, 2021 · Artificial Intelligence

Sequential Recommendation Algorithms: Overview and Techniques

This article surveys sequential recommendation methods, covering standard models such as pooling, RNN, CNN, attention, and Transformer, as well as long‑short term, multi‑interest, multi‑behavior approaches, and recent advances like contrastive learning, highlighting their impact on recommendation performance.

AttentionRNNTransformer
0 likes · 8 min read
Sequential Recommendation Algorithms: Overview and Techniques
DataFunSummit
DataFunSummit
Nov 19, 2021 · Artificial Intelligence

Sliding Spectrum Decomposition (SSD) for Diversified Recommendation in Re‑ranking

This article reviews the Sliding Spectrum Decomposition (SSD) model presented by Xiaohongshu at KDD 2021, explaining how it incorporates sliding‑window diversity into the re‑ranking stage, combines content‑based and collaborative‑filtering embeddings via the CB2CF framework, and demonstrates its effectiveness through offline and online A/B experiments.

EmbeddingSSDdiversity
0 likes · 14 min read
Sliding Spectrum Decomposition (SSD) for Diversified Recommendation in Re‑ranking
58 Tech
58 Tech
Nov 16, 2021 · Artificial Intelligence

Deep Optimization of the 58 Yellow Pages Smart Chat Assistant for Enhanced User Experience and Business Opportunity Conversion

This article details the development and continuous optimization of 58.com’s Yellow Pages smart chat assistant, covering background, metrics, model improvements for QABot and TaskBot, slot extraction, quality assessment, and future directions, resulting in near‑human conversion rates and significant operational savings.

AIBusiness OpportunityNatural Language Processing
0 likes · 22 min read
Deep Optimization of the 58 Yellow Pages Smart Chat Assistant for Enhanced User Experience and Business Opportunity Conversion
DataFunTalk
DataFunTalk
Nov 16, 2021 · Artificial Intelligence

Hotel Search Relevance Modeling and Architecture at Fliggy (Alibaba)

This article presents a comprehensive overview of Fliggy's hotel search relevance system, covering the business background, multi‑scenario architecture, core factor estimation, entity recognition, text and spatial relevance modeling, multi‑scenario fusion, and future optimization directions.

AIBERThotel search
0 likes · 17 min read
Hotel Search Relevance Modeling and Architecture at Fliggy (Alibaba)
DataFunSummit
DataFunSummit
Nov 14, 2021 · Artificial Intelligence

Overview of Pre‑training Models and the UER‑py Framework for Natural Language Processing

This article introduces the importance of pre‑training in natural language processing, reviews classic pre‑training models such as Skip‑thoughts, BERT, GPT‑2 and T5, presents the modular UER‑py framework and its Chinese resources, compares it with Huggingface Transformers, and outlines practical deployment steps in industry.

NLPPretrainingUER-py
0 likes · 22 min read
Overview of Pre‑training Models and the UER‑py Framework for Natural Language Processing
DataFunTalk
DataFunTalk
Nov 8, 2021 · Artificial Intelligence

User Behavior Clustering in Tencent Kankan: From Traditional Unsupervised Methods to N‑gram and action2vec

This article introduces Tencent Kankan's product landscape and explores various user clustering techniques—including classic unsupervised algorithms, N‑gram based sequence clustering, and deep‑learning driven action2vec—detailing their implementation steps, advantages, limitations, and practical insights for product optimization.

N-gramTencentaction2vec
0 likes · 12 min read
User Behavior Clustering in Tencent Kankan: From Traditional Unsupervised Methods to N‑gram and action2vec
DataFunTalk
DataFunTalk
Nov 2, 2021 · Artificial Intelligence

Personalized Recommendation and Advertising Algorithms for E‑commerce: Business Overview, Recall and Ranking Optimization, Multi‑Task Modeling, and Future Directions

This article presents a comprehensive technical overview of JD.com’s e‑commerce recommendation and advertising systems, covering business scenarios, recall optimizations (profile and similarity‑based), multi‑task ranking improvements, sample weighting, multi‑model ensembles, PID‑based CPC control, conversion‑delay modeling, and the achieved performance gains and future research plans.

CTR optimizatione-commercemachine learning
0 likes · 18 min read
Personalized Recommendation and Advertising Algorithms for E‑commerce: Business Overview, Recall and Ranking Optimization, Multi‑Task Modeling, and Future Directions
NetEase Smart Enterprise Tech+
NetEase Smart Enterprise Tech+
Nov 1, 2021 · Artificial Intelligence

How AI is Transforming Real-Time Audio Communication: Challenges and Solutions

This article explores the evolution of AI audio algorithms in real‑time communication, detailing current trends, technical hurdles such as computational complexity and data scarcity, and practical solutions including lightweight models, data augmentation, and hybrid AI‑traditional pipelines, illustrated with real‑world NetEase Cloud IM case studies.

AIVoice Activity Detectionaudio processing
0 likes · 18 min read
How AI is Transforming Real-Time Audio Communication: Challenges and Solutions
DataFunTalk
DataFunTalk
Oct 29, 2021 · Artificial Intelligence

Travel Intention‑Aware Out‑of‑Town POI Recommendation (TRAINOR) Framework

This article proposes TRAINOR, a travel‑intention‑aware out‑of‑town POI recommendation framework that tackles cold‑start and interest‑drift challenges by integrating graph neural networks for hometown preference, neural topic models for generic travel intentions, personalized intention inference, geographic modeling, and a preference‑transfer MLP, validated on real cross‑city check‑in data with superior recall performance.

Graph Neural NetworkPOI recommendationcold start
0 likes · 15 min read
Travel Intention‑Aware Out‑of‑Town POI Recommendation (TRAINOR) Framework
Alimama Tech
Alimama Tech
Oct 27, 2021 · Artificial Intelligence

Elastic Federated Learning Solution (EFLS): Architecture, Core Functions, and Technical Details

The Elastic Federated Learning Solution (EFLS) is Alibaba’s open‑source platform that enables privacy‑preserving vertical and horizontal federated learning for large‑scale sparse advertising, offering data‑intersection, high‑performance C++ training, a visual console, novel aggregation algorithms, and a roadmap toward multi‑party scaling and advanced encryption.

