The 2018 KDnuggets survey of over 2,000 data‑science professionals shows Python dominating with 66% usage, R dropping below 50%, TensorFlow leading deep‑learning frameworks, RapidMiner gaining traction, SQL remaining stable, Hadoop declining, and regional participation shifting toward Europe.
This paper introduces the SCW-LOL algorithm, a local online learning method based on Soft Confidence Weighted that extends a global model with multiple local classifiers, uses online K‑Means for sample assignment, provides theoretical error bounds, and demonstrates superior performance on ten benchmark datasets, especially for multi‑class classification.
The talk covered Meipai’s personalized deep ranking model that balances depth and low latency, a behavior‑driven video clustering method that enriches recommendation beyond visual cues, and the use of advanced data structures to accelerate solving large‑scale optimization problems in business contexts.
This article reviews the evolution of recommendation system architecture for C2C e‑commerce platforms, tracing stages from simple offline‑online pipelines through granular feed‑flow improvements, real‑time processing, and machine‑learning‑driven models, while highlighting user‑profile construction, challenges, and best‑practice guidelines.
Alibaba’s knowledge graph leverages massive product data, NLP, semantic reasoning, and machine‑learning inference to detect and block counterfeit, infringing, or unsafe items in real time, providing millisecond‑level responses, self‑learning capabilities, and explainable decisions across e‑commerce platforms, thereby protecting intellectual property and consumer rights.
Using a stroll conversation among Ant Financial AI team members, the article likens machine learning concepts such as overfitting, generalization, supervised and unsupervised learning, transfer learning, and model interpretability to human development stages, illustrating how both require diverse data, training, and evolving algorithms.
The article reviews Hulu’s 2018 iQIYI keynote on AI video applications, detailing how AI drives personalized recommendations, content analysis through computer vision and NLP, ad targeting across visual, linguistic, and semantic layers, and outlines the platform’s machine‑learning architecture and future directions.
This article explains the goals, architectures, data pipelines, recall strategies, and ranking models of contemporary recommendation systems, covering both online and offline components, collaborative filtering, content-based methods, feature engineering, and practical interview insights for engineers.
The Wenqiang Ge team, winners of the first week of the Tencent Advertising Algorithm Competition rematch, detail their FFM-based solution, including baseline adoption, feature engineering with discretized continuous values, cross‑feature handling, and tool choices such as Feather storage and the xlearn library for fast training.
An in‑depth comparison of Hadoop and Spark examines their architectures, performance, cost, security, and machine‑learning capabilities, helping readers decide which open‑source distributed processing platform best matches their batch, streaming, and analytical workloads.
This comprehensive guide walks you through the fundamentals of speech recognition, explains how Python’s SpeechRecognition library works, shows how to install and use various recognizer packages, process audio files and microphone input, handle noise, and troubleshoot common errors with clear code examples.
This guide shares practical advice from multiple AI interview experiences, covering how to build a standout profile, a curated list of target companies, interview techniques, motivation for meaningful work, and essential computer science, math, and machine‑learning fundamentals to help graduates secure AI roles.
Meitu Technology’s technical salon on June 9, 2018 in Xiamen showcased how its AI‑driven deep ranking, video‑clustering, and data‑structure‑based optimization techniques improve personalization, recommendation and economic‑focused problem solving for billions of mobile users, targeting mid‑senior R&D and algorithm engineers.
This article summarizes the Ant Financial paper presented at DASFAA 2018 that proposes a universal local explanation method for Gradient Boosting Decision Tree models, detailing the problem definition, the PMML‑based algorithm for attributing feature contributions, experimental validation on fraud detection data, and the practical benefits for model transparency and improvement.
The Think in Cloud 2018 conference in Beijing showcased how cloud platforms enable rapid AI deployment across sectors such as autonomous driving, intelligent customer service, and education, highlighting challenges, platform‑centric solutions, and real‑world case studies that illustrate the growing synergy between cloud computing and artificial intelligence.
Judea Pearl, the 2011 Turing Award laureate, argues that modern AI is stuck in curve‑fitting and that true intelligence requires machines to understand cause and effect, a perspective he expands on through a series of insightful interview questions and answers.
