BestHub
Sign in
Tagged articles
202 articles
Page 1 of 3
Data Party THU
Data Party THU
May 14, 2026 · Artificial Intelligence

Explore TimechoAI: The New Timer Time‑Series Large Model Cloud Service Now Open for Beta

TimechoAI, the cloud service built on the Timer time‑series large model, offers the latest SOTA model (Timer‑3.5) alongside classic baselines, supports multiple data input methods, covariate integration, and API/SDK access, and invites industrial and IoT teams to test its predictive maintenance, production optimization, energy load forecasting, and anomaly detection capabilities through a simple invitation process.

AI Cloud ServiceIndustrial IoTLarge Model
0 likes · 13 min read
Explore TimechoAI: The New Timer Time‑Series Large Model Cloud Service Now Open for Beta
Data Party THU
Data Party THU
May 12, 2026 · Artificial Intelligence

Time Series Large Models Explained: What They Are and Why They Matter

The article introduces time‑series data, its ubiquitous examples, the challenges of traditional small models, and proposes a universal time‑series large model that simplifies data preparation and model building, ultimately enabling more efficient and stable industrial AI solutions, now offered as a cloud service.

AIARIMACRISP-DM
0 likes · 6 min read
Time Series Large Models Explained: What They Are and Why They Matter
DeepHub IMBA
DeepHub IMBA
Apr 22, 2026 · Artificial Intelligence

A Survey of Time Series Forecasting Augmentation: Frequency Domain, Decomposition, and Patch Methods

The article reviews why classic classification augmentations fail for forecasting, outlines a taxonomy of effective time‑series augmentation techniques—including frequency‑domain, decomposition, and patch‑based methods—details the Temporal Patch Shuffle (TPS) pipeline, and presents extensive experiments showing TPS achieves state‑of‑the‑art improvements across long‑term, short‑term, and classification tasks.

Time Seriesdata augmentationforecasting
0 likes · 17 min read
A Survey of Time Series Forecasting Augmentation: Frequency Domain, Decomposition, and Patch Methods
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Mar 29, 2026 · Artificial Intelligence

How MetaTrader Uses Reinforcement Learning to Boost Trading Strategy Generalization

The article reviews the MetaTrader method, which formulates sequential portfolio optimization as a partially offline reinforcement‑learning problem, introduces a double‑layer RL algorithm and a conservative TD objective to improve out‑of‑distribution generalization, and demonstrates superior performance on CSI‑300 and NASDAQ‑100 datasets compared with existing baselines.

Financial TradingMetaTraderOOD data augmentation
0 likes · 15 min read
How MetaTrader Uses Reinforcement Learning to Boost Trading Strategy Generalization
Alibaba Cloud Native
Alibaba Cloud Native
Mar 22, 2026 · Artificial Intelligence

Revolutionizing AI‑Driven Operation Intelligence with AutoDA‑Timeseries, SemanticLog, and LogBase

The article outlines three core challenges—semantic gaps, poor generalization, and industrial usability—in operation intelligence and presents three academic breakthroughs—AutoDA‑Timeseries, SemanticLog, and LogBase—that together advance AI‑powered monitoring, log parsing, and large‑scale benchmarking for smarter, more efficient cloud operations.

AI OpsAutoDABenchmark
0 likes · 9 min read
Revolutionizing AI‑Driven Operation Intelligence with AutoDA‑Timeseries, SemanticLog, and LogBase
DeepHub IMBA
DeepHub IMBA
Mar 11, 2026 · Fundamentals

Detecting Time‑Series Change Points with Grid Search and Piecewise Regression

This article shows how to turn change‑point detection into an optimization problem by exhaustively searching knot configurations with grid search, selecting the best model using a penalised likelihood criterion (BIC), and applying piecewise regression to automatically locate trend breakpoints, illustrated with R and Python code on California natural‑gas consumption data.

BICPythonR
0 likes · 12 min read
Detecting Time‑Series Change Points with Grid Search and Piecewise Regression
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Mar 3, 2026 · Artificial Intelligence

How HORAI Uses Large‑Scale Multimodal Pretraining to Boost Time‑Series Forecasting and Anomaly Detection

The article reviews the HORAI model, which introduces a frequency‑enhanced multimodal pretraining paradigm and the massive MM‑TS dataset, showing that integrating derived images, endogenous text, and real‑world news dramatically improves zero‑shot forecasting and anomaly detection across six domains.

HORAIMultimodal LearningTime Series
0 likes · 23 min read
How HORAI Uses Large‑Scale Multimodal Pretraining to Boost Time‑Series Forecasting and Anomaly Detection
Model Perspective
Model Perspective
Jan 30, 2026 · Fundamentals

Mastering Multi‑Dimensional Forecasting: From Peer Benchmarks to System‑Level Insights

This article presents a comprehensive framework for forecasting that combines peer (same‑level) comparison, bottom‑up decomposition, top‑down system thinking, time‑series analysis, causal modeling, and scenario simulation, while highlighting each method's strengths, limitations, and practical wisdom for effective decision‑making.

PredictionTime Seriescausality
0 likes · 12 min read
Mastering Multi‑Dimensional Forecasting: From Peer Benchmarks to System‑Level Insights
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Jan 4, 2026 · Artificial Intelligence

How VTA Combines Large‑Model Reasoning for Precise and Explainable Stock Time‑Series Forecasting

The VTA framework integrates large language model reasoning with textual annotation of technical indicators, employs a Time‑GRPO reinforcement‑learning objective and multi‑stage joint conditional training, and achieves state‑of‑the‑art accuracy and expert‑rated interpretability on US, Chinese and European stock datasets.