AdvertisingElastic Federated LearningFlink
0 likes · 16 min read
Elastic Federated Learning Solution (EFLS): Architecture, Core Functions, and Technical Details
DataFunTalk
DataFunTalk
Oct 20, 2021 · Artificial Intelligence

Building an Industry Chain Knowledge Graph: Theory, Architecture, and Key Methods

This article presents a comprehensive overview of constructing an industry‑chain knowledge graph for the financial sector, covering its theoretical background, architectural design, automated building pipeline, key NLP techniques, and practical applications such as visualization, IPO review, and investment analysis.

Financial TechnologyKnowledge GraphNLP
0 likes · 22 min read
Building an Industry Chain Knowledge Graph: Theory, Architecture, and Key Methods
MaGe Linux Operations
MaGe Linux Operations
Oct 19, 2021 · Artificial Intelligence

10 Exciting Python Projects to Boost Your AI and Automation Skills

Explore ten innovative Python project ideas—from voice‑controlled GUIs and AI betting bots to trading algorithms, virtual assistants, SSL auto‑renewal, facial recognition, contact‑tracing, file organization, and YouTube‑based career path generators—each designed to sharpen your programming, AI, and automation expertise.

AIPythonmachine learning
0 likes · 12 min read
10 Exciting Python Projects to Boost Your AI and Automation Skills
Baidu Intelligent Testing
Baidu Intelligent Testing
Oct 19, 2021 · Artificial Intelligence

Graph-Based Anti-Fraud: Gang Mining and Node Representation for Account Security

This article describes how Baidu's account security team leverages large‑scale graph technology and graph neural networks to detect and characterize black‑industry cheating gangs, presents a customized GraphSAGE link‑prediction model, and evaluates its superiority over MLP and GCN embeddings for downstream risk‑control tasks.

Graph Neural NetworksNode Representationanti-fraud
0 likes · 12 min read
Graph-Based Anti-Fraud: Gang Mining and Node Representation for Account Security
DataFunTalk
DataFunTalk
Oct 16, 2021 · Artificial Intelligence

Feature Extraction and Modeling of Voice and Text Data for Post‑Loan Management

This article presents practical experiences in post‑loan management, detailing how to extract descriptive and deep‑learning features from voice recordings and textual transcripts, apply traditional signal processing, keyword and TF‑IDF methods, and build CRNN and transformer models to predict repayment behavior.

AIdeep learningmachine learning
0 likes · 19 min read
Feature Extraction and Modeling of Voice and Text Data for Post‑Loan Management
DataFunTalk
DataFunTalk
Oct 15, 2021 · Artificial Intelligence

Risk Control and Operations for Existing Credit Customers: Models, Strategies, and Practices

This article examines how financial institutions can manage risk and improve operations for existing loan customers by analyzing client flow, regulatory impacts, accelerated deterioration, and layered segmentation, and by applying advanced models such as rule‑based alerts, B‑card scoring, LSTM, and survival analysis to enable timely risk detection and targeted cross‑selling.

Customer SegmentationOperationsfinancial modeling
0 likes · 20 min read
Risk Control and Operations for Existing Credit Customers: Models, Strategies, and Practices
21CTO
21CTO
Oct 12, 2021 · Artificial Intelligence

What Does the Metaverse Really Mean? Insights from Microsoft China’s CTO

In this interview, Microsoft China CTO Wei Qing explains the true meaning of the Metaverse, contrasts it with "virtual space," discusses the challenges of adopting emerging technologies like AI, machine learning, and digital twins, and highlights the broader impact of information as a public infrastructure.

Artificial IntelligenceMetaversedigital twin
0 likes · 16 min read
What Does the Metaverse Really Mean? Insights from Microsoft China’s CTO
Baidu Intelligent Testing
Baidu Intelligent Testing
Oct 12, 2021 · Artificial Intelligence

Full‑Link Consistency Testing for Click‑Through Rate Models in Large‑Scale Machine Learning

The article describes a comprehensive full‑link consistency testing framework for click‑through‑rate models, defining consistency issues, outlining data and logic consistency goals, and presenting a multi‑stage technical solution—including online data capture, offline data stitching, q‑value comparison, and reporting—to ensure model stability and performance.

DNNclick-through ratedata pipeline
0 likes · 18 min read
Full‑Link Consistency Testing for Click‑Through Rate Models in Large‑Scale Machine Learning
Architects' Tech Alliance
Architects' Tech Alliance
Oct 11, 2021 · Information Security

How AI‑Powered Firewalls Outperform Traditional NGFWs in Detecting Advanced Threats

The article examines why conventional next‑generation firewalls (NGFW) struggle with sophisticated, unknown attacks, and explains how Huawei’s AI firewall leverages cloud‑trained and on‑premise unsupervised learning models, dedicated hardware, and encrypted‑traffic analysis to automatically detect and mitigate advanced threats across the attack chain.

AI firewallNGFWcloud security
0 likes · 9 min read
How AI‑Powered Firewalls Outperform Traditional NGFWs in Detecting Advanced Threats
DataFunTalk
DataFunTalk
Oct 11, 2021 · Artificial Intelligence

Full-Chain Linkage Techniques for Alibaba Display Advertising: From Deep Learning to Set Selection

Facing diminishing deep‑learning and compute gains in Alibaba’s display‑ad pipeline, the speaker proposes a full‑chain linkage approach that combines vector‑based recall (PDM), entire‑space pre‑ranking (ESDM), and set‑selection learning‑to‑rank models (LDM, LBDM) to align upstream modules with downstream objectives, yielding 8‑10% revenue growth.

deep learningfull-chain optimizationmachine learning
0 likes · 28 min read
Full-Chain Linkage Techniques for Alibaba Display Advertising: From Deep Learning to Set Selection
iQIYI Technical Product Team
iQIYI Technical Product Team
Oct 9, 2021 · Big Data

Exploring iQIYI’s Unified Big Data + AI Architecture: Challenges, Solutions, and Future Directions

iQIYI’s unified big‑data + AI platform combines a hybrid‑cloud model, storage‑compute separation via its QBFS virtual file system, a reusable feature‑store and operator DAGs, and multi‑tenant YARN scheduling to overcome legacy Hive/Spark bottlenecks, accelerate large‑scale model training, improve data quality, and prepare for future real‑time, privacy‑preserving AI workloads.

