Tagged articles
model selection
79 articles · Page 1 of 1
Analyzing LiteLLM's 2026 supply-chain attacks, this article reveals three structural risks of self-hosted LLM proxies—centralized keys, privileged runtime, and unrestricted extensions—and shows how Wasm-sandboxed AI gateways with immutable releases, serverless operations, fallback routing, and intelligent model selection eliminate these hidden costs while cutting latency and spend.
AI gatewayFinOpsLLM proxy
0 likes · 16 min read

The author benchmarks Claude Fable 5.2 against Opus 5.5, Kimi K3.1 Pro, and DeepSeek V4.1 Flash on a complex video generation prompt, comparing metrics like time, token usage, and output quality, then provides an 18-point analysis covering constraint handling, engineering granularity, self-verification, planning, safety boundaries, benchmark results, code refactoring, and cost-effectiveness.
AI Model ComparisonClaude Fable 5.2benchmarking
0 likes · 18 min read

HiRoute's new release introduces per-step model routing with a three-question decision framework, continuous trust-level evaluation of new models using real workflow evidence, task delegation to specialized agents, and cross-platform GUI support, all running locally and open-source.
Agent RoutingHiRouteLLM Evaluation
0 likes · 27 min read

After two years testing AI coding tools, the author recommends Codex for its instant interrupt feature, parallel agent execution via git worktree, persistent project rules via AGENTS.md, cloud-based background tasks, sandbox safety, and cost-effective model selection, while noting caveats like reasoning intensity limits and AGENTS.md size constraints.
AGENTS.mdAI coding assistantCodex
0 likes · 9 min read


liandkOct 13, 2026 · Artificial Intelligence
This article details real-world pitfalls when deploying large language models locally on Mac using Ollama, covering memory overflow causes, key parameter tuning (num_ctx, num_parallel, num_gpu), quantization level selection, model recommendations for coding vs chat, and monitoring strategies to avoid swap-induced performance degradation.
LLM DeploymentMacOllama
0 likes · 14 min read

The article analyzes Claude Sonnet 5.5's 70.6% Terminal-Bench 4.0 score, revealing it only surpasses Opus 5.5 at $13 per task via brute-force retries, while Opus dominates at practical $1-8 budgets; it maps scores to DevOps task complexity and provides a four-quadrant model selection matrix based on blast radius and state depth.
Claude Sonnet 5.5DevOpsOpus 5.5
0 likes · 19 min read

This article reviews Alibaba's new Qoder desktop app, an AI task workstation with programming and general modes, demonstrating building a Vue3 admin system with browser integration, model selection, BYOK support, and annotation-based UI iteration.
AI coding assistantAI task workstationBYOK
0 likes · 10 min read

Terminal-Bench 4.0 reveals that excessive reasoning (max) reduces accuracy for top models like Opus 5.5 and GPT-6 Astra due to overthinking traps—agent drift, over-engineering, context dilution, and self-doubt—while high-end models at medium reasoning outperform mid-tier models at max reasoning at lower cost.
AI EngineeringLLM reasoningPareto frontier
0 likes · 19 min read

OpenAI launched GPT-6 Sol and Luna while Anthropic released Claude Opus 5.5, all emphasizing lower costs and improved capabilities; the article compares pricing, benchmarks, cache economics, and independent evaluations, advising developers to test models on their own tasks to verify real-world cost per qualified result.
Claude Opus 5.5GPT-6LLM pricing
0 likes · 14 min read


TonyBaiSep 3, 2026 · Artificial Intelligence
Uber's engineering blog reveals how they scaled AI agent usage 9.4x while keeping costs flat by decomposing total spend into six measurable variables, optimizing model selection via benchmarks, reducing token consumption through CLI-based MCP calls and Code-Mode, leveraging a 24M-node context graph, and implementing real-time cost visibility for engineers.
AI agentsCode-ModeContext Graph
0 likes · 26 min read

Databricks shifts AI coding agents from always using the most powerful model to a task‑aware Smart Routing system that selects both model and harness, cutting per‑task costs by up to 56% while maintaining performance, as shown by internal and public benchmarks.
AI coding agentCost OptimizationDatabricks
0 likes · 10 min read

As the number of LLMs grows, developers face the dilemma of selecting the right model for each request; Alibaba Cloud’s AI Gateway introduces intelligent routing that evaluates model capabilities, cost, speed, and task suitability, making a single, optimal decision per request while preserving context in multi‑turn and Agent workflows.
AI gatewayAlibaba CloudProfile Optimization
0 likes · 11 min read