LLMStock PredictionTime Series
0 likes · 19 min read
How VTA Combines Large‑Model Reasoning for Precise and Explainable Stock Time‑Series Forecasting
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Dec 30, 2025 · Artificial Intelligence

MaGNet: Dual‑Hypergraph Mamba Network for Time‑Causal and Global Stock Trend Forecasting

MaGNet introduces a three‑component architecture—MAGE block with bidirectional Mamba, adaptive gating and sparse MoE, 2‑D spatio‑temporal attention, and a dual hypergraph framework (time‑causal and global probability hypergraphs)—that outperforms 17 baselines on six major stock indices in both prediction accuracy and risk‑adjusted returns.

Financial AIHypergraphMaGNet
0 likes · 14 min read
MaGNet: Dual‑Hypergraph Mamba Network for Time‑Causal and Global Stock Trend Forecasting
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Dec 23, 2025 · Artificial Intelligence

How H3M‑SSMoEs Combines Hypergraph Multimodal Learning and LLM Reasoning to Predict Stock Direction

The paper introduces H3M‑SSMoEs, a framework that integrates a multi‑context hypergraph for fine‑grained spatio‑temporal dynamics with a frozen Llama‑3.2‑1B LLM adapter, and a style‑structured expert mixture to jointly model stock relationships, multimodal semantics, and market regimes, achieving superior accuracy and investment returns on DJIA, NASDAQ‑100, and S&P‑100 benchmarks.

Financial AIHypergraphLLM
0 likes · 14 min read
How H3M‑SSMoEs Combines Hypergraph Multimodal Learning and LLM Reasoning to Predict Stock Direction
DevOps Coach
DevOps Coach
Dec 15, 2025 · Databases

Why PostgreSQL Is Becoming the Backend OS: From Search to Event Streaming

The article explains how PostgreSQL has evolved from a simple relational store into a versatile platform that supports full‑text search, vector similarity, geospatial queries, JSONB, message queues, and analytical workloads, allowing developers to replace multiple specialized tools with a single unified system.

Database ExtensionsEvent StreamingFull‑Text Search
0 likes · 6 min read
Why PostgreSQL Is Becoming the Backend OS: From Search to Event Streaming
Data Party THU
Data Party THU
Nov 22, 2025 · Artificial Intelligence

How Frequency‑Refined Augmentation Boosts Contrastive Learning for Time‑Series Classification

FreRA introduces a lightweight, plug‑in frequency‑refined augmentation that adaptively refines spectral components to preserve global semantics while injecting variance, dramatically improving contrastive learning performance on time‑series classification, anomaly detection, and transfer learning across multiple benchmark datasets.

Time Seriescontrastive learningdata augmentation
0 likes · 13 min read
How Frequency‑Refined Augmentation Boosts Contrastive Learning for Time‑Series Classification
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Nov 13, 2025 · Artificial Intelligence

Paper Review: AlphaGAT’s Two‑Stage Learning for Adaptive Portfolio Selection

AlphaGAT introduces a two‑stage learning framework that first extracts robust alpha factors with a CATimeMixer model and a novel loss, then dynamically weights these factors via reinforcement learning (PPO) and a graph attention network, achieving superior portfolio performance across DJIA, HSI, CSI‑100 and crypto markets despite noisy data and distribution shifts.

AlphaGATFinancial AITime Series
0 likes · 14 min read
Paper Review: AlphaGAT’s Two‑Stage Learning for Adaptive Portfolio Selection
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Nov 11, 2025 · Artificial Intelligence

A New Method: Dynamic Higher-Order Relations and Event-Driven Modeling for Stock Price Prediction

The article reviews a novel stock price prediction model that integrates a Hawkes‑process layer to capture sudden co‑movements and a dynamic hypergraph to represent high‑order relationships, detailing its formulation, training objective, extensive experiments on S&P 500 data, and superior performance over transformer, graph, and hypergraph baselines.

Financial AIHawkes processTime Series
0 likes · 12 min read
A New Method: Dynamic Higher-Order Relations and Event-Driven Modeling for Stock Price Prediction
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Nov 8, 2025 · Artificial Intelligence

Time-Series Paper Digest: Nov 1‑7 2025 Highlights

This digest summarizes three recent AI papers—DoFlow, Forecast2Anomaly, and ForecastGAN—detailing their causal generative flow model for interventions, a retrieval‑augmented framework for zero‑shot anomaly prediction, and a decomposition‑based adversarial approach that improves multi‑horizon forecasting across diverse datasets.

Deep LearningTime Seriesanomaly detection
0 likes · 8 min read
Time-Series Paper Digest: Nov 1‑7 2025 Highlights
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Oct 25, 2025 · Artificial Intelligence

Time Series Paper Digest: Extreme Event Prediction, Multimodal Fusion & Anomaly Detection

This article summarizes four recent arXiv papers on time‑series forecasting, covering a hierarchical knowledge‑distillation framework for extreme events, a graph‑enhanced multimodal fusion network, an interpretable unsupervised anomaly detector, and an adaptive masking loss that improves prediction accuracy.

Time Seriesadaptive maskinganomaly detection
0 likes · 10 min read
Time Series Paper Digest: Extreme Event Prediction, Multimodal Fusion & Anomaly Detection
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Oct 14, 2025 · Artificial Intelligence

How TS‑Agent Uses LLMs and Reflective Feedback to Automate Financial Time‑Series Modeling

TS‑Agent is a modular LLM‑driven framework that formalizes financial time‑series modeling as a three‑stage iterative decision process, leveraging structured knowledge bases, dynamic memory, and a feedback‑driven code‑editing loop to outperform AutoML baselines in accuracy, robustness, and auditability.