AIDistributed ComputingPlatform Architecture
0 likes · 10 min read
Exploring iQIYI’s Unified Big Data + AI Architecture: Challenges, Solutions, and Future Directions
DataFunSummit
DataFunSummit
Oct 8, 2021 · Artificial Intelligence

Graph Computing for Financial Credit Risk Control and Anti‑Fraud: Architecture, Challenges, and Lessons Learned

This article examines how graph computing is applied to financial credit risk management and anti‑fraud, covering business background, key credit terminology, stakeholder roles, graph‑based fraud detection techniques, system architecture evolution across three development stages, practical requirements such as stability, timeliness, accuracy and controllability, and summarizes operational insights.

AIGraph Databasesanti-fraud
0 likes · 16 min read
Graph Computing for Financial Credit Risk Control and Anti‑Fraud: Architecture, Challenges, and Lessons Learned
Youku Technology
Youku Technology
Sep 29, 2021 · Artificial Intelligence

Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment

By constructing virtual mirror samples that occupy identical positions across source and target domains, the authors eliminate covariate shift while preserving distribution structure, enabling superior unsupervised domain adaptation that achieves state‑of‑the‑art performance on Office and VisDA benchmarks and improves real‑world lighting and gender‑recognition tasks.

AI researchDomain AdaptationSOTA
0 likes · 3 min read
Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment
Baidu Geek Talk
Baidu Geek Talk
Sep 29, 2021 · Artificial Intelligence

Graph-Based Anti-Fraud: Gang Mining and Node Representation Using Graph Neural Networks

To curb large‑scale, organized fraud on Baidu’s platform, the Account Security team built a scalable heterogeneous graph framework that links accounts, features, and devices, trains GraphSAGE‑based node embeddings via link‑prediction, and leverages these representations to uncover fraud gangs, boosting detection accuracy above 90% across billions of nodes.

Graph Neural Networksanti-fraudgraph mining
0 likes · 13 min read
Graph-Based Anti-Fraud: Gang Mining and Node Representation Using Graph Neural Networks
IT Architects Alliance
IT Architects Alliance
Sep 25, 2021 · Big Data

Top 10 Classic Data Mining Algorithms and Their Core Characteristics

This article introduces the ten classic data‑mining algorithms selected by IEEE ICDM—C4.5, k‑Means, SVM, Apriori, EM, PageRank, AdaBoost, k‑NN, Naive Bayes, and CART—explaining their main ideas, advantages, and typical applications for readers seeking a solid foundation in data analysis.

AlgorithmsClassificationClustering
0 likes · 8 min read
Top 10 Classic Data Mining Algorithms and Their Core Characteristics
Taobao Frontend Technology
Taobao Frontend Technology
Sep 23, 2021 · Artificial Intelligence

Build and Deploy ML Models with Pipcook 2.0 in Under 20 Seconds

Discover how Pipcook 2.0 dramatically speeds up machine‑learning workflows for web developers—cutting installation to under 20 seconds, enabling rapid model training, prediction, and deployment via concise JSON pipelines, with step‑by‑step guidance, code snippets, and practical examples for image and text classification.

AI PipelinePipcookTensorFlow.js
0 likes · 12 min read
Build and Deploy ML Models with Pipcook 2.0 in Under 20 Seconds
DataFunTalk
DataFunTalk
Sep 17, 2021 · Artificial Intelligence

Interpretable Machine Learning: Methods, Tools, and Financial Applications

This article introduces the importance of model interpretability, reviews common explanation techniques such as model‑specific and model‑agnostic methods, global and local analyses, partial dependence plots, ICE, ALE, and tools like LIME and SHAP, and demonstrates their practical use in anti‑fraud and device‑classification scenarios within a financial‑technology context.

LIMESHAPfinancial risk modeling
0 likes · 14 min read
Interpretable Machine Learning: Methods, Tools, and Financial Applications
Java Interview Crash Guide
Java Interview Crash Guide
Sep 16, 2021 · Artificial Intelligence

Inside Toutiao’s Recommendation Engine: Architecture, Features, and Safety

This article explains the architecture and key components of Toutiao’s recommendation system, covering system overview, content analysis, user tagging, evaluation methods, and content safety measures, and discusses practical implementation details such as feature engineering, model training, recall strategies, and online experimentation.

A/B testingcontent moderationfeature engineering
0 likes · 20 min read
Inside Toutiao’s Recommendation Engine: Architecture, Features, and Safety
DataFunSummit
DataFunSummit
Sep 15, 2021 · Information Security

Intelligent Risk Control in Live Streaming: Algorithm Architecture and Practice at Douyu

This article presents Douyu's intelligent risk‑control system for live streaming, detailing the security challenges, a multi‑layer algorithm architecture covering content, user‑behavior, gang and device risks, the evolution of models for spam detection, risk scoring, gang identification, sequence analysis, and device fingerprinting, and discusses practical solutions and interpretability techniques.

AIfraud detectionlive streaming
0 likes · 12 min read
Intelligent Risk Control in Live Streaming: Algorithm Architecture and Practice at Douyu
G7 EasyFlow Tech Circle
G7 EasyFlow Tech Circle
Sep 15, 2021 · Artificial Intelligence

Can Predictive Models Uncover Causal Effects? A Truck Risk Case Study

Using a road freight accident prediction example, the article warns that interpreting predictive model explanations as causal effects can be misleading, explains when such models may answer causal questions, demonstrates SHAP analysis on an XGBoost model, and recommends causal inference tools like ecoml for reliable effect estimation.

Causal InferenceSHAPXGBoost
0 likes · 10 min read
Can Predictive Models Uncover Causal Effects? A Truck Risk Case Study
Volcano Engine Developer Services
Volcano Engine Developer Services
Sep 14, 2021 · Artificial Intelligence

How ByteDance’s AI Lab is Revolutionizing Intelligent Speech for Content Creation

ByteDance’s AI‑Lab leader Dr Yin Xiang discusses how the company’s intelligent speech technologies—spanning voice synthesis, recognition, and multimodal interaction—have been integrated across its global content platforms since 2017, boosting productivity in short videos, audiobooks, education, and more.