The 2018 UCloud Think in Cloud conference showcased how cloud infrastructure accelerates AI applications in customer service, education, and embedded devices, while also presenting blockchain use cases and security challenges across finance, insurance, and IoT, highlighting practical solutions and emerging platforms.
The Nanjing University team '每天队员都想改一次名字' shares their winning approach in Tencent Advertising Algorithm Competition, covering data processing, feature engineering, model training techniques, and alternative optimization targets for AUC improvement, and discuss lessons learned from previous year's champion experience.
This article introduces the most commonly used algorithms in engineering—recommendation, optimization, estimation, and classification—explains their typical application scenarios, and discusses various testing methods and evaluation metrics such as offline experiments, user surveys, A/B testing, and performance indicators like accuracy, coverage, diversity, and robustness.
By converting Mercari’s product titles, descriptions, and categorical data into TF‑IDF vectors and embeddings, training MLP and GRU networks, and ensembling them with weighted averaging, the authors achieve a 0.3873 RMSLE—matching the competition’s top score—and demonstrate the power of text‑only price prediction for C2C marketplaces.
The author, a graduate student and weekly champion of the Tencent advertising algorithm contest, shares practical guidance on selecting mainstream CTR models—including LightGBM, field‑aware factorization machines, and deep learning approaches—while offering tips on feature handling, hyper‑parameter settings, and resource‑efficient implementation.
This article presents an Active PU Learning framework that combines active learning with two‑step PU semi‑supervised learning to improve cash‑out fraud detection, reducing labeling costs, enhancing model performance, and achieving a three‑fold increase in identified fraudulent transactions compared to traditional unsupervised methods.
This comprehensive guide walks you through installing the SpeechRecognition library, choosing a suitable Python package, handling audio files and microphones, and using the Recognizer API to convert spoken English into text while addressing noise, offsets, and advanced options.
This article explains how 360’s network operations team uses time‑series analysis, statistical thresholds, EWMA, dynamic limits, and machine‑learning models such as K‑Means and Isolation Forest to automatically detect, locate, and remediate traffic anomalies across massive data‑center exits.
The article explains how gcForest, an ensemble‑of‑decision‑tree model that mimics deep neural network hierarchies, uses cascade forests and multi‑grained sliding‑window scanning to achieve effective representation learning with fewer hyper‑parameters, especially on small datasets.
This article summarizes a two‑stage method for anomaly detection when only a few labeled anomalies and many unlabeled instances are available, detailing problem formulation, isolation‑forest‑based scoring, clustering of anomalies, weighted multiclass modeling, experimental validation, and real‑world URL attack applications.
This article traces the evolution of Weibo's recommendation system architecture across three major phases—independent 1.0, layered 2.0, and platform‑centric 3.0—detailing the environmental drivers, technical components, advantages, drawbacks, and key outcomes of each stage.
On World Book Day, nine Alibaba technology veterans share a curated list of essential technical books—covering software testing, design patterns, AI, machine learning, reinforcement learning, Rust, and database architecture—offering concise reasons why each title is valuable for developers and engineers.
This article explains the objectives, methods, architecture, and key algorithms of modern recommendation systems, covering popular, manual, related, and personalized approaches, the data pipeline, real‑time challenges, cold‑start handling, diversity, content quality, and exploration‑exploitation strategies.
This article outlines Suning's evolution from a basic network operations unit to a sophisticated, multi‑layered security architecture that integrates organizational structure, protection platforms, risk management, big‑data threat perception, and continuous improvement to safeguard e‑commerce operations.
This article provides a comprehensive overview of search engine algorithm systems, tracing their evolution from simple Bayesian and SVM models to modern deep learning approaches, and detailing the architecture, query analysis, ranking methods, click models, and recent advances such as reinforcement learning and adversarial networks.
This article chronicles the author’s transition from a mathematics background to machine learning, detailing early challenges, hands‑on projects in recommendation systems, security, and AIOps, and sharing practical insights on feature engineering, model evaluation, and large‑scale anomaly detection.
This article presents an Active PU Learning framework that combines active learning with two‑step positive‑unlabeled learning to improve cash‑out fraud detection in Alipay’s fifth‑generation risk engine, AlphaRisk, achieving three‑fold identification gains over unsupervised methods while reducing labeling costs.