AutoMLFeedback LoopKnowledge Base
0 likes · 12 min read
How TS‑Agent Uses LLMs and Reflective Feedback to Automate Financial Time‑Series Modeling
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Sep 20, 2025 · Artificial Intelligence

Recent Time-Series Paper Summaries (Sep 13‑19, 2025)

This article summarizes four recent time‑series forecasting papers, covering a universal delay‑embedding foundation model, a dual causal network that leverages exogenous variables, a distribution‑aware alignment plug‑in called TimeAlign, and a shapelet‑based framework for interpretable directional forecasting in noisy financial markets.

Time Seriescausal networkfinancial markets
0 likes · 9 min read
Recent Time-Series Paper Summaries (Sep 13‑19, 2025)
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Sep 13, 2025 · Artificial Intelligence

Paper Summary: Recent AI Advances in Financial Time-Series (Sep 6‑12, 2025)

This article summarizes four recent AI research papers that explore zero‑shot PDE extrapolation with text‑trained LLMs, causal hidden‑state interventions for rare financial events, tabular reformulation of graph node classification, and a multimodal model for financial time‑series forecasting, detailing their methods, experiments, and key findings.

LLMTime Seriescausal intervention
0 likes · 10 min read
Paper Summary: Recent AI Advances in Financial Time-Series (Sep 6‑12, 2025)
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Sep 6, 2025 · Artificial Intelligence

Time Series Paper Digest (Aug 23–Sep 5 2025)

It presents concise summaries of six recent arXiv papers on unsupervised domain adaptation, efficient forecasting, SHAP explanations, text‑reinforced multimodal forecasting, online prediction with feature adjustment, zero‑shot forecasting zoo, and a new anomaly‑detection metric, highlighting methods, datasets, and results.

Multimodal LearningOnline LearningSHAP
0 likes · 16 min read
Time Series Paper Digest (Aug 23–Sep 5 2025)
Data Party THU
Data Party THU
Sep 5, 2025 · Big Data

Key Takeaways from the 2025 China University Big Data Challenge

In this reflective case study, a first‑time undergraduate shares how competing in the 2025 China University Big Data Challenge—predicting Shanghai‑Shenzhen 300 index component movements—deepened his understanding of structured time‑series data processing, algorithm adaptability, iterative model optimization, and the broader value of data‑driven problem solving.

Data ScienceModelingTime Series
0 likes · 5 min read
Key Takeaways from the 2025 China University Big Data Challenge
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Aug 28, 2025 · Artificial Intelligence

Key AI-Driven Quantitative Finance Papers from KDD2025

This article summarizes recent AI research on quantitative finance, covering AlphaAgent's LLM-driven alpha mining, UMI's multi‑level irrationality factors, PDU's progressive dependency learning for stock ranking, SSPT's stock‑specific pretraining transformer, and Enhancer's distribution‑aware meta‑learning framework, all of which demonstrate improved stock prediction and resistance to alpha decay.

Alpha MiningFinancial AILLM
0 likes · 9 min read
Key AI-Driven Quantitative Finance Papers from KDD2025
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Aug 26, 2025 · Artificial Intelligence

SSPT: Custom Pre‑training Tasks for Stock Data Boost Stock Selection Performance

This article reviews the SSPT paper, which introduces three stock‑specific pre‑training tasks—stock code classification, sector classification, and moving‑average prediction—built on a two‑layer Transformer, and demonstrates through extensive experiments across five market datasets that these tasks consistently improve cumulative return and Sharpe ratio over baselines.

Financial AITime SeriesTransformer
0 likes · 11 min read
SSPT: Custom Pre‑training Tasks for Stock Data Boost Stock Selection Performance
Data STUDIO
Data STUDIO
Aug 21, 2025 · Industry Insights

Predicting Stock Market Movements with a Markov‑Chain State‑Transition Model

This article explains how to model short‑term stock market dynamics using a Markov‑chain framework, covering the theory of memoryless state transitions, construction of a transition matrix, multi‑step probability forecasts, steady‑state analysis, a full Python implementation, and a real‑world case study with its limitations.

Markov chainPythonTime Series
0 likes · 18 min read
Predicting Stock Market Movements with a Markov‑Chain State‑Transition Model
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Aug 5, 2025 · Operations

How Alibaba Scales Anomaly Detection Across Millions of Metrics

This article explains how Alibaba tackles anomaly detection for tens of millions of metrics in a 100‑thousand‑machine cluster by comparing vertical time‑series methods with horizontal clustering, choosing DBSCAN for large‑scale monitoring, and detailing the ETL, computation, and visualization pipeline.

DBSCANTime Seriesanomaly detection
0 likes · 6 min read
How Alibaba Scales Anomaly Detection Across Millions of Metrics
AI Algorithm Path
AI Algorithm Path
Aug 1, 2025 · Fundamentals

Intuitive Explanation of the Exponential Weighted Moving Average Algorithm

This article explains the exponential weighted moving average (EWMA) as a practical time‑series approximation method, detailing its motivation, recursive formula, weight decay behavior, typical beta values, and a bias‑correction technique that improves early‑stage estimates.

Beta ParameterBias CorrectionExponential Weighted Moving Average
0 likes · 7 min read
Intuitive Explanation of the Exponential Weighted Moving Average Algorithm
37 Interactive Technology Team
37 Interactive Technology Team
Jul 4, 2025 · Operations

How Dynamic Thresholds with Prophet Transform Monitoring from Static Alerts to Intelligent Insights

Traditional fixed‑threshold monitoring often triggers noisy alerts during routine business rhythms, but by modeling time‑series patterns with Facebook Prophet to predict dynamic confidence intervals, teams can automatically adjust thresholds, reduce false positives, and accurately detect true anomalies across diverse services.

