BestHub
Sign in
Tagged articles
1881 articles
Page 14 of 19
Alibaba Terminal Technology
Alibaba Terminal Technology
Jan 3, 2020 · Frontend Development

How Frontend Code Was Auto-Generated for Alibaba’s Double‑11 Event

This article explains how Alibaba's Frontend Intelligent Project automatically generated 79.34% of the Double‑11 page code by recognizing business modules from visual drafts using data‑augmented samples, traditional multi‑class machine‑learning models, and a pipeline of preprocessing, model training, deployment, and OOD handling.

FrontendModel Deploymentautomation
0 likes · 15 min read
How Frontend Code Was Auto-Generated for Alibaba’s Double‑11 Event
DataFunTalk
DataFunTalk
Dec 30, 2019 · Artificial Intelligence

Technical Trends in Recommendation Systems: From Retrieval to Re‑ranking

This article surveys recent advances in recommendation system technology, covering the evolution from a two‑stage recall‑ranking pipeline to a four‑stage architecture, and detailing emerging trends in model‑based recall, user‑behavior sequence modeling, knowledge‑graph integration, graph neural networks, advanced ranking models, multi‑objective optimization, multimodal fusion, and listwise re‑ranking.

graph neural networksinformation retrievalknowledge graph
0 likes · 45 min read
Technical Trends in Recommendation Systems: From Retrieval to Re‑ranking
Tencent Cloud Developer
Tencent Cloud Developer
Dec 26, 2019 · Artificial Intelligence

WeChat Scan-to-Identify (Scan Object) Feature: Overview, Technical Architecture, Data Construction, and Algorithmic Advances

WeChat’s iOS Scan‑to‑Identify feature lets users point a camera at any product or scene to instantly retrieve related e‑commerce, encyclopedia or news content, using a four‑pipeline architecture that builds massive annotated and deduplicated databases, advanced RetinaNet‑based detection, multi‑task metric learning, and scalable training, deployment and scheduling platforms, with plans to extend into domains like facial, vehicle and plant recognition.

AIComputer VisionWeChat
0 likes · 34 min read
WeChat Scan-to-Identify (Scan Object) Feature: Overview, Technical Architecture, Data Construction, and Algorithmic Advances
DataFunTalk
DataFunTalk
Dec 20, 2019 · Artificial Intelligence

AutoCross: Automatic Feature Crossing for Tabular Data in Real-World Applications

The article presents AutoCross, a system that automatically generates and selects high‑order feature crossings for tabular data using multi‑granularity discretization, beam search, field‑wise logistic regression and successive mini‑batch gradient descent, achieving superior accuracy and efficiency in large‑scale recommendation scenarios.

AutoCrossBeam Searchautomatic feature engineering
0 likes · 10 min read
AutoCross: Automatic Feature Crossing for Tabular Data in Real-World Applications
Bitu Technology
Bitu Technology
Dec 20, 2019 · Big Data

Building a Model‑Driven Data Platform at Tubi: From Data Warehouse to Automated Machine Learning

The article describes how Tubi, North America’s largest free‑streaming service, built a model‑driven data platform using a high‑quality data warehouse, DBT‑based transformations, Kubernetes‑hosted JupyterHub, low‑latency Scala/Akka services, and automated machine‑learning pipelines to accelerate experimentation and decision‑making.

Data Platformdata engineeringdbt
0 likes · 11 min read
Building a Model‑Driven Data Platform at Tubi: From Data Warehouse to Automated Machine Learning
360 Quality & Efficiency
360 Quality & Efficiency
Dec 20, 2019 · Artificial Intelligence

Automated APK Test Script Recommendation: Data Processing and Model Training Pipeline

This article describes a complete pipeline for recommending automated test scripts for APK releases, covering CSV data preprocessing, feature encoding, tokenization with pkuseg and jieba, and training various machine‑learning models such as LDA, word2vec, XGBoost, deep neural networks, and multi‑label classifiers to predict script execution order.

APK testingDeep LearningModel Training
0 likes · 14 min read
Automated APK Test Script Recommendation: Data Processing and Model Training Pipeline
Tencent Cloud Developer
Tencent Cloud Developer
Dec 19, 2019 · Artificial Intelligence

AI-Powered Content Moderation: How Platforms Combat Harmful Content with AI

AI-powered moderation tools now scan text, images, live streams, and short videos, using techniques like TextCNN, Word2Vec, attention‑based classifiers, multi‑label sampling, and real‑time audio analysis to detect pornographic and harmful content, while emphasizing continual model updates and sample collection for both small and large platforms.

AI detectionComputer VisionTencent Security
0 likes · 12 min read
AI-Powered Content Moderation: How Platforms Combat Harmful Content with AI
Alibaba Cloud Developer
Alibaba Cloud Developer
Dec 17, 2019 · Artificial Intelligence

How Alibaba Boosted Short‑Video Engagement with Advanced Recommendation Algorithms

This article explains the rapid growth of short‑video on Taobao, describes the video feature framework, details the RankI2V and RankV2V recall methods, outlines coarse and fine ranking models, and presents real‑time interest and business strategies that significantly improved click‑through rates and viewing time.

Alibabamachine learningranking algorithms
0 likes · 19 min read
How Alibaba Boosted Short‑Video Engagement with Advanced Recommendation Algorithms
58 Tech
58 Tech
Dec 16, 2019 · Artificial Intelligence

Data Intelligence in the Used‑Car Business: User Traffic Prediction and Identification (Part 1)

This article details how the 58 Group applied data‑driven methods—user segmentation, interest description, clustering, and predictive modeling—to forecast and identify traffic in the used‑car scenario, illustrating the end‑to‑end pipeline, experimental results, and practical impact on downstream business processes.

Data IntelligenceTraffic PredictionUser Segmentation
0 likes · 19 min read
Data Intelligence in the Used‑Car Business: User Traffic Prediction and Identification (Part 1)
DataFunTalk
DataFunTalk
Dec 13, 2019 · Artificial Intelligence

Fundamentals of Deep Learning: Neural Networks, CNNs, RNNs, LSTM, and GRU

This article provides a comprehensive overview of deep learning fundamentals, covering neural network basics, forward and backward feedback architectures, key models such as MLP, CNN, RNN, LSTM and GRU, training techniques like gradient descent, learning rate schedules, momentum, weight decay, and batch normalization.