AIByteDanceSpeech Synthesis
0 likes · 13 min read
How ByteDance’s AI Lab is Revolutionizing Intelligent Speech for Content Creation
Alibaba Cloud Native
Alibaba Cloud Native
Sep 13, 2021 · Artificial Intelligence

How Fluid + JindoRuntime Supercharged Autonomous Driving Model Training

This article details how the Fluid CNCF project combined with JindoRuntime was used to overcome storage‑compute separation bottlenecks in an autonomous‑driving machine‑learning platform, achieving up to 300% faster training, reduced OSS bandwidth pressure, and higher GPU utilization through distributed caching on Kubernetes.

FluidJindoRuntimeKubernetes
0 likes · 13 min read
How Fluid + JindoRuntime Supercharged Autonomous Driving Model Training
360 Smart Cloud
360 Smart Cloud
Sep 13, 2021 · Artificial Intelligence

Active Learning: Concepts, Workflow, Strategies, and Evaluation Metrics

Active learning addresses the high cost of labeling data by iteratively selecting the most informative unlabeled samples for annotation, thereby reducing labeling effort while achieving target model performance, and the article explains its fundamentals, relationship to supervised and semi‑supervised learning, common selection strategies, hybrid methods, and evaluation metrics.

Labeling Cost ReductionQuery by Committeeactive learning
0 likes · 7 min read
Active Learning: Concepts, Workflow, Strategies, and Evaluation Metrics
DataFunSummit
DataFunSummit
Sep 10, 2021 · Artificial Intelligence

Advances in Pre‑Ranking: The COLD System for Large‑Scale Advertising

This article reviews the evolution of coarse‑ranking in large‑scale ad systems, explains the two main technical routes—set selection and precise value estimation—introduces the Computing‑Power‑Cost‑Aware Online Lightweight Deep (COLD) pre‑ranking framework, and presents experimental results and future directions for deeper integration with fine‑ranking.

AdvertisingCOLDfeature selection
0 likes · 21 min read
Advances in Pre‑Ranking: The COLD System for Large‑Scale Advertising
HelloTech
HelloTech
Sep 10, 2021 · Artificial Intelligence

Algorithmic Practices in Haolo Carpool Service: Platform, Matching Engine, Transaction Governance, and Intelligent Marketing

The article details Haolo's end-to-end AI platform—built on Hadoop/Yarn with Spark ML, XGBoost and TensorFlow—and explains how its matching recommendation engine, transaction-ecosystem governance models, and intelligent uplift-based marketing system jointly boost carpool efficiency, safety, user retention, and ROI.

AI AlgorithmsRide-sharingTransaction Governance
0 likes · 19 min read
Algorithmic Practices in Haolo Carpool Service: Platform, Matching Engine, Transaction Governance, and Intelligent Marketing
DataFunTalk
DataFunTalk
Sep 9, 2021 · Artificial Intelligence

Evolution and Architecture of a Financial Risk Control System: From Monolith to Microservices and Commercialization

This article details the design, refactoring, performance optimization, reliability monitoring, and commercialization of a financial risk control system, covering rule abstraction, decision workflows, feature engineering, model integration, and the trade‑offs between latency and accuracy in large‑scale production environments.

decision enginefeature engineeringmachine learning
0 likes · 15 min read
Evolution and Architecture of a Financial Risk Control System: From Monolith to Microservices and Commercialization
Architects Research Society
Architects Research Society
Sep 6, 2021 · Artificial Intelligence

Comparison of Deep Learning Software Frameworks

This article provides an overview of deep learning as a branch of artificial intelligence and presents detailed tables comparing numerous deep‑learning software frameworks and libraries, covering their creators, release dates, licenses, platforms, languages, APIs, and support for parallelism and hardware acceleration.

Artificial IntelligenceFrameworksdeep learning
0 likes · 8 min read
Comparison of Deep Learning Software Frameworks
DataFunSummit
DataFunSummit
Sep 6, 2021 · Artificial Intelligence

Graph Neural Network‑Based Payment Fraud Detection at eBay

This article explains how eBay uses graph neural networks and a heterogeneous‑graph fraud detection framework (xFraud) to improve payment risk assessment, overcome the limitations of traditional machine‑learning models, and effectively identify both individual and organized fraud in a large‑scale e‑commerce environment.

Dynamic GrapheBayfraud detection
0 likes · 15 min read
Graph Neural Network‑Based Payment Fraud Detection at eBay
Laravel Tech Community
Laravel Tech Community
Sep 5, 2021 · Artificial Intelligence

Comprehensive Collection of Open Data Sources and Datasets for AI and Data Analysis

This article provides a curated list of publicly available data query websites, simple universal datasets, large-scale collections, and specialized datasets for machine learning, image classification, text classification, and recommendation systems, offering valuable resources for AI research and data-driven projects.

Artificial Intelligencebig datadatasets
0 likes · 7 min read
Comprehensive Collection of Open Data Sources and Datasets for AI and Data Analysis
DataFunSummit
DataFunSummit
Sep 5, 2021 · Artificial Intelligence

Causal Inference and Experiment Design in Kuaishou Live Streaming: Methods and Case Studies

This article explains how Kuaishou applies causal inference frameworks, such as Rubin's potential outcomes and Pearl's causal graphs, together with machine‑learning techniques like double‑machine learning, causal forests, and meta‑learners to evaluate product features, recommendation strategies, and user behavior under complex network effects in live streaming.

A/B testingCausal InferenceKuaishou
0 likes · 14 min read
Causal Inference and Experiment Design in Kuaishou Live Streaming: Methods and Case Studies
Xianyu Technology
Xianyu Technology
Sep 2, 2021 · Artificial Intelligence

Real-time Product Matching and User Profiling System for Personalized Item Selection

The paper introduces a product‑matching and user‑profiling system that builds themed collections by comparing new items to cold‑start samples using a two‑stage similarity pipeline—exact edit‑distance and pHash checks followed by doc2vec and OCR‑based embeddings—and then profiles sellers with RFM and clustering to highlight attributes like recent C2C sales volume, achieving about 80 % precision in a license‑plate bidding scenario while outlining future fusion improvements.