ProphetTime Seriesanomaly detection
0 likes · 7 min read
How Dynamic Thresholds with Prophet Transform Monitoring from Static Alerts to Intelligent Insights
Architecture & Thinking
Architecture & Thinking
May 15, 2025 · Databases

Redis 8.0 Unveiled: New AGPLv3 License, Vector Search, JSON & More

Redis 8.0, released on May 1 2025, introduces a major license shift to AGPL‑v3, adds eight native data structures—including vector sets, JSON, and time‑series—enhances the query engine with up to 16× performance gains, improves scalability, security, and cloud‑native support, and provides extensive code examples for AI and real‑time analytics.

JSONTime Seriesdatabase
0 likes · 15 min read
Redis 8.0 Unveiled: New AGPLv3 License, Vector Search, JSON & More
MaGe Linux Operations
MaGe Linux Operations
May 7, 2025 · Operations

Master PromQL: From Basics to Advanced Query Techniques for Monitoring

This comprehensive guide walks you through PromQL fundamentals, data types, query expressions, selectors, operators, aggregation, and essential functions, illustrating each concept with real‑world monitoring scenarios and code examples to help you effectively query and analyze time‑series data in Prometheus.

PromQLPrometheusTime Series
0 likes · 32 min read
Master PromQL: From Basics to Advanced Query Techniques for Monitoring
JD Tech
JD Tech
Apr 1, 2025 · Artificial Intelligence

Self‑Isolation Mechanism for Time‑Series Anomaly Detection with Memory Space

This article presents a self‑isolation based streaming anomaly detection framework that combines memory‑space indexing to capture pattern anomalies, long‑term memory, and concept drift in time‑series data, and validates the approach with public benchmarks and real‑world risk‑control scenarios.

Time Seriesanomaly detectionconcept drift
0 likes · 24 min read
Self‑Isolation Mechanism for Time‑Series Anomaly Detection with Memory Space
Python Programming Learning Circle
Python Programming Learning Circle
Mar 24, 2025 · Artificial Intelligence

Comprehensive List of Aggregation Functions and Custom Feature Engineering Utilities for Python

This article presents a detailed collection of built‑in pandas aggregation methods and numerous custom Python functions for time‑series feature engineering, offering beginners practical tools to enhance data preprocessing and model performance in machine‑learning projects.

Time Seriesaggregation functionsfeature engineering
0 likes · 10 min read
Comprehensive List of Aggregation Functions and Custom Feature Engineering Utilities for Python
Alibaba Cloud Observability
Alibaba Cloud Observability
Mar 13, 2025 · Databases

How MetricStore 2.0 Redefines Cloud‑Native Time‑Series Storage Performance

MetricStore 2.0 introduces a comprehensive overhaul of memory, file, compute, and transport layers for cloud‑native time‑series data, delivering higher compression, lower latency, multi‑tenant resource control, and support for dynamic schemas, while addressing the scalability limits of its 1.0 predecessor.

ObservabilityTime Seriescloud-native
0 likes · 21 min read
How MetricStore 2.0 Redefines Cloud‑Native Time‑Series Storage Performance
JD Retail Technology
JD Retail Technology
Mar 11, 2025 · Artificial Intelligence

Can Self‑Isolation Streams Detect Anomalies Faster? A Deep Dive into Time‑Series Anomaly Detection

This article presents a comprehensive analysis of a self‑isolation‑based streaming anomaly detection framework, covering business motivations, existing techniques, technical challenges such as pattern anomalies, long‑term memory and concept drift, the core self‑isolation mechanism, memory‑space architecture, experimental evaluations, and practical risk‑control applications.

Time Seriesanomaly detectionconcept drift
0 likes · 28 min read
Can Self‑Isolation Streams Detect Anomalies Faster? A Deep Dive into Time‑Series Anomaly Detection
JD Tech Talk
JD Tech Talk
Feb 27, 2025 · Artificial Intelligence

Can Self‑Isolation Streams Detect Real‑Time Anomaly Patterns?

This article presents a comprehensive study of streaming‑time‑series anomaly detection, introducing a self‑isolation mechanism combined with a memory space to capture pattern anomalies, handle concept drift, and reduce false alarms, supported by extensive experiments on public datasets and real‑world risk‑control scenarios.

Time Seriesanomaly detectionconcept drift
0 likes · 27 min read
Can Self‑Isolation Streams Detect Real‑Time Anomaly Patterns?
JD Cloud Developers
JD Cloud Developers
Feb 27, 2025 · Artificial Intelligence

Self-Isolation Streams: Boosting Real-Time Anomaly Detection for Time-Series

This article presents a comprehensive study of time‑series anomaly detection using a self‑isolation mechanism combined with a memory‑space architecture, addressing pattern anomalies, long‑term memory, and concept drift, and demonstrates its effectiveness through extensive experiments and real‑world risk‑control scenarios.

Time Seriesanomaly detectionconcept drift
0 likes · 28 min read
Self-Isolation Streams: Boosting Real-Time Anomaly Detection for Time-Series
Python Crawling & Data Mining
Python Crawling & Data Mining
Jan 28, 2025 · Fundamentals

Master Pandas: From Data Import to Advanced Manipulation in Python

This tutorial walks you through pandas fundamentals—including reading CSV/Excel files, creating Series and DataFrames, performing basic operations, cleaning data, using loc/iloc indexing, grouping, concatenating, merging, and handling time series—providing code examples and visual outputs for each step.

Time Seriesdata cleaninggroupby
0 likes · 14 min read
Master Pandas: From Data Import to Advanced Manipulation in Python
Soul Technical Team
Soul Technical Team
Jan 24, 2025 · Operations

Migration from Thanos to VictoriaMetrics: Architecture, Plan, Issues, and Benefits

This article details the end‑to‑end migration from Thanos to VictoriaMetrics, covering background analysis, architectural comparison, a phased migration plan, encountered configuration and performance issues, resolution strategies, and the resulting performance, cost, and scalability improvements for the monitoring system.