CNNDeep LearningGRU
0 likes · 14 min read
Fundamentals of Deep Learning: Neural Networks, CNNs, RNNs, LSTM, and GRU
Alibaba Cloud Developer
Alibaba Cloud Developer
Dec 12, 2019 · Artificial Intelligence

How Multi‑Layer Multi‑Frequency Streaming Training Boosts Real‑Time CTR/CVR Prediction

This article details a novel Multi‑Layer Multi‑Frequency streaming training approach that enables minute‑level real‑time updates of massive CTR/CVR models by partitioning weights into freezing embeddings, changing embeddings, and changing weights, demonstrating significant offline and online AUC gains, especially during high‑traffic events like Double 11.

CTR predictione‑commercemachine learning
0 likes · 18 min read
How Multi‑Layer Multi‑Frequency Streaming Training Boosts Real‑Time CTR/CVR Prediction
DataFunTalk
DataFunTalk
Dec 9, 2019 · Artificial Intelligence

Automatic Construction of Knowledge Graphs: Methods, Challenges, and Applications

This article reviews the principles, techniques, and challenges of automatically building knowledge graphs, covering logical modeling, latent‑space analysis, human‑computer interaction, ontology support, and practical pipelines, and illustrates their use in network behavior analysis, intelligent Q&A, and recommendation systems.

Artificial IntelligenceHuman-Computer InteractionOntology
0 likes · 17 min read
Automatic Construction of Knowledge Graphs: Methods, Challenges, and Applications
Taobao Frontend Technology
Taobao Frontend Technology
Dec 5, 2019 · Frontend Development

From UI Sketch to Code: Frontend Intelligence Generates 79% of Double‑11 Modules

This article explains how Alibaba's Front‑End Intelligent project automatically converts UI design images into production‑ready code, covering layout analysis, background and foreground processing, a fusion of traditional image algorithms with deep‑learning detection, GAN‑based complex‑background extraction, experimental results and real‑world deployment.

GANImage ProcessingLayout Analysis
0 likes · 21 min read
From UI Sketch to Code: Frontend Intelligence Generates 79% of Double‑11 Modules
Alibaba Terminal Technology
Alibaba Terminal Technology
Dec 5, 2019 · Frontend Development

How Frontend Code Is Automatically Generated: Inside Alibaba’s AI‑Powered D2C Pipeline

This article explains Alibaba's front‑end intelligent project that automatically generated 79.34% of the Double‑11 UI code, detailing why images are used as input, the layered image‑processing pipeline, background and foreground analysis, traditional versus deep‑learning methods, fusion techniques, evaluation results, and real‑world deployments.

FrontendImage ProcessingLayout Analysis
0 likes · 20 min read
How Frontend Code Is Automatically Generated: Inside Alibaba’s AI‑Powered D2C Pipeline
Tencent Cloud Developer
Tencent Cloud Developer
Dec 3, 2019 · Artificial Intelligence

Feature Engineering Practices for Short‑Video Recommendation Systems

Effective short‑video recommendation relies on meticulous feature engineering that transforms raw signals—numerical counts, categorical IDs, content and user embeddings, context and session data—through bucketization, scaling, crossing, and smoothing, then selects and evaluates them via filtering, wrapping, regularization, and importance analysis to mitigate business biases and improve multi‑objective ranking performance.

Embeddingbias mitigationdata preprocessing
0 likes · 32 min read
Feature Engineering Practices for Short‑Video Recommendation Systems
58 Tech
58 Tech
Nov 29, 2019 · Artificial Intelligence

Ranking Strategy Optimization Practices for Commercial Traffic at 58.com

This article details the end‑to‑end optimization of 58.com’s commercial traffic ranking system, covering data‑flow upgrades, advanced feature engineering, real‑time and multi‑task model improvements, and a multi‑factor ranking mechanism, while sharing practical results and future directions.

Real-time Data Pipelinefeature engineeringmachine learning
0 likes · 17 min read
Ranking Strategy Optimization Practices for Commercial Traffic at 58.com
Amap Tech
Amap Tech
Nov 29, 2019 · Artificial Intelligence

Advancements in Query Analysis for Map Search: City Analysis, Where‑What Segmentation, and Path Planning

The article details Amap’s upgraded map‑search query analysis, introducing a two‑stage city‑identification system, enhanced where‑what segmentation with CRF and GBDT models, a three‑stage path‑planning pipeline, and outlines future deep‑learning and knowledge‑graph enhancements for robustness and low‑frequency query handling.

NLPcity detectionmachine learning
0 likes · 14 min read
Advancements in Query Analysis for Map Search: City Analysis, Where‑What Segmentation, and Path Planning
DataFunTalk
DataFunTalk
Nov 28, 2019 · Artificial Intelligence

Web Data Mining and Page Analysis Techniques for Search Engines

This article explains how search engines collect, analyze, and rank web pages by describing the spider system, HTML and layout tree construction, feature extraction, and machine‑learning based classification methods used to understand page content and improve result relevance.

HTML treefeature extractionlayout tree
0 likes · 8 min read
Web Data Mining and Page Analysis Techniques for Search Engines
Amap Tech
Amap Tech
Nov 21, 2019 · Artificial Intelligence

Advances in Geographic Text Processing for Map Search: Query Analysis, Error Correction, Rewriting, and Omission

Recent advances in map‑search text processing replace rule‑based pipelines with machine‑learning and deep‑learning models for query analysis, error correction, rewriting, and omission, using phonetic and spatial entity correction, vector‑based similarity, and CRF sequence labeling within a three‑stage architecture of analysis, recall, and ranking to deliver more precise POI results.

Error CorrectionNLPQuery Rewriting
0 likes · 17 min read
Advances in Geographic Text Processing for Map Search: Query Analysis, Error Correction, Rewriting, and Omission
Alibaba Terminal Technology
Alibaba Terminal Technology
Nov 21, 2019 · Frontend Development

How AI Is Revolutionizing Front‑End Development: From Design Drafts to Code

This article explores the rise of front‑end intelligence, analyzing background trends, competitive solutions, problem decomposition, and technical approaches for automatically converting design drafts into HTML, CSS, and JavaScript, while discussing challenges, model accuracy, data quality, and future roadmap for the D2C (Design‑to‑Code) system.