Product SelectionSimilarity Detectionmachine learning
0 likes · 7 min read
Real-time Product Matching and User Profiling System for Personalized Item Selection
Python Programming Learning Circle
Python Programming Learning Circle
Aug 30, 2021 · Artificial Intelligence

DeepDebug: Transformer‑Based Automatic Debugging Using Large Pretrained Models

The paper presents DeepDebug, a transformer‑based system that leverages large pretrained models and extensive synthetic and real‑world data to automatically localize and fix bugs in Python code, achieving significant improvements in patch generation success rates and reduction of false positives on benchmarks such as QuixBugs.

Transformerautomatic debuggingmachine learning
0 likes · 12 min read
DeepDebug: Transformer‑Based Automatic Debugging Using Large Pretrained Models
DataFunSummit
DataFunSummit
Aug 29, 2021 · Artificial Intelligence

Zhihu Recommendation Page Ranking: Architecture, Feature Design, Model Evolution, and Practical Insights

This article presents a comprehensive overview of Zhihu's recommendation page ranking system, detailing the request flow, ranking evolution from time‑based to deep‑learning models, feature engineering strategies, model architectures such as DNN, DeepFM, DIN, multi‑task learning, and lessons learned for production deployment.

CTRZhihufeature engineering
0 likes · 12 min read
Zhihu Recommendation Page Ranking: Architecture, Feature Design, Model Evolution, and Practical Insights
dbaplus Community
dbaplus Community
Aug 28, 2021 · Artificial Intelligence

Is AI Really Intelligent? Exploring Machine Learning, Neural Networks & Deep Learning

The article demystifies AI by explaining that current artificial intelligence is merely automated computation, then walks through fundamental machine‑learning concepts such as exhaustive search, linear regression, neural‑network neurons, activation functions, network structures, training calculations, and concludes with a Python implementation of a three‑layer neural network.

AIPythondeep learning
0 likes · 15 min read
Is AI Really Intelligent? Exploring Machine Learning, Neural Networks & Deep Learning
DataFunTalk
DataFunTalk
Aug 27, 2021 · Artificial Intelligence

Hybrid Bandit and Visual-aware Ranking Models for Advertising Creative Selection and Dynamic Optimization

The article presents a hybrid bandit framework combined with a visual‑aware ranking model to efficiently select and dynamically optimize advertising creatives, addressing cold‑start challenges, element‑level personalization, and production‑parameter search, and validates the approach with extensive offline and online experiments.

Bandit AlgorithmsCTR predictioncreative optimization
0 likes · 15 min read
Hybrid Bandit and Visual-aware Ranking Models for Advertising Creative Selection and Dynamic Optimization
Ctrip Technology
Ctrip Technology
Aug 26, 2021 · Artificial Intelligence

Applying Snorkel Weak Supervision to Automate Event Summaries in Ctrip Customer Service

The article explains how Ctrip’s hotel customer‑service team uses the Snorkel weak‑supervision framework to generate large‑scale labeled data for training models that automatically produce structured event summaries, detailing the workflow, labeling functions, generative and discriminative model training, and performance improvements.

Labeling FunctionsNLPSnorkel
0 likes · 14 min read
Applying Snorkel Weak Supervision to Automate Event Summaries in Ctrip Customer Service
DataFunSummit
DataFunSummit
Aug 20, 2021 · Artificial Intelligence

Data Privacy and Differential Privacy Techniques in Machine Learning

This article reviews recent data privacy challenges in machine learning, explains the distinction between privacy and security, presents classic attacks and anonymization methods such as K‑anonymity, L‑diversity and T‑closeness, and details differential privacy techniques and their impact on model performance.

Differential Privacyanonymizationinformation security
0 likes · 17 min read
Data Privacy and Differential Privacy Techniques in Machine Learning
DataFunTalk
DataFunTalk
Aug 16, 2021 · Artificial Intelligence

Intelligent Risk Control in Live Streaming: Architecture, Challenges, and Model Evolution at Douyu

This article presents Douyu's intelligent risk‑control system for live streaming, detailing the operational, activity, traffic, account, transaction and content safety challenges, the multi‑layer algorithm architecture, and the evolution of models for spam detection, risk scoring, gang identification, behavior sequencing, device fingerprinting, and interpretability.

Artificial Intelligencefraud detectionlive streaming
0 likes · 13 min read
Intelligent Risk Control in Live Streaming: Architecture, Challenges, and Model Evolution at Douyu
Kuaishou Tech
Kuaishou Tech
Aug 13, 2021 · Industry Insights

How Kuaishou Uses Causal Inference to Optimize Live‑Streaming Experiments

This article analyzes Kuaishou's live‑streaming ecosystem, detailing causal‑inference frameworks, observational and experimental techniques such as DID, double machine learning, causal forests, uplift meta‑learners, and complex experiment designs like dual‑sided and time‑slice rotation to evaluate product and recommendation strategies.

AB TestingCausal InferenceKuaishou
0 likes · 17 min read
How Kuaishou Uses Causal Inference to Optimize Live‑Streaming Experiments
Beike Product & Technology
Beike Product & Technology
Aug 13, 2021 · Artificial Intelligence

AI-Powered Intelligent Testing Platform for Frontend UI Quality Assurance

The article describes how an AI-driven testing platform combines computer‑vision, OCR, and machine‑learning techniques to automatically detect frontend UI and backend‑related quality issues in mobile apps, outlines its architecture, core capabilities, deployment workflow, and reports successful real‑world deployments and future plans.

AI testingcomputer visionfrontend quality
0 likes · 11 min read
AI-Powered Intelligent Testing Platform for Frontend UI Quality Assurance
Qingyun Technology Community
Qingyun Technology Community
Aug 12, 2021 · Artificial Intelligence

How Kubernetes Powers Scalable AI: Building an End‑to‑End Machine Learning Platform

This article explores how Kubernetes, enhanced by KubeSphere and serverless technologies, enables efficient AI workloads through GPU virtualization, multi‑cluster management, secure data sandboxes, automated testing, and scalable storage, illustrating a complete lifecycle from data ingestion to model inference.