This article dissects how to build a production‑grade AI auto‑programming system—covering the tasks junior developers spend their time on, a four‑layer architecture, core modules, model tiering, context engineering, toolchain integration, multi‑stage quality checks, and current limitations.
AI programmingcode generationcontext engineering
0 likes · 15 min read

The article details how OpenCode AI, combined with DigitalOcean's inference router, built a full‑featured Godot 4 penalty‑shootout game in a few hours, routing 596 tasks across cheap open‑source models, cutting token costs from $123 to $8.25 while revealing model performance, latency, and when to prefer frontier models.
AI codingCost OptimizationGodot
0 likes · 22 min read

Boris Cherny outlines 13 concrete engineering practices—spanning standardization, automated verification, workflow acceleration, and feedback loops—that transform Claude Code from a clever code generator into a reliable, cost‑effective productivity tool for software teams, complete with real‑world metrics and step‑by‑step guidance.
AI toolingCI/CDClaude Code
0 likes · 29 min read

The article explains how to select an embedding model by evaluating language support, vector dimension, context length, and performance metrics, provides concrete model examples for Chinese and multilingual scenarios, compares storage costs, and recommends starting with open‑source models before considering commercial APIs.
EmbeddingVector Dimensioncontext length
0 likes · 6 min read


Yunqi AI+Jul 11, 2026 · Artificial Intelligence
The article breaks down the 2026 mid‑year AI model landscape, compares tiered pricing across major providers, and offers concrete selection rules, caching tricks, tool‑chain setups, and habit‑based practices that together let teams minimize spend while maintaining high‑quality output.
AI modelsCachingClaude
0 likes · 12 min read

With AI‑generated code now accounting for 55.87% of the 2,000 monthly change requests in the cloud‑storage front‑end team, traditional code review pressure has surged, prompting the team to embed a multi‑agent AICR gate into the CI/CD pipeline that automates context extraction, parallel AI inspections, verification, and feedback while controlling latency and mis‑reports.
AI code reviewAICRCI/CD
0 likes · 32 min read

Microsoft's new MAI‑Code‑1‑Flash model is now available in IntelliJ, signaling a shift for Java developers from using a single, heavyweight AI model for all tasks to selecting fast, task‑specific models that improve iteration speed, reduce costs, and better match the risk profile of each coding activity.
AI codingCopilotJava
0 likes · 19 min read

The article analyzes how strict compliance, data‑security, and rigorous business requirements reshape financial large‑model deployments, detailing a PageIndex‑based retrieval architecture, engineering pitfalls such as rule explosion and prompt bloat, model‑selection trade‑offs, and forward‑looking agent‑centric designs.
Agentic AIRetrieval Augmentationfinancial AI
0 likes · 11 min read

Artificial Analysis provides an independent, reproducible benchmarking platform for voice AI, offering objective WER scores for ASR, Elo‑based blind‑listening scores for TTS, and three‑dimensional metrics for end‑to‑end speech dialogue, together with detailed methodology, top‑model rankings, and practical guidance for developers to choose the most suitable model and provider for their scenarios.
AI voice evaluationASRArtificial Analysis
0 likes · 14 min read

The article explains how to use the neuron-core/llm-classifier PHP package to define a difficulty score for prompts, calibrate it offline, and then route simple queries to inexpensive LLMs while sending hard queries to powerful models, all without added latency or cost.
LLMPHPRouting
0 likes · 10 min read


Qborfy AIJun 15, 2026 · Artificial Intelligence
This article provides a detailed side‑by‑side comparison of core API parameters such as temperature, top_p, top_k, penalties, max_tokens, tools and response_format across OpenAI, Claude, Gemini, DeepSeek, Kimi, MiniMax and Yi, explains common migration pitfalls, and offers practical guidance for selecting and adapting LLM services.
APILLMcompatibility
0 likes · 24 min read

The author details the deployment of an office AI system on an internal network using eight NVIDIA A800 GPUs, explaining model choices, inference engines, GPU allocations, compatibility issues, and presenting the overall architecture diagram.
AI model deploymentNVIDIA A800inference
0 likes · 3 min read


FunTesterMay 20, 2026 · Artificial Intelligence
The article explains why a single AI agent hits context and execution limits, describes Anthropic’s multi‑agent orchestration that splits tasks among dedicated sub‑agents coordinated by a controller, discusses model selection, communication, observability, and outlines scenarios where parallel orchestration delivers real benefits.
AI agentsMultiAgentParallelism
0 likes · 11 min read