AIFrontendautomation
0 likes · 20 min read
How AI Is Revolutionizing Front‑End Development: From Design Drafts to Code
Hulu Beijing
Hulu Beijing
Nov 15, 2019 · Artificial Intelligence

How Content-Based Video Relevance Prediction Advances Personalized Streaming

The CBVRP (Content-Based Video Relevance Prediction) challenge, co‑hosted by Hulu and ACM MM 2019, showcased the shift from user‑based collaborative filtering to content‑driven recommendation, highlighted winning teams and their papers, and underscored the ongoing research importance of cold‑start video recommendation for streaming platforms.

MultimediaStreamingcold start
0 likes · 15 min read
How Content-Based Video Relevance Prediction Advances Personalized Streaming
58 Tech
58 Tech
Nov 15, 2019 · Artificial Intelligence

From Zero to One: Building a Personalized Recommendation System for 58.com Recruitment Platform

This article presents a comprehensive case study of how 58.com built a personalized recommendation system for its large‑scale recruitment platform, covering business background, data challenges, user modeling, recall strategies, ranking pipelines, system architecture, experimental infrastructure, and future research directions.

AB testingfeature engineeringknowledge graph
0 likes · 18 min read
From Zero to One: Building a Personalized Recommendation System for 58.com Recruitment Platform
DataFunTalk
DataFunTalk
Nov 15, 2019 · Artificial Intelligence

From Zero to One: Building 58.com Recruitment Personalized Recommendation System

This article details how 58.com constructed a large‑scale personalized recommendation platform for its recruitment business, covering business background, user intent modeling, knowledge‑graph and NER techniques, user profiling, multi‑stage recall strategies, ranking model pipelines, serving infrastructure, AB testing, and future research directions.

CTRCVRknowledge graph
0 likes · 18 min read
From Zero to One: Building 58.com Recruitment Personalized Recommendation System
Alibaba Cloud Developer
Alibaba Cloud Developer
Nov 15, 2019 · Artificial Intelligence

Boosting Online Shopping with AI-Powered 3D Scene Merchandising

This article explores how Alibaba’s 3D scene‑based recommendation system combines computer‑vision, deep‑learning and data‑driven matching algorithms to create immersive, size‑accurate product visualizations that enhance user experience and drive higher click‑through rates in e‑commerce.

3d-visualizationDeep Learninge‑commerce
0 likes · 12 min read
Boosting Online Shopping with AI-Powered 3D Scene Merchandising
360 Tech Engineering
360 Tech Engineering
Nov 13, 2019 · Artificial Intelligence

Text Anti‑Spam Techniques and TextCNN Model for Real‑Time Spam Detection on the Huajiao Platform

This article introduces the Huajiao platform's text anti‑spam architecture, analyzes spam categories and challenges, compares rule‑based and machine‑learning approaches, details traditional NLP methods and the TextCNN deep‑learning model, provides its TensorFlow implementation, and describes the online deployment workflow.

CNNNLPTensorFlow
0 likes · 14 min read
Text Anti‑Spam Techniques and TextCNN Model for Real‑Time Spam Detection on the Huajiao Platform
Xianyu Technology
Xianyu Technology
Nov 13, 2019 · Artificial Intelligence

Real-time Feature Engineering for Recommendation Systems via Edge Computing

The article proposes moving real‑time feature engineering for recommendation systems from cloud to edge devices, enabling second‑level updates of user behavior features such as exposure, scroll speed, and clicks, which reduces latency, improves model freshness and recommendation accuracy through edge‑cloud collaboration.

Edge Computingmachine learningrecommendation
0 likes · 6 min read
Real-time Feature Engineering for Recommendation Systems via Edge Computing
vivo Internet Technology
vivo Internet Technology
Nov 12, 2019 · Artificial Intelligence

Elasticsearch Retrieval Optimization in Gitee: Interview with Chen Xin

In an interview, Gitee’s chief architect Chen Xin explains why Elasticsearch was chosen for code search, outlines how combining search with NLP can both aid semantic understanding and enrich repository queries, and shares his views on the platform’s fast‑evolving ecosystem and upcoming community meetup.

ElasticsearchGiteeNLP
0 likes · 4 min read
Elasticsearch Retrieval Optimization in Gitee: Interview with Chen Xin
58 Tech
58 Tech
Nov 11, 2019 · Artificial Intelligence

Design and Implementation of the 58 Car Price Estimation System Using Machine Learning

The article describes the end‑to‑end architecture, data collection, preprocessing, feature engineering, model selection, training, and hyper‑parameter tuning of 58’s car price estimation platform, which leverages Spark, XGBoost, LightGBM and custom business rules to predict vehicle resale values.

LightGBMXGBoostcar price estimation
0 likes · 11 min read
Design and Implementation of the 58 Car Price Estimation System Using Machine Learning
Alibaba Cloud Developer
Alibaba Cloud Developer
Nov 8, 2019 · Artificial Intelligence

How AI is Transforming Software Testing: From Manual Checks to Fully Automated Intelligence

This article explores the evolution of software testing, the challenges posed by rapid internet-driven development, a six‑level model of AI‑augmented testing, practical application scenarios such as unit, API and UI testing, and a survey of leading AI‑powered testing tools shaping the future of quality assurance.

AI testingQuality assurancemachine learning
0 likes · 15 min read
How AI is Transforming Software Testing: From Manual Checks to Fully Automated Intelligence
360 Zhihui Cloud Developer
360 Zhihui Cloud Developer
Nov 5, 2019 · Operations

How 360 Scaled AIOps: From Data to Self‑Healing Operations

At the 360 Internet Technology Training Camp, experts detailed how AI-driven AIOps can transform large‑scale operations, covering data collection, model‑based anomaly detection, alert correlation, self‑healing workflows, and visual dashboards, and presented a practical end‑to‑end framework that other companies can adopt quickly.

Big DataOperationsaiops
0 likes · 15 min read
How 360 Scaled AIOps: From Data to Self‑Healing Operations
DataFunTalk
DataFunTalk
Nov 4, 2019 · Artificial Intelligence

Standardizing Model Training and Feature Processing in Recommendation Systems

This article describes a standardized workflow for feature collection, configuration, processing, and model training/prediction in large‑scale recommendation systems, using CSV‑based definitions and code generation to ensure consistency between offline training and online serving while reducing manual coding effort.