AIGPU virtualizationKubeSphere
0 likes · 20 min read
How Kubernetes Powers Scalable AI: Building an End‑to‑End Machine Learning Platform
DataFunTalk
DataFunTalk
Aug 12, 2021 · Artificial Intelligence

Causal Inference and Experiment Design in Kuaishou Live Streaming

This article presents Dr. Jin Yaran’s comprehensive overview of causal inference challenges, frameworks, and practical case studies—including DID, double machine learning, causal forests, and meta‑learners—applied to Kuaishou’s live‑streaming product, and discusses complex experimental designs such as bilateral and time‑slice experiments.

A/B testingCausal InferenceData Analysis
0 likes · 15 min read
Causal Inference and Experiment Design in Kuaishou Live Streaming
DataFunSummit
DataFunSummit
Aug 12, 2021 · Artificial Intelligence

Algorithmic Practices in Hulu’s Video Advertising Platform

This article explains how Hulu leverages machine learning and AI techniques such as ad targeting, inventory prediction, flow matching, conversion rate optimization, causal inference, and shared‑account detection to improve the efficiency, effectiveness, and revenue of its video advertising ecosystem.

AIAd TargetingAdvertising
0 likes · 14 min read
Algorithmic Practices in Hulu’s Video Advertising Platform
Meituan Technology Team
Meituan Technology Team
Aug 12, 2021 · Artificial Intelligence

Adaptive Information Transfer Multi-task (AITM) Framework for Sequential User Conversion Modeling in Targeted Display Advertising

The Adaptive Information Transfer Multi‑task (AITM) framework integrates multi‑task learning with an attention‑based information‑transfer module to jointly model the sequential conversion chain in targeted display ads, mitigating class imbalance and boosting end‑to‑end user acquisition rates, as demonstrated by offline and online experiments.

AITMSequential Modelingconversion rate
0 likes · 16 min read
Adaptive Information Transfer Multi-task (AITM) Framework for Sequential User Conversion Modeling in Targeted Display Advertising
DataFunTalk
DataFunTalk
Aug 9, 2021 · Artificial Intelligence

Calibration Techniques for User Behavior Prediction in Online Advertising: Background, Algorithm Evolution, and Engineering Practice

This article introduces the concept of calibration in trustworthy machine learning, explains why accurate probability estimates are crucial for online advertising, reviews related research and evaluation metrics, and details the evolution of calibration algorithms such as Smoothed Isotonic Regression, Bayes‑SIR, real‑time optimizations, and post‑click conversion models, concluding with engineering deployment and future directions.

Online Advertisingalgorithm optimizationcalibration
0 likes · 18 min read
Calibration Techniques for User Behavior Prediction in Online Advertising: Background, Algorithm Evolution, and Engineering Practice
DataFunSummit
DataFunSummit
Aug 8, 2021 · Artificial Intelligence

Diversity as a Means, Not an End, in Recommendation Systems

The article argues that diversity in recommendation systems should be treated as a means rather than an ultimate goal, explains why it is hard to quantify, suggests using real performance metrics such as click‑through rate and dwell time, and offers practical strategies to improve listwise ranking.

diversitylistwisemachine learning
0 likes · 7 min read
Diversity as a Means, Not an End, in Recommendation Systems
DataFunSummit
DataFunSummit
Aug 7, 2021 · Artificial Intelligence

Long-Term User Interest Modeling for Click-Through Rate Prediction in Alibaba's Advertising System

This article describes how Alibaba's advertising team tackled the challenges of modeling long‑term user interests for CTR prediction by co‑designing incremental computation services, introducing memory‑network‑based models (MIMN and HPMN), and achieving significant offline and online performance gains.

CTR predictionLong-Term InterestOnline Advertising
0 likes · 17 min read
Long-Term User Interest Modeling for Click-Through Rate Prediction in Alibaba's Advertising System
DataFunSummit
DataFunSummit
Aug 6, 2021 · Artificial Intelligence

Personalized Advertising Ranking and Intelligent Bidding in iQIYI Effect Advertising

This article presents iQIYI's effect advertising system, detailing its dual-engine resource layout, oCPX billing model, algorithmic challenges of high‑dimensional sparse conversion data, the multi‑stage personalized recommendation pipeline, eCPM‑based ranking, online training/inference workflow, and intelligent bidding strategies that balance cost control and traffic quality.

Advertisingclick-through rateconversion estimation
0 likes · 11 min read
Personalized Advertising Ranking and Intelligent Bidding in iQIYI Effect Advertising
DataFunSummit
DataFunSummit
Aug 5, 2021 · Artificial Intelligence

Embedding‑Based Item‑to‑Item Similarity Recommendation for Homestay Platforms

This article describes how Tujia applied embedding techniques, inspired by word2vec and skip‑gram models, to build item‑to‑item similarity vectors for homestay recommendations, detailing the background challenges, the embedding solution, training methodology, evaluation results, practical improvements, and future development plans.

AB TestingEmbeddinghomestay
0 likes · 13 min read
Embedding‑Based Item‑to‑Item Similarity Recommendation for Homestay Platforms
Tencent Architect
Tencent Architect
Aug 4, 2021 · Artificial Intelligence

How We Accelerated Feature Hashing for Ad Ranking on GPUs

This article explains how Tencent's Light platform reduced the massive overhead of feature hashing in ad‑ranking by moving integer‑to‑string conversion and hash computation to the GPU, introducing custom contiguous string tensors, and achieving up to 12× speed‑up on V100 GPUs.

GPU optimizationTensorFlowad ranking
0 likes · 14 min read
How We Accelerated Feature Hashing for Ad Ranking on GPUs
ByteFE
ByteFE
Aug 2, 2021 · Artificial Intelligence

An Overview of Artificial Intelligence, Machine Learning, and Neural Networks

This article provides a beginner‑friendly overview of artificial intelligence, its relationship with machine learning, the four major learning paradigms—supervised, unsupervised, semi‑supervised and reinforcement learning—along with a historical sketch of neural networks, their training workflow, loss functions, back‑propagation, and parameter‑update mechanisms, while also containing a brief recruitment notice.