ThanosTime SeriesVictoriaMetrics
0 likes · 16 min read
Migration from Thanos to VictoriaMetrics: Architecture, Plan, Issues, and Benefits
Architect
Architect
Sep 27, 2024 · Artificial Intelligence

How AI Detects and Diagnoses Anomalies in Ctrip Train Ticket Metrics

This article presents a comprehensive AI‑driven system for automatically detecting anomalies in over 1,000 Ctrip train‑ticket business metrics and pinpointing their root causes, detailing the background, unsupervised algorithms, detection and attribution pipelines, practical results, and future improvements.

AI anomaly detectionCtripRoot Cause Analysis
0 likes · 21 min read
How AI Detects and Diagnoses Anomalies in Ctrip Train Ticket Metrics
Python Programming Learning Circle
Python Programming Learning Circle
Sep 10, 2024 · Artificial Intelligence

Time Series Feature Engineering Techniques in Python

This article explains how to extract a variety of date‑time based features—including date, time, lag, rolling, expanding, and domain‑specific attributes—from a time‑series dataset using pandas, and discusses proper validation strategies for building reliable forecasting models.

Time Seriesfeature engineeringforecasting
0 likes · 14 min read
Time Series Feature Engineering Techniques in Python
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Aug 27, 2024 · Artificial Intelligence

How AI Detects Cluster-Wide Task Slowdowns in Cloud Systems

A new AI‑driven method for detecting cluster‑wide task slowdowns in cloud platforms improves F1 score by 5.3% over state‑of‑the‑art techniques, addressing challenges of composite periodic patterns, training data contamination, and focusing on slowdown anomalies.

Neural NetworksTime SeriesUnsupervised Learning
0 likes · 8 min read
How AI Detects Cluster-Wide Task Slowdowns in Cloud Systems
Python Crawling & Data Mining
Python Crawling & Data Mining
Aug 15, 2024 · Fundamentals

Master Pandas: Essential Data Manipulation Techniques for Beginners

This comprehensive tutorial walks you through pandas basics, including reading CSV and Excel files, creating Series and DataFrames, performing data inspection, cleaning, indexing, hierarchical indexing, time‑series handling, grouping, aggregation, concatenation, merging, and practical code examples with visual outputs.

Time Seriesdata cleaninggroupby
0 likes · 12 min read
Master Pandas: Essential Data Manipulation Techniques for Beginners
Baidu Geek Talk
Baidu Geek Talk
Aug 7, 2024 · Artificial Intelligence

Detecting Time‑Series Anomalies in Embedding Space: A Practical AI Approach

This article presents an embedding‑based method for time‑series anomaly detection in security and anti‑cheat scenarios, explains how to vectorise logs, sample and compute distribution features, details implementation code, and validates the approach with four synthetic experiments showing precision‑recall improvements at day and hour granularity.

EmbeddingSecurityTime Series
0 likes · 12 min read
Detecting Time‑Series Anomalies in Embedding Space: A Practical AI Approach
DataFunTalk
DataFunTalk
Aug 1, 2024 · Artificial Intelligence

Ant Group's Time Series AI Practices: AntFlux Engine and Real‑World Applications

This article presents Ant Group's comprehensive time‑series AI solutions, detailing the AntFlux platform, the evolution from statistical to deep and large‑scale models—including Time‑LLM, iTransformer, and SLOTH—and illustrating how these technologies empower business insight, forecasting, decision‑making, and green computing across diverse scenarios.

AntFluxTime Seriesforecasting
0 likes · 17 min read
Ant Group's Time Series AI Practices: AntFlux Engine and Real‑World Applications
ITPUB
ITPUB
Jul 22, 2024 · Operations

How We Upgraded Watcher to Second‑Level Monitoring for Real‑Time Order Alerts

This article details the end‑to‑end redesign of Quora Travel's Watcher monitoring platform from minute‑level to second‑level precision, covering architectural changes, storage engine migration, client‑side metric collection, server‑side scheduling, dashboard and alarm adaptations, and the resulting operational improvements.

DevOpsObservabilityTime Series
0 likes · 20 min read
How We Upgraded Watcher to Second‑Level Monitoring for Real‑Time Order Alerts
Model Perspective
Model Perspective
Jun 26, 2024 · Artificial Intelligence

Unlocking Fraud Detection: Build a Hidden Markov Model with Python

This article explains the fundamentals and mathematics of Hidden Markov Models, illustrates their core components and basic problems, and walks through a complete Python implementation for credit‑card fraud detection, including data preparation, model training, and evaluation.

Hidden Markov ModelPythonTime Series
0 likes · 10 min read
Unlocking Fraud Detection: Build a Hidden Markov Model with Python
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
Jun 5, 2024 · Artificial Intelligence

LARA: A Light, Anti‑Overfitting Retraining Method for Unsupervised Time‑Series Anomaly Detection

The LARA approach, presented at WWW2024, offers a lightweight, anti‑overfitting retraining solution for unsupervised time‑series anomaly detection in cloud services, achieving state‑of‑the‑art accuracy with minimal new data and dramatically reducing training overhead.

Cloud AITime SeriesUnsupervised Learning
0 likes · 5 min read
LARA: A Light, Anti‑Overfitting Retraining Method for Unsupervised Time‑Series Anomaly Detection
Python Programming Learning Circle
Python Programming Learning Circle
May 23, 2024 · Artificial Intelligence

Comprehensive Collection of Aggregation Functions for Feature Engineering in Python

This article presents a detailed compilation of pandas built‑in aggregation methods and a wide range of custom Python functions for time‑series feature engineering, providing ready‑to‑use code snippets that cover statistical descriptors, drawdown metrics, peak detection, and more for data science practitioners.