CTR predictionModel Trainingfeature engineering
0 likes · 14 min read
Standardizing Model Training and Feature Processing in Recommendation Systems
Python Programming Learning Circle
Python Programming Learning Circle
Nov 3, 2019 · Artificial Intelligence

Build Machine Learning Apps in Minutes with Streamlit: A Python‑Only Guide

This article explains how machine‑learning engineers can create fully functional, interactive apps using only Python and the open‑source Streamlit framework, covering its core principles, widget handling, caching, GPU support, deployment workflow, and real‑world examples with code snippets and diagrams.

App DevelopmentData visualizationPython
0 likes · 9 min read
Build Machine Learning Apps in Minutes with Streamlit: A Python‑Only Guide
58 Tech
58 Tech
Oct 28, 2019 · Artificial Intelligence

Ranking Strategy Optimization Practice in 58 Commercial Traffic

This article details the comprehensive optimization of 58's commercial traffic ranking system, covering data‑flow upgrades, advanced feature engineering, model enhancements—including online training, multi‑task and relevance models—and a multi‑factor ranking mechanism that together improve monetization efficiency and user experience.

Real-time Data Pipelinee‑commercefeature engineering
0 likes · 16 min read
Ranking Strategy Optimization Practice in 58 Commercial Traffic
Amap Tech
Amap Tech
Oct 23, 2019 · Artificial Intelligence

Scene‑aware and Fine‑grained Positioning Technology: Insights from Gaode Maps

Gaode’s scene‑aware positioning platform, serving billions of daily requests across 300,000 apps, combines GPS, Wi‑Fi/base‑station fingerprinting, inertial navigation, map‑matching and AI‑driven models to deliver sub‑10‑meter accuracy indoors and in vehicles, while leveraging massive data loops, hierarchical ranking, feature compression, and exploring 5G, VSLAM and ultra‑wideband for future fine‑grained localization.

AIMap Serviceslocation
0 likes · 16 min read
Scene‑aware and Fine‑grained Positioning Technology: Insights from Gaode Maps
DataFunTalk
DataFunTalk
Oct 17, 2019 · Artificial Intelligence

iQIYI Effect Advertising: Architecture, Click & Conversion Rate Estimation, and Intelligent Bidding

This article presents iQIYI's effect advertising system, detailing its dual‑engine resource slots, oCPX billing model, algorithmic challenges of high‑dimensional sparse conversion data, the personalized recommendation pipeline, feature engineering across real‑time, short‑term and long‑term signals, and the intelligent bidding mechanism that balances cost control with traffic quality.

Advertisingclick-through rateconversion optimization
0 likes · 9 min read
iQIYI Effect Advertising: Architecture, Click & Conversion Rate Estimation, and Intelligent Bidding
58 Tech
58 Tech
Oct 12, 2019 · Artificial Intelligence

Recruitment Recommendation System: Ranking Framework, Model Evolution, and Feature Engineering

This article details 58.com’s recruitment recommendation platform, describing its personalized matching challenges, typical recommendation scenarios, a three‑stage ranking framework, optimization goals, the evolution from rule‑based methods to logistic regression, factorization machines, XGBoost, and deep learning models, extensive feature engineering practices, and future research directions.

AIDeep Learningfeature engineering
0 likes · 16 min read
Recruitment Recommendation System: Ranking Framework, Model Evolution, and Feature Engineering
Architects' Tech Alliance
Architects' Tech Alliance
Oct 11, 2019 · Cloud Computing

Understanding FPGA: Architecture, Advantages, and Microsoft’s Data‑Center Deployments

This article explains what FPGA (Field‑Programmable Gate Array) is, why it offers lower latency and higher energy efficiency than CPUs or GPUs for both compute‑intensive and communication‑intensive workloads, and details Microsoft’s three‑generation FPGA deployment strategy in its data‑center and cloud infrastructure.

Data CenterFPGAHardware acceleration
0 likes · 20 min read
Understanding FPGA: Architecture, Advantages, and Microsoft’s Data‑Center Deployments
Meituan Technology Team
Meituan Technology Team
Oct 10, 2019 · Artificial Intelligence

Iterative Development of Delivery Time Estimation Models: Tree Model, Vector Retrieval, and End‑to‑End Deep Learning

The paper chronicles Meituan’s three‑stage evolution of delivery‑time estimation—from a hierarchical address tree with local linear regression, through a vector‑retrieval system that boosts recall, to a lightweight end‑to‑end deep‑learning model that meets sub‑5 ms latency while delivering progressively lower error and full coverage.

Deep LearningLogisticsPerformance Optimization
0 likes · 21 min read
Iterative Development of Delivery Time Estimation Models: Tree Model, Vector Retrieval, and End‑to‑End Deep Learning
Alibaba Cloud Developer
Alibaba Cloud Developer
Oct 10, 2019 · Artificial Intelligence

Boosting Spring Festival Activity: Alibaba’s Full‑Link Intelligent Delivery Framework

This article explains how Alibaba’s Hand‑Taobao platform uses a full‑link intelligent delivery framework—combining user intent recognition, rights recommendation, and advanced machine‑learning models such as XFTRL and Thompson Sampling—to predict activity drops during the Spring Festival and deliver personalized interventions that significantly improve DAU, click‑through, and redemption rates.

A/B testinge‑commercemachine learning
0 likes · 12 min read
Boosting Spring Festival Activity: Alibaba’s Full‑Link Intelligent Delivery Framework
Architects Research Society
Architects Research Society
Oct 7, 2019 · Artificial Intelligence

Comparison of Deep Learning Software Frameworks and Libraries

The article introduces deep learning as a machine‑learning subfield aimed at achieving artificial intelligence, explains its advantages in pattern recognition, and presents a visual comparison of prominent deep‑learning software frameworks, related tools, and additional resources while also including promotional information for a WeChat community.

AI frameworksNeural Networksmachine learning
0 likes · 3 min read
Comparison of Deep Learning Software Frameworks and Libraries
21CTO
21CTO
Oct 6, 2019 · Artificial Intelligence

How Toutiao’s AI Recommendation Engine Works: From Content Analysis to Real‑Time Ranking

This article explains the architecture and principles of Toutiao’s recommendation system, covering its three‑dimensional model of content, user and environment features, content analysis techniques, user tagging, real‑time training pipelines, evaluation methods, and content safety measures that together drive personalized feeds.