This article recounts Alibaba‑Mama researcher Jing Shi’s presentation on the evolution of deep learning for click‑through‑rate (CTR) estimation, covering the shift from handcrafted features and linear models to piecewise linear MLR, end‑to‑end neural networks, multi‑interest user modeling, and large‑scale distributed training challenges.
Scientists suggest that mimicking the brain’s serotonin‑driven neuromodulation could give AI systems human‑like reasoning and emotional processing, while researchers at USC’s AI Lab are applying advanced machine‑learning patrol‑randomization and risk‑assessment algorithms, such as the ARMOR platform, to predict and prevent crimes like poaching.
This article explains the fundamentals and advanced techniques of e‑commerce product recommendation systems, covering conventional and personalized approaches, user profiling, data collection, storage, modeling, the three‑stage pipeline of preprocessing, recall and ranking, as well as system architecture, challenges, and key algorithms such as LR and GBDT.
This article explains the importance of modeling stability, describes how to assess feature and model stability using the Population Stability Index (PSI), provides step‑by‑step calculation methods, and shares practical monitoring practices such as rank mapping and daily SQL‑based checks.
This comprehensive tutorial walks you through Python data mining and machine learning fundamentals, covering data preprocessing techniques, common classification algorithms, an Iris flower classification case study, and practical tips for selecting the right algorithm, all illustrated with clear code examples and visualizations.
This article curates a ranked list of twelve deep‑learning books, from beginner‑friendly guides to comprehensive textbooks, describing each title’s focus, strengths, and ideal audience, helping readers choose the right resource to start or deepen their AI knowledge.
Meituan’s AI‑powered Rider Smart Assistant uses voice‑based interaction, real‑time routing, ETA prediction and massive GPS data to solve NP‑hard dispatch problems, cut manual phone calls, shorten order‑acceptance latency and rider wait times, and deliver safer, faster, more efficient same‑city logistics for riders and customers.
This article introduces Python’s essential features for data analysis and mining, then reviews the most widely used libraries—NumPy, SciPy, Matplotlib, Pandas, Scikit‑Learn, Keras, and Gensim—each accompanied by concise code examples that demonstrate their core capabilities.
This article introduces the Tree‑based Deep Match (TDM) framework, which uses a novel max‑heap tree structure to enable efficient, hierarchical retrieval over massive candidate sets, allowing any advanced deep learning model to improve matching accuracy, recall, and novelty in industrial recommendation systems.
In this article the author revisits Jiang Zemin’s 2008 paper on China’s information‑technology industry, highlighting his early predictions about machine learning, GPU research and SaaS, and reflecting on how those insights have proved prescient a decade later.
This article examines Baidu's practical applications of machine‑learning‑driven intelligent operations, detailing three real‑world scenarios, the challenges of KPI anomaly labeling, the design of an automated detection framework, evaluation results across multiple datasets, and broader insights for scaling AIOps in production environments.
This article introduces a GitHub repository that compiles comprehensive cheat sheets covering key Python libraries such as Keras, NumPy, Pandas, SciPy, Matplotlib, Scikit-learn, and others, providing quick reference resources to help beginners and researchers efficiently navigate machine learning and deep learning workflows.
This article reviews the evolution from rule‑based DeepDive methods to deep‑learning approaches such as PCNNs and attention‑enhanced models for relation extraction, presents experimental results on the NYT dataset, discusses practical challenges in large‑scale deployment, and outlines future research directions.
This article explains how Alibaba’s Shenma Search team builds and refines a large‑scale knowledge graph using open information extraction, detailing relation‑extraction techniques, distant supervision challenges, and the DeepDive system’s architecture, custom Chinese NLP pipeline, iterative improvements, and empirical results across millions of triples.
This beginner‑friendly TensorFlow tutorial by Chen Yidong walks readers through Windows environment setup, explains TensorFlow’s graph‑execution model, and demonstrates both softmax linear regression and a deep convolutional neural network for MNIST, while also covering utility scripts, TensorBoard visualization, and CPU/GPU or multi‑GPU deployment.
An in‑depth, visual guide walks readers through the fundamentals of machine learning—distinguishing supervised from unsupervised approaches, explaining dimensionality reduction with PCA, detailing clustering techniques such as hierarchical clustering, K‑Means and DBSCAN, and summarizing core regression and classification algorithms including linear regression, SVM, decision trees, logistic regression, Naïve Bayes, and KNN.