PythonTime Seriesaggregation
0 likes · 17 min read
Comprehensive Collection of Aggregation Functions for Feature Engineering in Python
Alibaba Cloud Big Data AI Platform
Alibaba Cloud Big Data AI Platform
May 7, 2024 · Artificial Intelligence

How Alibaba’s New Time‑Series Models Are Redefining Forecasting and Anomaly Detection

Alibaba Cloud’s big‑data research team announced four groundbreaking time‑series papers accepted at ICLR 2024, ICDE 2024 and WWW 2024, introducing models such as Pathformer, ContraLSP, MACE, and LARA that advance multi‑scale forecasting, explainable AI, and efficient anomaly detection for intelligent operations.

AITime Seriesanomaly detection
0 likes · 11 min read
How Alibaba’s New Time‑Series Models Are Redefining Forecasting and Anomaly Detection
DataFunTalk
DataFunTalk
Mar 19, 2024 · Big Data

High‑Performance Vehicle IoT Big Data Platform Solution Based on DolphinDB

This article presents a comprehensive vehicle‑IoT big‑data platform solution that outlines required capabilities, describes a DolphinDB‑based architecture, shares a real‑world case of 1.8 × 10⁸ writes per second, and provides step‑by‑step deployment and query scripts for rapid verification.

Big DataData AnalyticsDolphinDB
0 likes · 18 min read
High‑Performance Vehicle IoT Big Data Platform Solution Based on DolphinDB
HelloTech
HelloTech
Mar 14, 2024 · Artificial Intelligence

Feature Engineering: Concepts, Methods, and Automation

Feature engineering transforms existing data into new predictive variables through manual analysis or automated pipelines, encompassing single‑variable encoding, pairwise arithmetic, group‑statistics, multi‑variable combinations, time‑series and text derivations, with tools like Deep Feature Synthesis and beam‑search to generate and select useful features.

Time Seriesautomated featuresdata preprocessing
0 likes · 17 min read
Feature Engineering: Concepts, Methods, and Automation
DataFunSummit
DataFunSummit
Feb 12, 2024 · Artificial Intelligence

Ant Group's Time Series AI Practices and the AntFlux Intelligent Engine

This article presents Ant Group's comprehensive time‑series AI solutions, covering the business value of temporal data, the evolution of statistical and deep learning models, large‑scale time‑series platforms such as AntFlux, and real‑world applications ranging from financial forecasting to green computing.

AIAntFluxTime Series
0 likes · 17 min read
Ant Group's Time Series AI Practices and the AntFlux Intelligent Engine
Model Perspective
Model Perspective
Feb 1, 2024 · Artificial Intelligence

Discover Top Change & Prediction Model Articles for AI and Data Science

This article compiles a categorized list of recent model papers, covering change models and various prediction models—including time series, machine learning, gray prediction, and deep learning—providing direct references for students and researchers interested in AI and data‑driven modeling.

PredictionTime Seriesartificial intelligence
0 likes · 6 min read
Discover Top Change & Prediction Model Articles for AI and Data Science
Baidu Geek Talk
Baidu Geek Talk
Jan 29, 2024 · Databases

BTS (Baidu Table Storage): Architecture and Core Technologies

BTS (Baidu Table Storage) is Baidu Intelligent Cloud’s high‑performance, low‑cost semi‑structured NoSQL service that evolved from single‑table to multi‑model (wide tables, time‑series, soon documents), featuring a three‑layer compute‑storage separation architecture, multi‑level caching, hot‑backup HA, and supporting massive IoT, AI, autonomous‑driving and monitoring workloads.

BTSBaidu Table StorageDatabase Architecture
0 likes · 21 min read
BTS (Baidu Table Storage): Architecture and Core Technologies
dbaplus Community
dbaplus Community
Jan 2, 2024 · Operations

How Xiaohongshu Scaled Its Metrics System Tenfold with Cloud‑Native Architecture

Facing exploding metric volumes, high resource consumption, and fragile operations, Xiaohongshu's observability team completely rebuilt its metrics pipeline using Victoriametrics, achieving ten‑fold performance gains, minute‑level scaling, high‑availability, cost reduction, and robust multi‑cloud active‑active deployment while preserving data safety and query speed.

ObservabilityPrometheusTime Series
0 likes · 34 min read
How Xiaohongshu Scaled Its Metrics System Tenfold with Cloud‑Native Architecture
AntTech
AntTech
Dec 14, 2023 · Artificial Intelligence

Highlights of Ant Group’s 20 Accepted Papers at NeurIPS 2023

The article summarizes Ant Group's twenty accepted NeurIPS 2023 papers, covering advances in generative AI, time‑series forecasting, 3D image synthesis, and other machine‑learning topics, and provides brief overviews of three highlighted works along with links to the remaining studies.

3D Image SynthesisAnt GroupNeurIPS
0 likes · 10 min read
Highlights of Ant Group’s 20 Accepted Papers at NeurIPS 2023
Xiaohongshu Tech REDtech
Xiaohongshu Tech REDtech
Dec 14, 2023 · Cloud Native

Evolution of Xiaohongshu Metrics System: Cloud‑Native Observability, High Availability, and Performance Optimizations

Xiaohongshu’s observability team rebuilt its Prometheus‑based metrics platform using vmagent, dual‑active HA clusters, query push‑down, high‑cardinality governance and multi‑cloud active‑active design, delivering ten‑fold collection speed, up to 70× query capacity, massive CPU‑memory‑storage savings and fully automated scaling.

Time SeriesVictoriaMetricscloud-native
0 likes · 35 min read
Evolution of Xiaohongshu Metrics System: Cloud‑Native Observability, High Availability, and Performance Optimizations
Alibaba Cloud Developer
Alibaba Cloud Developer
Nov 8, 2023 · Cloud Native

How SLS Boosted Prometheus Query Performance Over 10× with Cloud‑Native Innovations

This article details the recent technical upgrades to Alibaba Cloud's SLS Prometheus storage engine, describing how compatibility with PromQL was retained while achieving more than tenfold query speed improvements, reducing costs through smarter aggregation writes, built‑in downsampling, global caching, parallel computation, and push‑down processing, and presenting benchmark comparisons with open‑source solutions.