Real-time Trainingcontent analysismachine learning
0 likes · 18 min read
How Toutiao’s AI Recommendation Engine Works: From Content Analysis to Real‑Time Ranking
MaGe Linux Operations
MaGe Linux Operations
Sep 27, 2019 · Artificial Intelligence

Top 10 Python Libraries Every AI Developer Should Master

This article introduces ten essential Python libraries—TensorFlow, Scikit‑Learn, NumPy, Keras, PyTorch, LightGBM, Eli5, SciPy, Theano, and Pandas—detailing their features, typical use cases, and adoption in machine‑learning and data‑science projects, while highlighting each library's performance advantages, community support, and integration capabilities to help developers choose the right tool for their AI workflows.

KerasNumPyPyTorch
0 likes · 15 min read
Top 10 Python Libraries Every AI Developer Should Master
ITPUB
ITPUB
Sep 27, 2019 · Artificial Intelligence

How Didi and Ant Financial Co‑Built SQLFlow to Bring AI to Data Analysts

The article describes how Didi's data science team partnered with Ant Financial to open‑source SQLFlow, a tool that translates SQL into Python for AI model training and inference, enabling analysts to use familiar SQL to run deep‑learning, XGBoost, and clustering models across diverse business scenarios.

AIData ScienceSQLFlow
0 likes · 9 min read
How Didi and Ant Financial Co‑Built SQLFlow to Bring AI to Data Analysts
ITPUB
ITPUB
Sep 25, 2019 · Artificial Intelligence

From Physics to Kaggle Grandmaster: A Data Scientist’s Journey and Advice

Physicist‑turned‑Kaggle Grandmaster Bojan Tunguz shares his journey from academia to industry, the challenges of becoming a data‑science competitor, his workflow, favorite tools, and practical advice for newcomers seeking to excel in machine‑learning competitions.

Artificial IntelligenceData ScienceKaggle
0 likes · 10 min read
From Physics to Kaggle Grandmaster: A Data Scientist’s Journey and Advice
Python Programming Learning Circle
Python Programming Learning Circle
Sep 25, 2019 · Artificial Intelligence

How Google’s AI Quest Is Driving Quantum Supremacy and Shaping the Future

The article chronicles Google’s relentless push in artificial intelligence—from building massive neural networks and open‑source tools like TensorFlow to pursuing quantum supremacy—while highlighting ethical debates, internal conflicts, and the broader societal impact of its AI breakthroughs.

AI ethicsGoogle AIQuantum Computing
0 likes · 18 min read
How Google’s AI Quest Is Driving Quantum Supremacy and Shaping the Future
DataFunTalk
DataFunTalk
Sep 25, 2019 · Artificial Intelligence

Practical Exploration of OCPC Advertising Algorithm at Phoenix New Media

This article presents a comprehensive overview of the OCPC (Optimized Cost Per Click) advertising algorithm deployed by Phoenix New Media, detailing its background, problem definition, two‑price mechanism, smart bidding, CVR estimation techniques, online learning architecture, challenges such as data sparsity and conversion delay, and future research directions.

CVR estimationOCPCOnline Learning
0 likes · 15 min read
Practical Exploration of OCPC Advertising Algorithm at Phoenix New Media
DataFunTalk
DataFunTalk
Sep 23, 2019 · Artificial Intelligence

Understanding UC International Feed Recommendation: Goal Determination, Multi‑Objective Estimation, and Mixed Ranking

This article explains how UC international feed recommendation tackles goal definition, multi‑objective point estimation using models such as ESMM, DBMTL and MMoE, mixed‑ranking optimization, and cold‑start challenges by leveraging content understanding and feature generalization to improve user satisfaction.

AIcold-startmachine learning
0 likes · 12 min read
Understanding UC International Feed Recommendation: Goal Determination, Multi‑Objective Estimation, and Mixed Ranking
DataFunTalk
DataFunTalk
Sep 20, 2019 · Artificial Intelligence

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

The article argues that diversity should be treated as a tool rather than a final objective in recommendation systems, explains why it is hard to quantify, discusses appropriate metrics such as user feedback and engagement, and presents practical strategies—including expert rules, richer recall pipelines, and list‑wise modeling—to improve diversity while optimizing true business goals.

DiversityMetricslistwise
0 likes · 7 min read
Diversity as a Means, Not an End, in Recommendation Systems
Xianyu Technology
Xianyu Technology
Sep 17, 2019 · Frontend Development

Large-Scale UI Sample Generation for Alibaba 99 Promotion Module Recognition

The article describes a pipeline that automatically extracts a JSON‑like DSL representation of Alibaba’s 99‑promotion UI from rendered pages, cleanses CSS, converts transforms, renders the DSL to images, and combines it with dynamic ViewModel data to generate tens of thousands of high‑quality samples per module, raising recognition accuracy above 98%.

DSLData GenerationFront-end
0 likes · 8 min read
Large-Scale UI Sample Generation for Alibaba 99 Promotion Module Recognition
DataFunTalk
DataFunTalk
Sep 17, 2019 · Artificial Intelligence

Machine Learning for Personalized Education Paths – Case Study and Reflections

This lecture explores how machine learning can generate individualized learning pathways for students by building knowledge dependency graphs, defining optimization goals, and leveraging historical data to rank candidate routes, while reflecting on data, model, business, and demand challenges in AI-driven education.

AIBig Dataknowledge graph
0 likes · 10 min read
Machine Learning for Personalized Education Paths – Case Study and Reflections
360 Tech Engineering
360 Tech Engineering
Sep 16, 2019 · Artificial Intelligence

Backpropagation Algorithm for Fully Connected Neural Networks with Python Implementation

This article explains the backpropagation training algorithm for fully connected artificial neural networks, detailing its gradient‑descent basis, mathematical derivation, matrix formulation, and provides a complete Python implementation with mini‑batch stochastic gradient descent, momentum, learning‑rate decay, and experimental results.

BackpropagationMini-BatchNeural Network
0 likes · 14 min read
Backpropagation Algorithm for Fully Connected Neural Networks with Python Implementation
DataFunTalk
DataFunTalk
Sep 16, 2019 · Artificial Intelligence

Evolution of Weibo Advertising Strategy Engineering Architecture

This article presents a comprehensive overview of the evolution of Weibo's advertising strategy engineering architecture, detailing the system's growth from early banner ads to a sophisticated, multi‑layered online advertising platform that integrates algorithmic models, A/B experimentation, real‑time data pipelines, and precision targeting to support scalable, high‑performance ad delivery.