This article explains the shortcomings of traditional GANs, introduces the Wasserstein GAN (WGAN) as a remedy using the Earth‑Mover distance, describes the theoretical motivations, outlines the algorithmic steps and constraints, and provides illustrative diagrams and references for deeper study.
JD.com's Archimedes is a data center operating system that provides one-click scaling, intelligent scheduling, mixed deployment, and multi-site active-active capabilities, significantly improving resource utilization and reducing IT costs.
This article explains why machine learning is essential for complex tasks, defines neural networks, outlines three reasons to study them, and provides concise overviews of eight fundamental neural network architectures—including perceptron, CNN, RNN, LSTM, Hopfield, Boltzmann machines, deep belief networks, and deep autoencoders—grouped by their structural categories.
This article walks through a complete machine‑learning workflow on the UCI Census Income dataset, covering data exploration, preprocessing (including log‑transformation and scaling), model training with Naïve Bayes, Decision Tree and SVM, performance evaluation, hyper‑parameter tuning via grid search, feature importance analysis, and feature selection, providing code snippets and visualizations.
This article provides a concise overview of fifteen widely used machine learning models—including decision trees, random forests, k‑means, KNN, EM, linear and logistic regression, Naive Bayes, Apriori, Boosting, GBDT, SVM, neural networks, HMM, and CRF—detailing their features, strengths, weaknesses, and typical application scenarios.
This article reviews recent progress in Bayesian machine learning, covering foundational theory, non‑parametric approaches such as Dirichlet and Indian buffet processes, regularized Bayesian inference, and scalable techniques for big‑data environments including stochastic variational methods, distributed algorithms, and hardware acceleration.
This article explains the fundamentals of Bayes' theorem, shows how to compute prior, likelihood, and posterior probabilities, demonstrates Bayesian A/B testing with Python code, introduces Bayesian networks for causal inference, and discusses the role of Bayesian methods in machine learning and data‑driven decision making.
This article explains entropy, joint entropy, conditional entropy, and related measures such as KL divergence and cross‑entropy, using intuitive coin‑flip examples and mathematical formulas to show how they quantify uncertainty and information in probability distributions.
The article recounts the author’s 2017‑onward journey building an intelligent operations platform at Tencent, detailing challenges such as legacy thresholds, AIOps talent shortage, and lack of frameworks, and explains how a two‑stage hybrid unsupervised‑supervised model was devised to automatically detect anomalies across millions of KPI time‑series, enabling scalable root‑cause analysis and cost optimization.
This article explains how Hidden Markov Models can be used to model Chinese word segmentation, covering the underlying Markov process, model parameters, basic HMM problems, and both supervised and unsupervised training methods.
This article details JD's evolution from rule‑based recommendations to a multi‑screen, AI‑driven personalization platform, describing its system architecture, data pipelines, feature services, and key technologies that enable real‑time, user‑centric product suggestions across the e‑commerce ecosystem.
The article explains the core concepts of recommendation engines—user profiling and data classification—describes how large‑scale data processing tools are used to build models, and outlines common offline and A/B testing approaches for evaluating recommendation performance.
This article explains the concepts of entropy, joint entropy, conditional entropy, relative entropy (KL divergence) and cross‑entropy, illustrating their definitions, mathematical formulas, intuitive interpretations, and relationships through simple probability examples and visual diagrams.
This article introduces Generative Adversarial Networks (GANs), explains their minimax formulation, value function, Jensen‑Shannon divergence, common variants, and practical training issues such as gradient saturation, while also previewing the next topic on Hidden Markov Models.
This article reviews the PreFix system, which uses machine‑learning on datacenter switch logs to predict hardware failures ahead of time, detailing its design, feature extraction, random‑forest model, experimental validation across multiple switch models, and its broader applicability to disk failure prediction.
In an exclusive interview, UCloud’s R&D Director Ye Lideng shares how the company’s CBA strategy, AI‑first products, and innovative cloud services empower startups, drive industry adoption, and shape the future of artificial intelligence and cloud computing in China.
This article presents a comprehensive overview of Toutiao's recommendation system, detailing its three‑dimensional modeling approach, real‑time training pipeline, feature engineering, content and user analysis techniques, evaluation methodology, and the extensive content‑safety mechanisms employed to ensure reliable and responsible information distribution.