Artificial IntelligenceUnsupervised Learningdeep learning
0 likes · 18 min read
An Overview of Artificial Intelligence, Machine Learning, and Neural Networks
DataFunSummit
DataFunSummit
Jul 31, 2021 · Artificial Intelligence

Credit Risk Strategies: From Rule‑Based Scoring to Machine Learning Models

This article presents a comprehensive overview of credit risk control strategies, covering industry background, traditional scoring‑card development, data integration, feature engineering, model evaluation, rate and limit optimization, and advanced machine‑learning approaches for loan underwriting.

Financial AnalyticsRisk ModelingScoring
0 likes · 11 min read
Credit Risk Strategies: From Rule‑Based Scoring to Machine Learning Models
MaGe Linux Operations
MaGe Linux Operations
Jul 29, 2021 · Artificial Intelligence

Unlock Powerful Face Recognition with Python’s face_recognition Library

This article introduces the open‑source Python library face_recognition, explains how to install it, locate and extract faces, generate 128‑dimensional embeddings, compare faces, detect facial landmarks, apply virtual makeup, and build a simple custom face‑recognition application with complete code examples and visual results.

computer visionface recognitionfacial landmarks
0 likes · 11 min read
Unlock Powerful Face Recognition with Python’s face_recognition Library
DataFunSummit
DataFunSummit
Jul 24, 2021 · Artificial Intelligence

Alibaba 1688 User Growth, Full‑Chain Growth System, and Deep‑Learning Applications in Search and Promotion

This article presents a comprehensive overview of Alibaba 1688's user‑growth strategy, detailing lifecycle segmentation, budget‑constrained installation optimization, intelligent red‑packet allocation, smart push mechanisms, information‑flow advertising, and the deep‑learning‑driven search pipeline that together power the platform's growth engine.

Search Optimizationbudget optimizatione-commerce
0 likes · 20 min read
Alibaba 1688 User Growth, Full‑Chain Growth System, and Deep‑Learning Applications in Search and Promotion
DataFunTalk
DataFunTalk
Jul 23, 2021 · Artificial Intelligence

Ad Fraud Detection and Risk Control Practices at Alibaba Mama

This article explains Alibaba Mama's ad fraud risk control workflow, defines invalid traffic types, describes perception, insight, and disposal mechanisms, and outlines the AI‑driven detection models, evaluation metrics, and future research directions for large‑scale advertising security.

Ad FraudAlibabaanomaly detection
0 likes · 14 min read
Ad Fraud Detection and Risk Control Practices at Alibaba Mama
iQIYI Technical Product Team
iQIYI Technical Product Team
Jul 23, 2021 · Artificial Intelligence

XGBoost Serving: An Open‑Source High‑Performance Inference System for GBDT and GBDT+FM Models

XGBoost Serving is an open‑source, high‑performance inference system built on TensorFlow Serving that adds dedicated servables for pure GBDT, GBDT+FM binary‑classification, and GBDT+FM multi‑classification models, providing automatic version lifecycle management, GRPC/HTTP APIs, and up to 50 % latency reduction, now available on GitHub after successful deployment in iQIYI’s recommendation platform.

GBDTServing ArchitectureXGBoost Serving
0 likes · 12 min read
XGBoost Serving: An Open‑Source High‑Performance Inference System for GBDT and GBDT+FM Models
Sohu Tech Products
Sohu Tech Products
Jul 21, 2021 · Artificial Intelligence

Kaggle Jane Street Market Prediction Competition Summary and Model Insights

This article summarizes the author's participation in the Kaggle Jane Street Market Prediction competition, detailing the anonymous feature dataset, utility‑score metric, data preprocessing, the combined AE‑MLP and XGBoost modeling approach, threshold tuning, experimental findings, and references for further study.

AutoencoderKaggleMLP
0 likes · 8 min read
Kaggle Jane Street Market Prediction Competition Summary and Model Insights
Efficient Ops
Efficient Ops
Jul 17, 2021 · Databases

How AutoTiKV’s Machine Learning Optimizes Beaver Search Engine Performance

This article describes how the Beaver search engine’s many performance‑related configuration parameters can be automatically tuned using machine‑learning techniques from OtterTune and AutoTiKV, detailing the background research, Gaussian Process regression model, Bayesian optimization process, implementation steps, test results, and future improvements.

Bayesian optimizationBeaverGaussian Process
0 likes · 23 min read
How AutoTiKV’s Machine Learning Optimizes Beaver Search Engine Performance
Test Development Learning Exchange
Test Development Learning Exchange
Jul 17, 2021 · Artificial Intelligence

Face Recognition with OpenCV and Python

This tutorial explains the concept of facial recognition, describes how it works, and provides step‑by‑step instructions and code examples for implementing face detection and identification using OpenCV and Python, including installation, basic image handling, and a complete sample script.

OpenCVPythoncomputer vision
0 likes · 4 min read
Face Recognition with OpenCV and Python
Python Programming Learning Circle
Python Programming Learning Circle
Jul 16, 2021 · Artificial Intelligence

Using the face_recognition Python Library for Face Detection, Landmark Identification, and Simple Applications

This article demonstrates how to install the Python face_recognition library, locate faces in images, crop and save them, encode faces into 128‑dimensional vectors, compare faces, detect facial landmarks, apply virtual makeup, and assemble these steps into a simple custom face‑recognition application.

Face Detectionface_recognitionfacial landmarks
0 likes · 10 min read
Using the face_recognition Python Library for Face Detection, Landmark Identification, and Simple Applications
DataFunTalk
DataFunTalk
Jul 15, 2021 · Artificial Intelligence

Graph Neural Network‑Based Payment Fraud Detection at eBay

The article explains how eBay protects its global payment system using a graph‑neural‑network driven risk management framework called xFraud, which combines heterogeneous graph sampling, node‑type encoding, attention mechanisms and dynamic‑graph extensions to detect and explain both individual and organized fraud patterns in real‑time.

Graph Neural NetworksRisk ManagementeBay
0 likes · 13 min read
Graph Neural Network‑Based Payment Fraud Detection at eBay
MaGe Linux Operations
MaGe Linux Operations
Jul 14, 2021 · Cloud Computing

What Is Intelligent Edge Computing and Why It Matters Today

Intelligent edge computing extends traditional edge architectures by embedding AI-driven data analysis and machine learning directly at the network edge, enabling faster, low‑latency decisions for use cases like smart cameras and autonomous vehicles, and is rapidly becoming a core strategy for modern enterprises.