A/B testingAdvertisingSystem Architecture
0 likes · 19 min read
Evolution of Weibo Advertising Strategy Engineering Architecture
DataFunTalk
DataFunTalk
Sep 12, 2019 · Artificial Intelligence

Exploring Personalized Recommendation at Kuaikan Comics: Business, Algorithms, and System Architecture

This article details Kuaikan Comics' personalized recommendation pipeline, covering business context, diverse content formats, technical challenges, content‑based and collaborative‑filtering methods, ranking models, system architecture, A/B testing, and future directions for improving recommendation quality.

A/B testingCTR predictionSystem Architecture
0 likes · 14 min read
Exploring Personalized Recommendation at Kuaikan Comics: Business, Algorithms, and System Architecture
DataFunTalk
DataFunTalk
Sep 10, 2019 · Artificial Intelligence

Computational Advertising: Overview and Key Techniques from the Second Edition

The article introduces the second edition of "Computational Advertising", highlights its practical coverage of bidding algorithms, eCPM estimation, query expansion methods, and ad placement optimization, while also noting its industry impact, author credentials, and a limited‑time book giveaway.

Ad Techbidding algorithmscomputational advertising
0 likes · 10 min read
Computational Advertising: Overview and Key Techniques from the Second Edition
DataFunTalk
DataFunTalk
Sep 10, 2019 · Big Data

Why We Should Ride the Big Data Carriage: Business Perspectives on Data Growth and Machine Learning

The article explains why businesses must embrace the rapid, non‑linear growth of data and machine‑learning technologies, illustrating how data volume and richer information can drive exponential business value, improve competitiveness, and create sustainable positive feedback loops across various industry scenarios.

AIBig DataBusiness strategy
0 likes · 13 min read
Why We Should Ride the Big Data Carriage: Business Perspectives on Data Growth and Machine Learning
Architecture Digest
Architecture Digest
Sep 9, 2019 · Artificial Intelligence

Overview of Recommendation System Architecture, Algorithms, and Evaluation

This article provides a comprehensive introduction to recommendation systems, covering their definition, overall offline and online architectures, feature engineering, collaborative filtering, latent semantic models, ranking algorithms, and evaluation methods including A/B testing and offline metrics.

A/B testingcollaborative filteringfeature engineering
0 likes · 28 min read
Overview of Recommendation System Architecture, Algorithms, and Evaluation
Alibaba Cloud Developer
Alibaba Cloud Developer
Sep 9, 2019 · Big Data

Unlocking the Power of Unstructured Data: From AI Breakthroughs to Business Value

This article explains how unstructured data—comprising documents, images, audio, video and more—now dominates over 80% of all data, outlines its characteristics and challenges, compares it with structured data, and showcases real-world AI applications such as ImageNet, intelligent customer service and smart security, while proposing a roadmap for building a unified unstructured‑data asset.

Big DataData Analyticsmachine learning
0 likes · 15 min read
Unlocking the Power of Unstructured Data: From AI Breakthroughs to Business Value
Snowball Engineer Team
Snowball Engineer Team
Sep 4, 2019 · Artificial Intelligence

Advancing Recommendation Systems at Xueqiu: Transitioning from Point-Wise CTR Prediction to Pair-Wise TF-Ranking

This article explores the evolution of recommendation algorithms at Xueqiu, highlighting the limitations of traditional point-wise click-through rate prediction models and detailing the ongoing transition to a pair-wise TF-Ranking framework designed to mitigate user and content biases while significantly enhancing overall recommendation accuracy and user experience.

Algorithm OptimizationCTR predictionPair-Wise Learning
0 likes · 5 min read
Advancing Recommendation Systems at Xueqiu: Transitioning from Point-Wise CTR Prediction to Pair-Wise TF-Ranking
DataFunTalk
DataFunTalk
Sep 3, 2019 · Big Data

The Value of Big Data in Machine Learning: Detailed Illustration and Insights

This article explains how big data enhances machine learning by enabling finer-grained data characterization, improving confidence in statistical conclusions, and supporting smarter learning through multiple stages of model development, illustrated with concrete examples and a discussion of sample size dilemmas.

Big Datadata analysismachine learning
0 likes · 10 min read
The Value of Big Data in Machine Learning: Detailed Illustration and Insights
DataFunTalk
DataFunTalk
Sep 2, 2019 · Artificial Intelligence

Credit Risk Strategies: Data, Rules, and Model Development for Consumer Lending

This article presents a comprehensive overview of consumer credit risk management, covering industry background, traditional scoring‑card and machine‑learning model development processes, risk‑rate and limit strategies, rule effectiveness diagnostics, and advanced model‑optimization techniques to improve underwriting performance and cost efficiency.

consumer lendingcredit risklimit strategy
0 likes · 10 min read
Credit Risk Strategies: Data, Rules, and Model Development for Consumer Lending
DataFunTalk
DataFunTalk
Aug 30, 2019 · Artificial Intelligence

TransFM: Integrating Translation-based Recommendation and Factorization Machines for Sequential Recommendation

This article reviews the TransFM model, which combines the translation‑based sequential recommendation approach (TransRec) with factorization machines (FM), explains its formulation, optimization via sequential Bayesian personalized ranking, and demonstrates its superior performance on Amazon and Google Local datasets compared with several baselines.

Evaluationfactorization machinesmachine learning
0 likes · 8 min read
TransFM: Integrating Translation-based Recommendation and Factorization Machines for Sequential Recommendation
Alibaba Cloud Developer
Alibaba Cloud Developer
Aug 28, 2019 · Artificial Intelligence

Exact‑K Recommendation: Graph Attention Networks and RL from Demonstrations Explained

This article introduces the Exact‑K recommendation problem, highlights its differences from traditional Top‑K approaches, and presents a novel solution combining Graph Attention Networks (GAttN) with Reinforcement Learning from Demonstrations (RLfD), backed by extensive experiments showing superior performance on real-world datasets.

exact-kgraph attention networksmachine learning
0 likes · 14 min read
Exact‑K Recommendation: Graph Attention Networks and RL from Demonstrations Explained
DataFunTalk
DataFunTalk
Aug 27, 2019 · Artificial Intelligence

How Machines Learn: From Newton’s Second Law to the Core Steps of Supervised Learning

This article illustrates how a machine can rediscover Newton’s second law by treating force and acceleration data as a simple linear regression problem, detailing the three fundamental steps of hypothesis space definition, loss function design, and optimization through calculus or gradient methods.