This article explores the growing complexity of AI adoption, the need for customized predictive solutions, and practical steps for enterprises to integrate machine learning without over‑hauling development teams, using IoT predictive‑maintenance as a concrete example.
Learning to rank reframes search as a machine‑learning problem that optimizes document ordering rather than numeric prediction, using relevance metrics such as NDCG and feature‑based scoring functions, and comparing point‑wise, pair‑wise (RankSVM) and list‑wise (ListNet) approaches while stressing that proper error definition and feature selection matter more than the specific algorithm.
This article details Ctrip's end‑to‑end personalized recommendation system for travel, covering data collection, candidate recall methods, ranking models, feature engineering practices, and future directions, illustrating how millions of users receive tailored travel suggestions.
The article presents Ping An Bank's AI-driven data platform, covering business background, architectural layers, algorithmic applications such as customer segmentation, portrait, business forecasting, and graph analysis, and shares practical insights on platform design, model deployment, and the role of data product managers.
The article details Ctrip's large‑scale personalized recommendation system, covering data sources, recall strategies, ranking models, feature engineering techniques, and practical insights from industry research to improve user experience in travel services.
Alibaba leverages multiple machine‑learning models—including spending forecasts, discount‑sensitivity, spread‑ability, category‑preference, and churn prediction—to intelligently allocate shopping vouchers and red packets during Double 11, boosting consumer engagement, merchant sales, and overall platform GMV.
This article provides a comprehensive overview of Toutiao's recommendation system, covering its three‑dimensional modeling approach, feature engineering, real‑time training pipeline, recall strategies, user‑tag generation, evaluation methodology, and content‑safety mechanisms.
This article explains JD Finance's operational challenges in a rapidly expanding micro‑service environment and presents a comprehensive approach that combines offline and online load testing, precise capacity calculations, and intelligent root‑cause alert analysis using both rule‑based and machine‑learning techniques.
Alibaba’s latest AI-driven ad retrieval framework, unveiled at WWW 2018, replaces keyword‑based search with a user‑behavior heterogeneous graph and machine‑learning models, delivering personalized, high‑efficiency ad matching that boosts ROI for advertisers, improves user experience, and enhances platform revenue.
This article presents the design, architecture, and several AI-driven models—including user intent detection, group supervision, content extraction, knowledge graph construction, and self‑service QA—of Ctrip's intelligent cloud customer service platform, highlighting its impact on service efficiency and business automation.
In this lecture, Prof. Pei Dan of Tsinghua University outlines the evolution of intelligent operations from rule‑based automation to machine‑learning‑driven AIOps, discusses data, feedback loops, and practical challenges, and calls for stronger collaboration between industry and academia to accelerate research and deployment.
This article reviews the key concepts, challenges, and recent research on transfer learning presented at CIKM 2017, covering instance, feature, parameter, and relation‑based methods, supervised and unsupervised deep TL approaches, and transitive transfer learning with associated loss formulations and optimization strategies.
This article explores whether regular programmers should switch to AI engineering, presents three detailed real‑world transition cases, outlines step‑by‑step learning paths, essential resources, and practical advice for mastering machine learning and deep learning technologies.
This article surveys the 20 most active Python machine‑learning repositories on GitHub, summarizing each project's core capabilities, typical use cases, and providing direct links for developers interested in exploring open‑source AI tools.
This article explains user behavior concepts and feedback types, introduces collaborative filtering methods including user‑based, item‑based and latent factor models, discusses similarity measures, power‑law distributions, and practical considerations such as negative sampling, providing a comprehensive overview for building recommendation systems.
The author recounts a 16‑hour drive to Las Vegas for AWS re:Invent, highlighting AI‑focused sessions such as Alexa, Lex, Polly, serverless Lambda, the MXNet vs TensorFlow competition, and emerging video‑processing research, while noting strengths, limitations, and future growth prospects.
This article traces the evolution of computer chess from the 18th‑century automaton "The Turk" through early programs by Turing, Shannon, and McCarthy, to landmark systems like Deep Blue, AlphaGo, and AlphaZero, highlighting key algorithms, milestones, and their impact on AI research.
