BestHub
Sign in
Tagged articles
18 articles
Page 1 of 1
Qunar Tech Salon
Qunar Tech Salon
Feb 17, 2025 · Artificial Intelligence

Evolution of Qunar Hotel Search Ranking: From LambdaMart to LambdaDNN and Multi‑Objective Optimization

The article details Qunar’s hotel search ranking system evolution, covering the shift from rule‑based sorting to LambdaMart, the adoption of LambdaDNN deep models, multi‑objective MMOE architectures, multi‑scenario integration, extensive feature engineering, and experimental results demonstrating significant offline and online performance gains.

Learning-to-RankRecommendation Systemsdeep-learning
0 likes · 36 min read
Evolution of Qunar Hotel Search Ranking: From LambdaMart to LambdaDNN and Multi‑Objective Optimization
Architect
Architect
May 19, 2022 · Artificial Intelligence

Learning to Rank (LTR) Practice in Amap Search Suggestions: From Data Collection to Model Optimization

This article details Amap's practical experience with Learning to Rank for search suggestions, covering application scenarios, data pipeline construction, feature engineering, model training, loss‑function adjustments, and the resulting performance improvements, while also discussing challenges such as sparse features and click bias.

AmapLearning-to-RankSearch Suggestion
0 likes · 9 min read
Learning to Rank (LTR) Practice in Amap Search Suggestions: From Data Collection to Model Optimization
DataFunSummit
DataFunSummit
Mar 24, 2022 · Artificial Intelligence

An Overview of Learning to Rank (LTR) Models: Point‑wise, Pair‑wise, List‑wise, and Generative Approaches

This article provides a comprehensive introduction to Learning to Rank (LTR), describing its four major categories—point‑wise, pair‑wise, list‑wise, and generative models—along with typical algorithms such as Wide & Deep, ESMM, RankNet, LambdaRank, LambdaMART, DLCM, and miRNN, and discusses their architectures, loss functions, and practical considerations in advertising and recommendation systems.

Generative ModelsLearning-to-RankPairwise
0 likes · 22 min read
An Overview of Learning to Rank (LTR) Models: Point‑wise, Pair‑wise, List‑wise, and Generative Approaches
DataFunTalk
DataFunTalk
Jan 25, 2021 · Artificial Intelligence

Evolution of Zhihu Search Ranking Models: From GBDT to DNN, Multi‑Goal and Context‑Aware LTR

This article reviews the development of Zhihu's search system, describing the transition from early GBDT ranking to deep neural networks, the introduction of multi‑objective and position‑bias‑aware learning‑to‑rank methods, context‑aware techniques, end‑to‑end training, personalization, and future research directions.

DNNDeep LearningGBDT
0 likes · 17 min read
Evolution of Zhihu Search Ranking Models: From GBDT to DNN, Multi‑Goal and Context‑Aware LTR
Yuewen Technology
Yuewen Technology
Nov 10, 2020 · Artificial Intelligence

Modeling Web Novel Popularity with Predictive Ranking and Statistical Fusion

This article explains how a binary‑classification model combining estimated future behavior and statistical data is used to compute a unified popularity score for web novels, improving both recall and ranking in search and library scenarios while addressing challenges of cold‑start and long‑tail items.

LambdaMARTLearning-to-RankLightGBM
0 likes · 9 min read
Modeling Web Novel Popularity with Predictive Ranking and Statistical Fusion
DataFunTalk
DataFunTalk
Nov 9, 2020 · Artificial Intelligence

Practical Application of TensorFlow Ranking (TFR) in iQIYI Overseas Recommendation System

This article describes how iQIYI's overseas recommendation team adopted TensorFlow Ranking to replace traditional CTR models with Learning‑to‑Rank, detailing the framework’s architecture, challenges such as regularization and sequence feature support, the solutions implemented, and experimental results showing significant performance gains.

Learning-to-RankTensorFlow Rankingranking algorithms
0 likes · 15 min read
Practical Application of TensorFlow Ranking (TFR) in iQIYI Overseas Recommendation System
DataFunTalk
DataFunTalk
Jun 27, 2020 · Artificial Intelligence

Applying Learning to Rank for Search Suggestions at Gaode Maps

This article details how Gaode Maps leveraged machine‑learning‑based Learning to Rank to rebuild its search‑suggestion ranking pipeline, addressing challenges in sample construction, feature sparsity, and model optimization, and achieving significant improvements in relevance metrics and user experience.

Gaode MapsLearning-to-RankSearch Suggestion
0 likes · 9 min read
Applying Learning to Rank for Search Suggestions at Gaode Maps
Alibaba Cloud Developer
Alibaba Cloud Developer
Nov 27, 2019 · Artificial Intelligence

How Gaode Map Boosted Search Suggestions with Learning-to-Rank

Gaode Map revamped its search suggestion service by replacing rule‑based ranking with a Learning‑to‑Rank model, detailing challenges in sample construction, feature engineering, loss‑function tuning, and the resulting performance gains across millions of queries and diverse geographic regions.