Newton's lawhypothesis spaceloss function
0 likes · 15 min read
How Machines Learn: From Newton’s Second Law to the Core Steps of Supervised Learning
Amap Tech
Amap Tech
Aug 27, 2019 · Artificial Intelligence

POI Category Tagging: Multi‑Label Classification, Feature Engineering and Model Design

The system tackles POI category tagging as a multi‑label classification problem by engineering textual and non‑textual features, mining click‑log and external samples through active learning, and deploying hierarchical and per‑tag deep textCNN models with feature fusion, achieving over 5 % accuracy gain, ten‑fold speedup, and markedly higher precision and coverage that boost map‑search relevance.

POI taggingTextCNNfeature engineering
0 likes · 19 min read
POI Category Tagging: Multi‑Label Classification, Feature Engineering and Model Design
Youku Technology
Youku Technology
Aug 26, 2019 · Artificial Intelligence

Technical Deep Dive of Adaptive Streaming for “The Longest Day in Chang'an”: AI, Big Data, and QoE Optimization

Alibaba Entertainment’s technical deep‑dive reveals how its Smart Bitrate system leverages big‑data analytics, AI‑driven machine‑learning (including MPC and the Pensieve model) to dynamically select 5‑10‑second video segments, optimizing QoE by balancing high‑definition playback and buffering, achieving 5‑10% more HD viewing and 10‑20% fewer stalls for “The Longest Day in Chang’an.”

AIMPCQoE
0 likes · 10 min read
Technical Deep Dive of Adaptive Streaming for “The Longest Day in Chang'an”: AI, Big Data, and QoE Optimization
Tencent Cloud Developer
Tencent Cloud Developer
Aug 23, 2019 · Artificial Intelligence

WeChat Reading "Guess You Like" Recommendation System: Algorithms and Architecture

WeChat Reading’s “Guess You Like” engine combines real‑time click and reading data with tag‑based and deep‑learning embeddings, LSH similarity search, and a DeepFM ranking model to deliver cross‑type book, article, and video recommendations, continuously balancing exploitation and exploration to boost CTR and user engagement.

content-based filteringmachine learningrecommendation system
0 likes · 13 min read
WeChat Reading "Guess You Like" Recommendation System: Algorithms and Architecture
360 Quality & Efficiency
360 Quality & Efficiency
Aug 23, 2019 · Artificial Intelligence

High‑Performance High‑Dimensional Vector KNN Search Using FAISS

This article introduces the background of vector representations in machine learning, explains the K‑Nearest Neighbors algorithm and its key parameters, reviews traditional tree‑based and modern high‑performance search solutions, and demonstrates how FAISS can achieve microsecond‑level KNN queries on large‑scale high‑dimensional data.

FAISSVector Searchhigh-dimensional
0 likes · 5 min read
High‑Performance High‑Dimensional Vector KNN Search Using FAISS
DataFunTalk
DataFunTalk
Aug 22, 2019 · Artificial Intelligence

End‑to‑End Group Risk Perception Modeling: From Requirement Mining to Deployment

This article presents a comprehensive workflow for group risk perception, covering business requirement mining, data acquisition and understanding, feature engineering, model training and evaluation, deployment, and practical user applications, with detailed objectives, methods, and deliverables for each stage.

Model Deploymentdata mininggroup behavior analysis
0 likes · 11 min read
End‑to‑End Group Risk Perception Modeling: From Requirement Mining to Deployment
DataFunTalk
DataFunTalk
Aug 20, 2019 · Artificial Intelligence

The Story of Machine Learning: Why Machines Can Learn and How Statistical Learning Makes It Possible

This article explains why machine learning relies on big‑data statistical learning, illustrating human learning through induction and deduction, presenting case studies that highlight the limits of anecdotal reasoning, and introducing the law of large numbers and probabilistic trust as foundations for reliable AI models.

Big DataLearning Theorymachine learning
0 likes · 19 min read
The Story of Machine Learning: Why Machines Can Learn and How Statistical Learning Makes It Possible
DataFunTalk
DataFunTalk
Aug 19, 2019 · Artificial Intelligence

Algorithmic Practices in Hulu's Video Advertising System

This article details how Hulu leverages machine learning and AI techniques—including ad targeting, inventory prediction, conversion rate optimization, causal inference, and real‑time bidding—to improve ad efficiency, user experience, and revenue across its video streaming platform.

AIAd TargetingAdvertising
0 likes · 15 min read
Algorithmic Practices in Hulu's Video Advertising System
Python Crawling & Data Mining
Python Crawling & Data Mining
Aug 16, 2019 · Fundamentals

Master NumPy: Essential Array and Matrix Operations for Data Science

This guide introduces NumPy's core features—including array creation, arithmetic, indexing, aggregation, multi‑dimensional handling, matrix operations, and practical examples such as computing mean‑square error—providing a comprehensive foundation for Python‑based data analysis and machine‑learning workflows.

Array OperationsData ScienceMatrix Computation
0 likes · 10 min read
Master NumPy: Essential Array and Matrix Operations for Data Science
Programmer DD
Programmer DD
Aug 16, 2019 · Artificial Intelligence

Can AI Hear the Sweetest Watermelon? Acoustic Detection Explained

An interdisciplinary study from Zhejiang University demonstrates how machine learning, especially LS‑SVM, can analyze acoustic signals from knocked watermelons to accurately classify their ripeness and internal hollowness, offering a low‑cost, efficient alternative to traditional subjective methods and boosting watermelon quality assessment.

AILS-SVMacoustic detection
0 likes · 11 min read
Can AI Hear the Sweetest Watermelon? Acoustic Detection Explained
DataFunTalk
DataFunTalk
Aug 15, 2019 · Artificial Intelligence

Intelligent Customer Acquisition System Practice at Du Xiaoman Financial

This article presents a comprehensive overview of Du Xiaoman Financial's intelligent customer acquisition system, covering acquisition channels, efficiency improvements through multi‑stage models, data understanding with deepFM, the platform architecture, and related recruitment for senior machine‑learning engineers.

AICustomer Acquisitiondata engineering
0 likes · 9 min read
Intelligent Customer Acquisition System Practice at Du Xiaoman Financial
DataFunTalk
DataFunTalk
Aug 14, 2019 · Artificial Intelligence

Understanding Recommendation Systems: From Information Overload to Personalized AI Solutions

The article explores how the rapid growth of the internet has created information overload, discusses the challenges of recommendation systems such as sparsity and timeliness, outlines a four‑step personalized content pipeline, and highlights the interdisciplinary nature of building effective AI‑driven recommendation solutions.