The author reflects on attending AWS re:Invent 2017, highlighting Alexa's AI capabilities, the ecosystem for skill development, the technical challenges of building voice assistants, and the need for tight integration of product, algorithm, and engineering to advance intelligent assistants.
This article details how to create a simple Chinese pinyin input method using a Hidden Markov Model, training data from Jieba, storing probability matrices in SQLite, and implementing the Viterbi algorithm in Python, complete with code snippets and performance observations.
From foundational concepts to practical examples, this guide walks engineers through ten essential supervised and unsupervised machine‑learning algorithms—decision trees, Naïve Bayes, linear regression, logistic regression, SVM, ensemble methods, clustering, PCA, SVD, and ICA—explaining their theory, real‑world uses, and why they matter.
This article describes Ctrip’s evolution from rule‑based web attack detection to a Spark‑powered machine‑learning system, detailing the Nile architecture, data collection, feature engineering with TF‑IDF, model training, evaluation metrics, online deployment, and future enhancements for information security.
This article reviews Alibaba's end‑to‑end intelligent dialogue system, detailing its connection‑driven interaction model, the core NLU framework, intent classification, attribute extraction, ranking, QA and chat modules, product deployments, and future research directions.
Meituan‑Dianping’s DSP coarse‑ranking filters large ad candidate sets by scoring ads with user‑profile, weather, and keyword scenario models—using frequent‑itemset mining, AdaBoost, and TF/IDF—then aggregates these scores via a linear‑regression model to select high‑relevance ads for fine‑ranking, boosting click‑through and conversion rates.
This article explains what user profiling is, why it’s crucial for recommendation systems, outlines key dimensions such as personal attributes, status, and interests, describes algorithms like classification and autoregressive models, and details offline and real‑time computation methods, evaluation techniques, and practical examples.
He Xiaofeng, JD Mall Infrastructure chief architect, discusses his role in building a real‑time computing platform, applying streaming frameworks, machine learning, and knowledge‑graph techniques to product data mining, improve search accuracy, and outline future research directions.
This article explains what recommendation systems are, their purpose, differences from search, typical multi‑layer architecture, real‑time and offline processing flows, user feedback handling, and key metrics for evaluating their effectiveness.
This article introduces how to leverage the opencv4nodejs Node.js module—binding OpenCV’s full API—to develop a face detection and recognition application, highlighting the CPU‑intensive nature of computer‑vision tasks, the limitations of JavaScript, and the availability of synchronous and asynchronous examples.
In this comprehensive talk, Pei Dan outlines the technical and strategic roadmap for bringing AIOps to production, explains the challenges of anomaly detection, fault localization, root‑cause analysis and prediction, and demonstrates how to decompose complex operations problems into AI‑solvable tasks.
The O2O Machine Learning Applications Seminar, featuring experts from Meituan‑Dianping and Alibaba, explores real‑world ML implementations for online‑to‑offline services, including online learning for search, Alibaba’s Ali Xiaomi intelligent assistant, deep‑learning‑driven recommendation systems, and advertising algorithms such as CTR and CVR optimization, sharing practical insights and best practices.
This article surveys the most essential Python packages for data science in 2017, covering core scientific computing, data manipulation, visualization, machine learning, deep learning, natural language processing, and web scraping, and explains why each library remains indispensable for modern analysts.
This article explains the origins and development of artificial intelligence, clarifies the relationships and distinctions among AI, machine learning, and deep learning, and uses several illustrative diagrams to help readers quickly grasp how these three hot AI technologies are connected and differ from each other.
An analysis of Indeed.com job‑trend data reveals how programming languages like Python, Java, R, C++, Scala and Julia rank in popularity for machine‑learning and data‑science positions, highlighting growth patterns and offering guidance on language selection based on career goals.
This article introduces the fundamental concepts of machine learning, defining the terms "machine" and "learning," presenting Tom Mitchell's formal definition, outlining the roles of learners and predictors, and contrasting machine‑learning programs with traditional software through clear diagrams.
The iQIYI recommendation system combines a two‑stage pipeline of recall and ranking, evolving from logistic regression to a GBDT‑FM‑DNN ensemble, using online feature storage, extensive feature engineering, and configurable strategies to deliver personalized video suggestions while addressing feature drift and multi‑objective business goals.