IoTedge computingintelligent edge
0 likes · 6 min read
What Is Intelligent Edge Computing and Why It Matters Today
Meituan Technology Team
Meituan Technology Team
Jul 8, 2021 · Artificial Intelligence

Multi-Business Ranking Modeling in Meituan Search

Meituan Search tackles the multi‑business ranking challenge by introducing a quota‑allocation model (MQM) and a series of precise ranking models (MBN) that progressively incorporate sub‑networks, multi‑task learning and transformer‑based behavior sequences, delivering consistent CTR and purchase‑rate gains across food, hotel, travel and other services while outlining future work on feature utilization, sample‑imbalance mitigation and multi‑objective optimization.

Meituanmachine learningmulti-task learning
0 likes · 15 min read
Multi-Business Ranking Modeling in Meituan Search
Taobao Frontend Technology
Taobao Frontend Technology
Jul 8, 2021 · Artificial Intelligence

How to Build Machine Learning Apps Directly in the Browser with JavaScript

This article explains a four‑level methodology for choosing JavaScript‑based machine‑learning tools, demonstrates practical code examples ranging from NLP with nlp.js to deep‑learning with TensorFlow.js, traditional ML with mljs, and statistical computing with stdlib, and shows how to run them entirely in the browser.

JavaScriptTensorFlow.jsfrontend AI
0 likes · 11 min read
How to Build Machine Learning Apps Directly in the Browser with JavaScript
Tencent Advertising Technology
Tencent Advertising Technology
Jul 7, 2021 · Artificial Intelligence

Multimedia AI in Advertising and Experimental Design for Two-Sided Markets: Key Insights from Tencent's Algorithm Competition

This article summarizes key insights from a Tencent technical live stream, detailing how artificial intelligence enhances advertising efficiency and recommendation accuracy, outlines future AI research and application trends, discusses essential hiring criteria for algorithm engineers, and introduces experimental design challenges in two-sided market platforms.

Advertising TechnologyAlgorithm Engineeringmachine learning
0 likes · 5 min read
Multimedia AI in Advertising and Experimental Design for Two-Sided Markets: Key Insights from Tencent's Algorithm Competition
Programmer DD
Programmer DD
Jul 6, 2021 · Artificial Intelligence

Does GitHub Copilot Really Copy-Paste Code? An In-Depth AI Analysis

This article examines GitHub Copilot’s AI-driven code suggestions, its underlying Codex model, multilingual support, performance on LeetCode challenges, and the controversy over potential code copying, presenting a detailed classification of observed cases, statistical analysis, and conclusions about the rarity and nature of actual code recitation.

AI code generationGitHub Copilotcode plagiarism
0 likes · 8 min read
Does GitHub Copilot Really Copy-Paste Code? An In-Depth AI Analysis
Xianyu Technology
Xianyu Technology
Jul 1, 2021 · Artificial Intelligence

Improving Search Relevance in Xianyu: System Design and Model Implementation

The paper describes Xianyu’s new relevance‑matching pipeline—integrating basic, text‑matching, semantic (BERT‑based dual‑tower), multimodal, and click‑graph features and fusing them with a GBDT model—which boosts search DCG@10 by 6.5 %, query satisfaction by 24 % and click interaction by over 20 % while outlining future enhancements for finer attribute matching and richer structured data.

Multimodale-commercefeature engineering
0 likes · 13 min read
Improving Search Relevance in Xianyu: System Design and Model Implementation
DataFunTalk
DataFunTalk
Jun 26, 2021 · Artificial Intelligence

Algorithmic Practices in Haola Ride‑Sharing: Platform Infrastructure, Matching Recommendation Engine, Transaction Governance, and Intelligent Marketing

This article presents a comprehensive overview of Haola's ride‑sharing algorithm ecosystem, covering the machine‑learning platform foundation, the architecture and evolution of the matching recommendation engine, the transaction‑ecosystem governance models, and the intelligent marketing uplift framework, highlighting technical challenges, solutions, and performance gains.

AI AlgorithmsMarketing OptimizationRide-sharing
0 likes · 21 min read
Algorithmic Practices in Haola Ride‑Sharing: Platform Infrastructure, Matching Recommendation Engine, Transaction Governance, and Intelligent Marketing
Meituan Technology Team
Meituan Technology Team
Jun 24, 2021 · Artificial Intelligence

Construction and Application of Meituan's Common‑Sense Concept Knowledge Graph

The paper describes Meituan’s common‑sense concept knowledge graph, detailing a multi‑stage construction pipeline—concept, hierarchy, attribute, bridging, and POI/SPU linking—using BERT, XGBoost, and graph neural networks, and demonstrates its deployment in category‑word enrichment, search suggestions, and medical‑beauty tagging, achieving over two million concepts, three million relations, and roughly 90 % accuracy.

Knowledge GraphNatural Language Processingconcept mining
0 likes · 26 min read
Construction and Application of Meituan's Common‑Sense Concept Knowledge Graph
DataFunTalk
DataFunTalk
Jun 23, 2021 · Artificial Intelligence

Graph Algorithm Practices for Anti‑Cheat on the Douyu Live‑Streaming Platform

This article explains how Douyu uses graph‑based algorithms to detect and mitigate fraudulent streaming traffic, covering the platform's risk‑control scenarios, the overall graph architecture, its evolution, modeling workflow, practical case studies, and the resulting improvements in detection accuracy and interpretability.

Graph Algorithmsanti-cheatgraph embedding
0 likes · 16 min read
Graph Algorithm Practices for Anti‑Cheat on the Douyu Live‑Streaming Platform
Big Data Technology Architecture
Big Data Technology Architecture
Jun 22, 2021 · Databases

Hopsworks Feature Store: Transparent Dual‑Storage System for Online and Offline Machine Learning Features

This article explains how Hopsworks’ feature store unifies online low‑latency and offline high‑throughput storage using a dual‑system architecture built on RonDB, detailing its API, metadata handling, ingestion pipeline, benchmarks, and how it simplifies production machine‑learning feature access.

Feature StoreRonDBbenchmark
0 likes · 17 min read
Hopsworks Feature Store: Transparent Dual‑Storage System for Online and Offline Machine Learning Features