Cloud NativePrometheusTime Series
0 likes · 17 min read
How SLS Boosted Prometheus Query Performance Over 10× with Cloud‑Native Innovations
Ctrip Technology
Ctrip Technology
Oct 19, 2023 · Artificial Intelligence

Anomaly Detection and Root Cause Analysis System for Ctrip Train Ticket Business Metrics

This article presents an AI‑driven system that automatically detects anomalies in over 1,000 Ctrip train‑ticket business metrics using six unsupervised algorithms and locates their root causes through a hard‑voting ensemble of four specialized methods, demonstrating practical results and future enhancements.

CtripRoot Cause AnalysisTime Series
0 likes · 18 min read
Anomaly Detection and Root Cause Analysis System for Ctrip Train Ticket Business Metrics
Liangxu Linux
Liangxu Linux
Oct 11, 2023 · Databases

Beyond MySQL: A Practical Guide to 10+ Database Types and Their Ideal Use‑Cases

This article provides a concise yet comprehensive overview of relational, key‑value, document, search‑engine, time‑series, vector, spatial, graph, columnar, and multimodel databases, explaining their data models, typical queries, core advantages, and popular implementations to help developers choose the right storage solution for any project.

ColumnarNoSQLRelational
0 likes · 16 min read
Beyond MySQL: A Practical Guide to 10+ Database Types and Their Ideal Use‑Cases
Test Development Learning Exchange
Test Development Learning Exchange
Sep 12, 2023 · Artificial Intelligence

Various Anomaly Detection Techniques with Python Code Examples

This article introduces ten common anomaly detection approaches—including statistical thresholds, boxplots, clustering, isolation forest, LOF, collaborative filtering, robust covariance, NLP, computer‑vision, and time‑series methods—each accompanied by concise Python code snippets illustrating how to identify outliers in different data domains.

PythonTime Seriesanomaly detection
0 likes · 9 min read
Various Anomaly Detection Techniques with Python Code Examples
IT Services Circle
IT Services Circle
Aug 26, 2023 · Databases

An Overview of Different Types of Databases

This article introduces and compares major database categories—including relational, key‑value, document, columnar, graph, and time‑series databases—explaining their structures, typical use cases, and advantages, helping readers understand when to choose each type for various applications.

DocumentKey-ValueNoSQL
0 likes · 7 min read
An Overview of Different Types of Databases
Network Intelligence Research Center (NIRC)
Network Intelligence Research Center (NIRC)
Aug 19, 2023 · Artificial Intelligence

Detecting Time‑Series Anomalies with the Anomaly Transformer’s Association Discrepancy

The article explains how the Anomaly Transformer leverages prior‑ and series‑association discrepancies, a learnable Gaussian kernel, and a Minimax training strategy to distinguish normal from abnormal points in time‑series data, achieving state‑of‑the‑art results on five benchmark datasets.

Association DiscrepancyMinimax TrainingSOTA
0 likes · 6 min read
Detecting Time‑Series Anomalies with the Anomaly Transformer’s Association Discrepancy
Model Perspective
Model Perspective
Aug 13, 2023 · Artificial Intelligence

Unlocking Hidden Markov Models: Theory, Algorithms, and Python Implementations

This article explains Hidden Markov Models, covering their core concepts, basic elements, the three fundamental problems with forward, Viterbi, and Baum‑Welch algorithms, provides a weather illustration, detailed Python code using hmmlearn, and a real‑world earthquake case study, highlighting practical implementation steps.

HMMHidden Markov ModelPython
0 likes · 15 min read
Unlocking Hidden Markov Models: Theory, Algorithms, and Python Implementations
Ctrip Technology
Ctrip Technology
Aug 3, 2023 · Operations

Intelligent Anomaly Detection for Ctrip Operations: LSTM Forecasting, Trend Analysis, Adaptive Thresholds, and Periodic Anomaly Filtering

The article describes Ctrip's AIOps approach to improving alert quality by combining statistical methods and machine‑learning models such as LSTM, trend analysis, adaptive threshold calculation, and dynamic‑time‑warping based periodic anomaly detection, achieving significant gains in precision and fault‑recall rates.

LSTMTime Seriesadaptive threshold
0 likes · 12 min read
Intelligent Anomaly Detection for Ctrip Operations: LSTM Forecasting, Trend Analysis, Adaptive Thresholds, and Periodic Anomaly Filtering
DataFunTalk
DataFunTalk
Jul 31, 2023 · Operations

Applying Causal Inference to Inventory Management: Demand Forecasting and Strategy Implementation

This article explores how causal inference techniques, including dynamic Bayesian networks and time‑series models, can be used to improve demand forecasting and replenishment strategies in inventory management, offering both theoretical concepts and practical case studies for operational decision‑making.

Demand ForecastingOperations ResearchTime Series
0 likes · 14 min read
Applying Causal Inference to Inventory Management: Demand Forecasting and Strategy Implementation
Bitu Technology
Bitu Technology
Jul 7, 2023 · Artificial Intelligence

Building a KPI Alert System with Matrix Profiling and MACD at Tubi

An in‑depth case study describes how Tubi’s data‑science team built a flexible KPI alert system that tackles seasonal trends and diverse metric scales by applying seasonal decomposition, Matrix Profiling via the Stumpy library for anomaly detection, and MACD for trend analysis, achieving higher true‑positive rates while reducing false alarms.