Feature-EngineeringLBSLearning-to-Rank
0 likes · 11 min read
How Gaode Map Boosted Search Suggestions with Learning-to-Rank
DataFunTalk
DataFunTalk
Aug 8, 2019 · Artificial Intelligence

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

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

Learning-to-RankReal-Timee‑commerce
0 likes · 14 min read
Practical Experience of JD E‑commerce Recommendation System: Architecture, Ranking, Real‑time Updates, and Experiment Platform
Amap Tech
Amap Tech
Jun 5, 2019 · Artificial Intelligence

Applying Learning to Rank for Search Suggestion Optimization at Gaode Maps

Gaode Maps applied Learning to Rank to optimize search suggestions, moving from rule-based to gradient boosted rank model, addressing sample construction and feature sparsity via session-based labeling and loss adjustment, achieving a seven‑point MRR gain and higher coverage, and paving the way for personalization and deep learning.

Gaode MapsLearning-to-RankModel Optimization
0 likes · 11 min read
Applying Learning to Rank for Search Suggestion Optimization at Gaode Maps
Meituan Technology Team
Meituan Technology Team
Jan 17, 2019 · Artificial Intelligence

Evolution of Meituan-Dianping Search Core Ranking: From Traditional Models to LambdaDNN Listwise Deep Learning

The Meituan‑Dianping search team progressed its core ranking from linear, FM and GBDT models to a knowledge‑graph‑enhanced deep‑learning architecture, culminating in the listwise LambdaDNN network that directly optimizes NDCG, supported by extensive feature engineering, distributed TensorFlow training, and the Athena diagnostic system.

Deep LearningKnowledge GraphLambdaDNN
0 likes · 29 min read
Evolution of Meituan-Dianping Search Core Ranking: From Traditional Models to LambdaDNN Listwise Deep Learning
21CTO
21CTO
Dec 25, 2018 · Artificial Intelligence

Demystifying Learning to Rank: From Core Concepts to Scalable Online Architecture

This article offers a comprehensive, system‑engineer‑focused guide to Learning to Rank, covering fundamental machine‑learning concepts, evaluation metrics, training approaches, and a detailed online ranking architecture with feature, recall, and model governance, illustrated by real‑world examples from Meituan‑Dianping.

A/B testingLearning-to-RankModel Deployment
0 likes · 32 min read
Demystifying Learning to Rank: From Core Concepts to Scalable Online Architecture
Meituan Technology Team
Meituan Technology Team
Dec 20, 2018 · Artificial Intelligence

Demystifying Learning to Rank: From Core Algorithms to Scalable Online Sorting Architecture

This article provides a comprehensive, system‑engineer‑focused guide to Learning to Rank, covering fundamental machine‑learning concepts, evaluation metrics such as Precision, nDCG and ERR, training‑testing‑inference stages, pointwise/pairwise/listwise methods, and a detailed multi‑layer online ranking architecture with feature, model and recall governance.

A/B testingDomain-Driven DesignEvaluation Metrics
0 likes · 29 min read
Demystifying Learning to Rank: From Core Algorithms to Scalable Online Sorting Architecture
HomeTech
HomeTech
Oct 29, 2018 · Artificial Intelligence

Applying ListNet Listwise Ranking Model for Car Purchase Intent Prediction

This article introduces the ListNet listwise ranking algorithm, explains its theoretical foundations and loss function, presents a Python implementation with gradient computation, and demonstrates its superior performance over pointwise and pairwise models on public benchmarks and an internal automotive dataset for predicting users' intended car series.

Learning-to-Ranklistnetmachine-learning
0 likes · 14 min read
Applying ListNet Listwise Ranking Model for Car Purchase Intent Prediction
vivo Internet Technology
vivo Internet Technology
Jan 22, 2018 · Artificial Intelligence

Learning to Rank: From Regression to Search Ranking and Evaluation Methods

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.

Learning-to-RankNDCGPairwise
0 likes · 16 min read
Learning to Rank: From Regression to Search Ranking and Evaluation Methods
Qunar Tech Salon
Qunar Tech Salon
Aug 21, 2016 · Artificial Intelligence

Hotel Search Ranking: Problem Definition, Model Construction, Feature Engineering, and Offline Evaluation

This article presents a comprehensive overview of hotel search ranking, covering problem definition, the distinction between ranking and probability estimation, handling position bias, detailed feature engineering, the AnyBoost linear boosting model, offline evaluation methods, and observed online performance improvements.

Learning-to-Rankfeature engineeringhotel ranking
0 likes · 7 min read
Hotel Search Ranking: Problem Definition, Model Construction, Feature Engineering, and Offline Evaluation