The article explains why a reranking step is essential in RAG pipelines, describes how it refines the initial vector‑search results, compares mainstream rerank techniques, discusses practical engineering choices such as candidate set size and model selection, and outlines how to evaluate and tune rerank performance.
Cross-EncoderEvaluation MetricsLLM
0 likes · 15 min read

This article analyzes why token waste in Claude Code stems mainly from bloated context rather than verbose prompts and presents seven concrete techniques—including model selection, CLAUDE.md management, Subagent usage, precise file targeting, early compacting, context diagnostics, and restrained tool integration—to reduce token consumption by up to 80% while preserving workflow efficiency.
AI coding assistantClaude CodeCompact command
0 likes · 14 min read

This article explains why embedding models are the foundation of RAG pipelines, outlines concrete evaluation metrics such as MTEB v2 scores, latency, throughput and cost, compares a range of commercial and open‑source models, and discusses emerging trends like multimodal and long‑context embeddings.
Embedding ModelsMTEBRAG
0 likes · 13 min read

RouteMoA moves model selection ahead of inference by using a lightweight scorer to predict each model's suitability from the query, dramatically cutting computation cost and latency while preserving or improving accuracy, as demonstrated on a 15‑model pool with up to 90% cost reduction and 64% latency reduction.
ACL 2026Inference OptimizationMixture of Agents
0 likes · 9 min read

The paper introduces RouteMoA, a dynamic routing framework that predicts model capabilities before inference to avoid unnecessary computation, thereby cutting cost by 89.8% and latency by 63.6% while improving accuracy in large‑scale multi‑model pools.
Mixture of AgentsRouteMoAdynamic routing
0 likes · 8 min read

The article presents a practical AI‑driven security audit system for gateway routes that uses a layered “general Agent + business Skill” design, combines batch AI filtering with human verification, achieves full‑coverage, minute‑level detection, and reduces token costs by over 95 % through multiple optimizations.
AI agentAPI SecurityGateway
0 likes · 15 min read


Wuming AIApr 26, 2026 · Artificial Intelligence
The article outlines thirteen actionable strategies—ranging from choosing the right billing plan and trimming context to using layered models, caching, and proper output prompts—to dramatically reduce token consumption and overall expenses when working with AI services.
AICachingContext Management
0 likes · 10 min read

Thunderbolt, an open‑source AI client from Mozilla’s Thunderbird team, lets developers pick any OpenAI‑compatible model, run it on‑premises via Docker or Kubernetes, and keep all conversation data on their own servers, eliminating vendor lock‑in and enhancing privacy.
AI clientDockerKubernetes
0 likes · 6 min read

The article details how a growing Qoder product suite prompted the creation of a fully automated, 24‑hour feedback handling pipeline that classifies, clusters, analyses logs, and even generates fix code using Qoder CLI agents, cutting manual effort from 30 minutes per issue to about two minutes while maintaining human code‑review oversight.
AI automationCost OptimizationDevOps
0 likes · 13 min read

The article analyzes how advancing small‑model capabilities are shifting agent system design from merely checking if a model can run under resource limits to evaluating its suitability for specific tasks, thereby redefining model selection logic and workflow partitioning.
LLM scalingagent systemsmodel selection
0 likes · 7 min read

With more than two million LLMs available, this guide explains how to evaluate functional capabilities, latency, throughput, cost, tool‑calling reliability, context‑window size and compliance, and presents a step‑by‑step framework for picking the most suitable model for each business scenario.
Cost OptimizationLLMTool Calling
0 likes · 25 min read

The article explains the definitions, properties, and asymmetric nature of KL divergence, compares Forward KL (mean‑seeking) and Reverse KL (mode‑seeking) through bimodal examples, and provides practical guidelines for choosing between them based on sampling and probability‑evaluation capabilities in machine‑learning tasks.
KL Divergenceforward KLmachine learning
0 likes · 10 min read

This article analyzes the rapid growth of large language models, presents a six‑dimensional classification framework, compares open‑source and closed‑source options, and offers a step‑by‑step selection checklist for enterprises seeking the most suitable model for their specific needs.
AI DeploymentAI Trendsenterprise AI
0 likes · 10 min read

Discover three practical ways to replace costly, slow Claude Code API calls with domestic large‑language models—DeepSeek, Alibaba Cloud Bailei, and third‑party relay services—offering lower latency, dramatically reduced fees, step‑by‑step configuration, performance benchmarks, and troubleshooting tips for developers.
AI codingClaude CodeCost Optimization
0 likes · 8 min read