AIBig Datadata engineering
0 likes · 16 min read
Understanding Recommendation Systems: From Information Overload to Personalized AI Solutions
Youku Technology
Youku Technology
Aug 12, 2019 · Artificial Intelligence

Interpretation of the Paper “Multi-View Multi-Label Learning with View‑Specific Information Extraction” (SIMM)

The article explains SIMM, a neural‑network framework for multi‑view multi‑label learning that jointly extracts a shared, view‑invariant subspace via adversarial loss and orthogonal view‑specific features, demonstrating superior performance across eight benchmark datasets compared to existing MVML and ML‑kNN methods.

AIadversarial learningmachine learning
0 likes · 11 min read
Interpretation of the Paper “Multi-View Multi-Label Learning with View‑Specific Information Extraction” (SIMM)
360 Tech Engineering
360 Tech Engineering
Aug 8, 2019 · Artificial Intelligence

Recommendation System Optimization: Lessons, AB Testing Cycles, and Practical Principles

This article shares extensive practical experience on recommendation system optimization, outlining the importance of problem definition, the limits of AB testing, and four guiding principles—avoid fundamentally wrong actions, do the right things correctly, keep solutions simple, and prevent over‑optimization.

A/B testingSystem Designalgorithm engineering
0 likes · 9 min read
Recommendation System Optimization: Lessons, AB Testing Cycles, and Practical Principles
DataFunTalk
DataFunTalk
Aug 8, 2019 · Artificial Intelligence

Practical Experience of JD E‑commerce Recommendation System: Architecture, Ranking, Real‑time Updates, and Experiment Platform

This article shares JD's e‑commerce recommendation system practice, covering the overall online/offline architecture, recall and ranking modules, real‑time feature and model updates, multi‑objective and diversity strategies, first‑stage index‑based ranking, KNN recall, and a layered experiment platform for rapid iteration.

Learning-to-RankReal-Timee‑commerce
0 likes · 14 min read
Practical Experience of JD E‑commerce Recommendation System: Architecture, Ranking, Real‑time Updates, and Experiment Platform
Amap Tech
Amap Tech
Aug 6, 2019 · Artificial Intelligence

Boosting ETA Accuracy: How TCN Improves Historical Speed Prediction for Navigation

To enhance estimated arrival times in navigation, this article analyzes the shortcomings of traditional historical average methods and proposes a machine‑learning solution using Temporal Convolutional Networks combined with dynamic and static feature engineering, demonstrating reduced bad‑case rates and better handling of seasonal patterns.

ETA predictionTCNTime Series
0 likes · 11 min read
Boosting ETA Accuracy: How TCN Improves Historical Speed Prediction for Navigation
21CTO
21CTO
Jul 31, 2019 · Artificial Intelligence

How JD Built a Scalable AI‑Powered Recommendation System

The article outlines JD’s evolution from rule‑based product suggestions in 2012 to a sophisticated, AI‑driven, multi‑screen personalized recommendation platform, detailing its product types, system architecture, data collection, offline and online computation, and the core recommendation engine that powers features like “Guess You Like.”

AIBig DataJD.com
0 likes · 14 min read
How JD Built a Scalable AI‑Powered Recommendation System
Architecture Digest
Architecture Digest
Jul 30, 2019 · Artificial Intelligence

Evolution and Architecture of JD.com’s Personalized Recommendation System

The article details JD.com’s journey from rule‑based product recommendations in 2012 to a sophisticated, AI‑driven personalized recommendation system, describing its multi‑screen product types, data collection, offline and online computation pipelines, and the modular architecture of its recommendation engine.

JD.comSystem Architecturee‑commerce
0 likes · 12 min read
Evolution and Architecture of JD.com’s Personalized Recommendation System
Efficient Ops
Efficient Ops
Jul 28, 2019 · Operations

How 58’s Intelligent Monitoring System Guarantees 24/7 Service Stability

This article details the design, architecture, and AI‑driven features of 58’s intelligent monitoring platform, explaining how multi‑dimensional data collection, predictive analytics, and smart alarm merging ensure continuous, automated observability across network, server, application, and business layers.

Observabilityanomaly detectioncloud infrastructure
0 likes · 20 min read
How 58’s Intelligent Monitoring System Guarantees 24/7 Service Stability
DataFunTalk
DataFunTalk
Jul 26, 2019 · Artificial Intelligence

Hulu’s Video Content Understanding: Challenges, Practices, and Applications

This article summarizes Hulu Chief Research Officer Xie Xiaohui’s presentation on why video content understanding is essential, the technical challenges involved, and Hulu’s end‑to‑end solutions—including fine‑grained segmentation, logo and subtitle detection, automated pipelines, tagging taxonomy, content generation, and vector embeddings—to improve recommendation, advertising, and search for massive video libraries.

AIHulucontent tagging
0 likes · 14 min read
Hulu’s Video Content Understanding: Challenges, Practices, and Applications
Tencent Cloud Developer
Tencent Cloud Developer
Jul 19, 2019 · Artificial Intelligence

Multi-turn Dialogue Intent Classification: Data Processing, Model Construction, and Operational Optimization

The article details a multi‑turn dialogue intent classification pipeline that extracts and expands labeled utterances, preprocesses text with custom tokenization, trains a two‑layer CNN‑Highway and a multi‑head self‑attention model, analyzes errors, and achieves up to 98.7% accuracy on a large, balanced dataset.

BERTCNNdialogue system
0 likes · 15 min read
Multi-turn Dialogue Intent Classification: Data Processing, Model Construction, and Operational Optimization
DataFunTalk
DataFunTalk
Jul 19, 2019 · Artificial Intelligence

From the Pre‑Recommendation Era to the Bronze Age: Evolution of Recommendation Systems and Mitigating the Matthew Effect

The article traces the historical development of recommendation systems from early manual and hot‑ranking methods through natural ranking and machine‑learning‑based scoring, discusses the Matthew effect and its mitigation via randomization, multi‑objective weighting, and pipeline architectures, and outlines modern personalization and recall strategies for e‑commerce platforms.

@DataAlgorithmse‑commerce
0 likes · 25 min read
From the Pre‑Recommendation Era to the Bronze Age: Evolution of Recommendation Systems and Mitigating the Matthew Effect