KPI monitoringMACDTime Series
0 likes · 11 min read
Building a KPI Alert System with Matrix Profiling and MACD at Tubi
DataFunTalk
DataFunTalk
May 10, 2023 · Artificial Intelligence

AI‑Driven Predictive Maintenance for NIO Power: GAN and Conceptor Techniques for PHM

This article presents NIO Power's intelligent equipment health management solution, detailing business background, operational challenges, PHM difficulties, and frontier AI technologies such as GAN‑based unsupervised anomaly detection and Conceptor‑based small‑sample fault diagnosis, illustrated with real‑world case studies and a comprehensive Q&A.

ConceptorGANNIO Power
0 likes · 28 min read
AI‑Driven Predictive Maintenance for NIO Power: GAN and Conceptor Techniques for PHM
ITPUB
ITPUB
Apr 28, 2023 · Databases

Why Time Series Databases Are Revolutionizing IoT and Industry

This article explains what time series databases are, outlines their key characteristics, traces their evolution from early real‑time databases to modern solutions, and examines current technical innovations and market trends driving their rapid adoption across IoT, finance, and industrial sectors.

AIIoTTime Series
0 likes · 11 min read
Why Time Series Databases Are Revolutionizing IoT and Industry
MaGe Linux Operations
MaGe Linux Operations
Mar 30, 2023 · Operations

Demystifying PromQL: How Nested Functional Queries Work in Prometheus

This article explores the structure and evaluation of PromQL queries, covering its nested functional language nature, expression types, time handling with instant and range queries, and practical examples using the PromLens visualizer, helping readers grasp how Prometheus processes and types queries.

ObservabilityPromQLTime Series
0 likes · 11 min read
Demystifying PromQL: How Nested Functional Queries Work in Prometheus
DataFunSummit
DataFunSummit
Mar 22, 2023 · Artificial Intelligence

Sales Forecasting in Alibaba Health's Pharmaceutical E‑commerce: Business Background, Algorithm Solutions, and Scenario Exploration

The article details a comprehensive presentation on Alibaba Health's pharmaceutical e‑commerce sales forecasting, covering supply‑chain challenges, the evolution of time‑series prediction methods, a full data‑to‑model pipeline, change‑point detection, handling imbalanced data, multi‑model fusion, and specialized seasonal and long‑sequence forecasting techniques.

Alibaba HealthSales ForecastingTime Series
0 likes · 16 min read
Sales Forecasting in Alibaba Health's Pharmaceutical E‑commerce: Business Background, Algorithm Solutions, and Scenario Exploration
Top Architect
Top Architect
Mar 8, 2023 · Databases

Deep Dive into Prometheus V2 Storage Engine and Query Process

This article explains the internal storage layout, on‑disk and in‑memory data structures, and the query execution flow of Prometheus V2, illustrating how blocks, chunks, WAL, indexes and postings are organized and accessed to serve time‑series queries efficiently.

GoPrometheusStorage Engine
0 likes · 15 min read
Deep Dive into Prometheus V2 Storage Engine and Query Process
Python Programming Learning Circle
Python Programming Learning Circle
Nov 22, 2022 · Artificial Intelligence

Using tsfresh for Automated Time Series Feature Extraction in Python

This article introduces the tsfresh Python package, explains why traditional machine‑learning models struggle with time‑series data, and demonstrates how tsfresh can automatically generate and select hundreds of useful features—including statistical, nonlinear, and signal‑processing metrics—while supporting big‑data frameworks such as Dask and Spark.

PythonTime Seriesfeature engineering
0 likes · 5 min read
Using tsfresh for Automated Time Series Feature Extraction in Python
JD Cloud Developers
JD Cloud Developers
Nov 7, 2022 · Artificial Intelligence

Detecting Time‑Series Anomalies Without Thresholds Using LSTM and Unsupervised Fusion

This article presents a threshold‑free anomaly detection framework for streaming time series that combines an LSTM‑based baseline module with an unsupervised detection module, detailing the architecture, training process, data preprocessing, and experimental results that demonstrate superior accuracy and F1 scores.

Deep LearningLSTMTime Series
0 likes · 15 min read
Detecting Time‑Series Anomalies Without Thresholds Using LSTM and Unsupervised Fusion
DataFunSummit
DataFunSummit
Sep 28, 2022 · Big Data

Elasticsearch Time Series Engine: Practices, Challenges, and Alibaba Cloud TimeStream

This article presents a comprehensive overview of using Elasticsearch as a time series engine, covering its motivations, challenges, key features, Alibaba Cloud TimeStream optimizations such as columnar storage, LSM structures, downsampling, and integration with Prometheus and Grafana, while also discussing performance and cost considerations.

Big DataDownsamplingElasticsearch
0 likes · 15 min read
Elasticsearch Time Series Engine: Practices, Challenges, and Alibaba Cloud TimeStream
Model Perspective
Model Perspective
Sep 25, 2022 · Artificial Intelligence

Mastering ARCH and GARCH Models in Python: From Theory to Forecasting

This guide explains the limitations of ARIMA‑type models for handling changing variance, introduces ARCH and GARCH as solutions, and walks through Python implementations—including data generation, model fitting, and forecasting—complete with code snippets and visualizations.

ArchGARCHPython
0 likes · 7 min read
Mastering ARCH and GARCH Models in Python: From Theory to Forecasting
Model Perspective
Model Perspective
Sep 9, 2022 · Fundamentals

What Is a Time Series and How Do We Analyze Its Patterns?

A time series is a chronologically ordered set of interrelated data points whose analysis involves studying its development patterns and forecasting future behavior, with classifications based on dimensionality, continuity, statistical properties such as stationarity, and distribution types like Gaussian or non‑Gaussian.

Time Seriesforecastingmultivariate
0 likes · 2 min read
What Is a Time Series and How Do We Analyze Its Patterns?