This guide shows how the high OpenAI Codex fees can be replaced by domestic large language models—DeepSeek, GLM‑4.7, Qwen3.5 and others—through three practical integration methods, providing step‑by‑step commands, configuration files, performance benchmarks and cost‑saving calculations for individual developers and teams.
AI codingCodex IntegrationCost Optimization
0 likes · 20 min read


SuanNiMar 31, 2026 · Industry Insights
Anthropic’s March 2026 Economic Index analyzes over two million Claude.ai and API conversations, showing how usage is spreading from high‑skill professional tasks to everyday activities, how model choice varies by task value, and how longer‑time users achieve higher success rates, highlighting emerging AI adoption trends and skill gaps.
AI ProductivityAnthropicClaude
0 likes · 15 min read

This article outlines the challenges of manual frontend code review, compares AI-powered CR solutions, details a pipeline integration using Cursor Agent CLI, and provides practical guidelines, model selection tips, and built‑in prompt engineering to automate and improve code quality checks.
AI code reviewCI integrationCursor Agent
0 likes · 12 min read

The article examines the shortcomings of conventional AI evaluation methods, introduces the concept of an "unknown" risk in production settings, and presents SCALE—a continuously updated, high‑fidelity benchmark that stresses large‑model SQL capabilities with real‑world incident data and mixed objective‑subjective scoring.
AI-evaluationSQL benchmarklarge language models
0 likes · 11 min read

The article explains the structure, advantages, and disadvantages of star, snowflake, and constellation data‑warehouse schemas, shares real‑world experiences, and provides practical criteria—performance, team skill, and business scope—to help practitioners select the most suitable model or combine them effectively.
Constellation SchemaDatabase DesignETL
0 likes · 9 min read

The article argues that conventional AI evaluation metrics miss critical unknown risks, outlines three key challenges in AI model selection for database tasks, introduces the SCALE benchmark with real‑world incident data, and explains its mixed evaluation framework that combines objective, subjective, and performance‑driven assessments to guide tech leaders toward reliable SQL‑focused AI solutions.
AI-evaluationDatabase AISCALE benchmark
0 likes · 10 min read

With Ollama 0.17 you can start the powerful OpenClaw AI assistant using a single command, automatically install the software, choose cloud or local models, enable web‑search, connect to multiple messaging platforms, and keep all data private on your own machine.
AI assistantOllamaOpenClaw
0 likes · 10 min read

The 2026 overview details lightweight, heavily quantized open‑source speech‑recognition models and CPU‑specific inference engines, offering concrete tips, model comparisons, and a concise selection guide that enable real‑time, GPU‑free ASR deployment with low latency and high stability.
ASRCPU inferenceSpeech Recognition
0 likes · 4 min read

The article introduces Ollama's new "ollama launch" command, which lets users configure and start programming tools like Claude Code, OpenCode, Codex, and Droid with a single command, and explains quick‑start steps, recommended local and cloud models, and an extended five‑hour cloud coding session.
AI modelsCloud SessionsOllama
0 likes · 6 min read

The article walks through a six‑step framework—defining the product, setting value‑based metrics, acquiring and labeling data, choosing and evaluating models, building an MVP, and creating a growth loop—to guide AI product managers from concept to launch while emphasizing practical trade‑offs and real‑world examples.
AI productMVPdata labeling
0 likes · 10 min read

The article examines the practical difficulties of constructing AI agents, covering SDK selection pitfalls, explicit caching strategies, heavy reliance on reinforcement, failure isolation techniques, virtual file‑system coordination, output‑tool quirks, model trade‑offs, and the ongoing struggle to devise reliable testing and evaluation methods.
AI agentsCachingSDK abstraction
0 likes · 29 min read

This article outlines the motivation, design, architecture, engineering implementation, large‑model selection, and future improvement plans for an AI‑driven experiment analysis agent that integrates data aggregation, modular workflow orchestration, and interactive frontend features to streamline AB‑test insights.
AI agentFrontend DevelopmentWorkflow Design
0 likes · 14 min read

This concise guide presents twelve core AI algorithms—from gradient boosting and deep neural networks to decision trees and K‑nearest neighbors—detailing their strengths, typical applications such as fraud detection, image classification, and price forecasting, and offering practical tips for selecting the right model.
AIAlgorithmsdata science
0 likes · 3 min read

Our team "Stay Overnight" from Chongqing University of Posts and Telecommunications placed second nationally in the 2025 China University Computer Competition Big Data Challenge, navigating volatile financial data, shifting from time‑series to supervised learning, and emphasizing feature engineering to boost model performance.
big datacompetition reportfeature engineering
0 likes · 4 min read


Qborfy AIAug 16, 2025 · Artificial Intelligence
This article explains what tokens are in large language models, how they are counted and priced, compares tokenization methods across major models, and provides practical guidelines and code examples for optimizing token usage and selecting the appropriate model for different scenarios.
AICost OptimizationLLM
0 likes · 8 min read


ArchitectJul 11, 2025 · Artificial Intelligence
OpenAI’s new non‑vectorized Agentic RAG approach replaces traditional vector search with a hierarchical, multi‑round content selection process, leveraging large‑context models like GPT‑4.1‑mini for efficient document loading, dynamic navigation, and accurate answer generation, while outlining model selection strategies, cost trade‑offs, and production considerations.
AI ArchitectureRAGagentic retrieval
0 likes · 15 min read

This article reviews the evolution of AutoML, explains its core principles, compares major Python AutoML libraries with code examples, provides a decision‑making framework and benchmark results, and offers practical guidance on selecting the most suitable tool for different machine‑learning projects.
AutoMLPythonbenchmark
0 likes · 15 min read


ArchitectMar 19, 2025 · Artificial Intelligence
This guide explains how to leverage the Massive Text Embedding Benchmark (MTEB) to identify high‑performing embedding models for Retrieval‑Augmented Generation (RAG) and outlines key factors such as model size, dimension, language support, resource requirements, inference speed, domain suitability, long‑text handling, scalability, and cost.
AIEmbeddingMTEB
0 likes · 12 min read

The article explains how mastering mathematical modeling requires moving beyond surface techniques to develop a deep mindset (“心法”) and long‑term inner skill (“内功”), emphasizing reflective practice, flexible model selection, and continuous improvement for real‑world problem solving.
Learning Strategiesinner skillmathematical modeling
0 likes · 5 min read


CSS MagicOct 29, 2024 · Artificial Intelligence
With a growing array of overseas and domestic LLM APIs in 2024, this guide explains how to pick the right model—starting with a top‑tier option like GPT‑4o for feasibility testing, then moving to cost‑effective or Chinese alternatives, while weighing price, inference speed, context window, API compatibility, and rate limits.
API compatibilityChinese LLMGPT-4o
0 likes · 8 min read

Many participants in math modeling contests fall into the trap of blindly applying familiar models, which limits creativity and leads to mismatched solutions; this article examines the root causes, illustrates with a case study on illegal wildlife trade, and offers practical strategies to deepen problem understanding and foster innovative modeling approaches.
Competitioncase studyinnovation
0 likes · 7 min read

This article outlines practical steps—understanding problem background, gathering quality data, selecting appropriate models, solving and analyzing them, and applying results—to ensure mathematical modeling moves beyond theory and effectively addresses real-world issues.
case studydata collectionmathematical modeling
0 likes · 9 min read

The article examines how large language models can streamline advertising copy creation by addressing format diversity, creativity, and new media demands, detailing model evaluation, fine‑tuning of Chinese‑adapted LLMs—ultimately selecting QWen 1.5‑7B—and showing that deployment boosts copy quality, click‑through and conversion rates while outlining future personalization and data‑efficient scaling.
AICopy GenerationLLM
0 likes · 18 min read

An OCR‑based video review system using PaddleOCR’s DB detector and SVTR recognizer, combined with multi‑level frame deduplication, message‑queue task decoupling, Redis prioritization, and dynamic thread‑pool scheduling, was fine‑tuned on 5 000 samples to cut daily frames from 794 million to 3.6 million, achieving automated detection of over 230 abnormal videos per day and replacing three manual reviewers, with future plans for GPU acceleration and cross‑instance GRPC dispatch.
AIMultithreadingOCR
0 likes · 20 min read

This article explains why causal inference tools are essential for industrial growth, outlines data‑flow standards such as randomized controlled trials, discusses model selection including causal forests and policy learning, and describes evaluation, offline simulation, and resource‑constrained optimization for deploying causal models in production.
AICausal Inferencecausal forest
0 likes · 12 min read

This article explains the fundamentals of modern large language models, outlines the top five most powerful LLMs—including GPT‑4, Claude 2, Llama 2, Orca, and Cohere—and provides practical guidance on selecting and applying them across business and development use cases.
AI applicationsClaude 2GPT-4
0 likes · 9 min read

This guide explains essential evaluation metrics for classification and regression models—including confusion matrix, ROC/AUC, R², and main performance indicators—covers model selection strategies such as train‑validation‑test splits, k‑fold cross‑validation, and regularization techniques, and discusses bias‑variance trade‑offs and diagnostic tools.
Evaluation MetricsRegularizationcross-validation
0 likes · 6 min read

The article explains how combining human expertise with AI techniques—through problem decomposition, model selection, feature engineering, and knowledge‑graph construction—enables practical NLP solutions for document extraction and intelligent Q&A, illustrating the process with contract‑field extraction case studies.
AIDocument ExtractionNLP
0 likes · 14 min read

Mathematical modeling follows a systematic logic—starting from problem definition, variable analysis and hypothesis formation, through model selection, construction, solution, and interpretation—emphasizing quantification, appropriate model application, computational solving, and honest explanation to reliably address complex real‑world problems.
Simulationmodel selectionproblem solving
0 likes · 6 min read

This article explains why residuals of an ARMA model should be white noise, how to use the Q‑test to detect autocorrelation, and how AIC and BIC criteria balance model fit against complexity for selecting the most appropriate ARMA specification.
AICARMABIC
0 likes · 3 min read

This article explains the process of constructing ARMA models, covering model identification, order selection using the AIC criterion, parameter estimation (including Python implementation), and diagnostic testing such as Ljung‑Box, before demonstrating how to generate forecasts from the fitted model.
AICARMATime Series
0 likes · 4 min read

This article introduces regression analysis and explains why it is essential for predictive modeling, then details seven widely used regression techniques—including linear, logistic, polynomial, stepwise, ridge, lasso, and elastic‑net—while offering guidance on selecting the most appropriate model for a given dataset.
Lasso RegressionRidge Regressionlinear regression
0 likes · 13 min read

This article analyzes why gradient‑boosted decision trees frequently outperform neural networks in many Kaggle contests, examining data characteristics, model strengths and weaknesses, real competition examples, and practical guidelines for choosing the right model based on nonlinearity and interpretability.
GBDTKagglemachine learning
0 likes · 9 min read

This article dispels common AI misconceptions, explains when explainability matters, compares deep learning with traditional methods, and offers actionable advice for enterprises on selecting models, AI platforms, and crafting effective AI strategies to stay competitive.
AIenterprise strategyexplainability
0 likes · 11 min read

The article presents a series of insightful diagrams that illustrate core machine‑learning concepts such as the relationship between training and test error, the dangers of under‑ and over‑fitting, Occam’s razor, feature interactions, discriminative versus generative models, loss functions, least‑squares geometry, and sparsity.
Loss Functionsbias‑variancefeature engineering
0 likes · 6 min read

The team from Jilin University, Harbin Institute of Technology, and Beijing University of Posts and Telecommunications shares their winning strategy for the Tencent Advertising Algorithm Competition, detailing their feature engineering, model selection, and future work to handle large‑scale data challenges.
AdvertisingCompetitionTencent
0 likes · 4 min read

The author reflects on six months of learning machine learning, explains that the core techniques are simple while real difficulty lies in applying them to specific problems, and shows how scikit‑learn can quickly address classification, regression, clustering, and dimensionality‑reduction tasks before discussing the need for deeper model and hyper‑parameter tuning.
Classificationhyperparameter tuningmachine learning
0 likes · 3 min read

The ThreeIdiots team shares their experience winning the weekly champion in Tencent's social ads algorithm contest, detailing their feature engineering strategy, time‑based data splitting, handling of large‑scale data, and model choices such as LightGBM and FM, while emphasizing the importance of thoughtful feature extraction over extensive parameter tuning.
Algorithm CompetitionTencentdata splitting
0 likes · 7 min read

The authors share their first‑time competition experience, detailing common pitfalls in feature engineering, data leakage, and model choice, and provide concrete suggestions for beginners and mid‑level teams to improve performance in a social advertising algorithm contest.
Competitionmodel selection
0 likes · 9 min read

This article explains the logical steps of mathematical modeling—from problem definition, variable analysis, and quantification, through model selection, building, solving, and interpretation—highlighting how existing knowledge, appropriate model use, and honest reporting form the core of effective problem solving.
logicmathematical modelingmodel selection
0 likes · 6 min read
