music recommendation

DataFunSummit

Feb 26, 2025 · Artificial Intelligence

Applying Multimodal Large Models to Music Recommendation at NetEase Cloud Music

This article details how NetEase Cloud Music leverages multimodal large language models to improve music recommendation across daily, personalized, and playlist scenarios by extracting rich audio, text, and visual features, addressing data skew, cold‑start challenges, and achieving measurable gains in user engagement and distribution efficiency.

Feature ExtractionNetEase Cloud MusicRecommendation systems

0 likes · 12 min read

Applying Multimodal Large Models to Music Recommendation at NetEase Cloud Music

DataFunTalk

Jun 30, 2024 · Artificial Intelligence

Application and Exploration of Large Audio Representation Models for Cold-Start Songs in QQ Music

This article presents a technical overview of how large‑scale audio representation models are fine‑tuned with I2I co‑occurrence and U2I interaction data to improve cold‑start song recommendation on QQ Music, describing the challenges, methodology, deployment scenarios, and experimental results.

I2I fine-tuningU2I fine-tuningaudio representation

0 likes · 17 min read

Application and Exploration of Large Audio Representation Models for Cold-Start Songs in QQ Music

DataFunSummit

Dec 8, 2023 · Artificial Intelligence

Multimodal Cold‑Start Techniques for Music Recommendation at NetEase Cloud Music

This article presents NetEase Cloud Music's multimodal cold‑start solution, detailing the problem background, feature selection using CLIP, two modeling approaches (I2I2U indirect and U2I DSSM direct), contrastive learning enhancements, interest‑boundary modeling, and evaluation results showing significant gains in user engagement.

AICold Startcontrastive learning

0 likes · 15 min read

Multimodal Cold‑Start Techniques for Music Recommendation at NetEase Cloud Music

DataFunTalk

Nov 10, 2023 · Artificial Intelligence

Multimodal Cold-Start Techniques for Music Recommendation at NetEase Cloud Music

This article presents NetEase Cloud Music's multimodal cold-start recommendation approach, detailing the problem's significance, feature extraction using CLIP, I2I2U indirect modeling, U2I DSSM direct modeling with contrastive learning and interest‑boundary mechanisms, deployment pipeline, evaluation results, and future optimization directions.

Cold Startcontrastive learningdeep learning

0 likes · 14 min read

DataFunTalk

Apr 3, 2022 · Artificial Intelligence

Exploring QQ Music Recall Algorithms: Knowledge‑Graph Fusion, Sequence & Multi‑Interest Modeling, Audio Recall, and Federated Learning

This article presents a comprehensive overview of QQ Music's recall system, detailing business scenarios, challenges such as noisy user behavior and cold‑start, and four key solutions—including knowledge‑graph‑enhanced recall, sequence and multi‑interest modeling, audio‑based recall, and federated learning—along with experimental results, deployment details, and a Q&A session.

Audio EmbeddingFederated Learningknowledge graph

0 likes · 20 min read

Exploring QQ Music Recall Algorithms: Knowledge‑Graph Fusion, Sequence & Multi‑Interest Modeling, Audio Recall, and Federated Learning

DataFunSummit

Mar 17, 2022 · Artificial Intelligence

Optimizing QQ Music Ranking Model: From User Perception to Multi‑Category Traffic Exploration

This talk presents the evolution of QQ Music's ranking system, detailing background challenges, user‑perception modeling, multi‑objective and causal learning to mitigate the Matthew effect, long‑tail content support, cross‑domain recommendation, and module personalization for diversified traffic, concluding with future research directions.

causal inferencecross-domain recommendationmulti-objective learning

0 likes · 16 min read

Optimizing QQ Music Ranking Model: From User Perception to Multi‑Category Traffic Exploration

DataFunTalk

Feb 14, 2022 · Artificial Intelligence

Optimizing QQ Music Ranking Models: From Pairwise Methods to Multi‑Objective Learning and Causal Inference

This talk details the evolution of QQ Music's ranking system, covering background, user‑perception modeling, pairwise optimization, advanced model architectures, multi‑objective learning with causal inference to mitigate the Matthew effect, cross‑domain recommendation, and module personalization that together boost user engagement and platform traffic.

causal inferencecross-domain recommendationmulti-objective learning

0 likes · 16 min read

Optimizing QQ Music Ranking Models: From Pairwise Methods to Multi‑Objective Learning and Causal Inference

Rare Earth Juejin Tech Community

Feb 10, 2022 · Artificial Intelligence

Simple Music Recommendation System: Audio‑Feature and Playlist‑Based Approaches

This article presents two straightforward music recommendation methods—content‑based filtering using audio features and collaborative filtering using playlist data—detailing their design ideas, key Python and Go code snippets, model training, evaluation, and possible improvements.

Pythonaudio feature extractioncollaborative filtering

0 likes · 13 min read

Simple Music Recommendation System: Audio‑Feature and Playlist‑Based Approaches

DataFunTalk

Nov 20, 2020 · Artificial Intelligence

NetEase Cloud Music Recommendation System: Architecture, Challenges, and AI‑Driven Solutions

The article presents a comprehensive overview of NetEase Cloud Music's recommendation system, detailing its rapid user growth, diverse music‑recommendation scenarios, differences from e‑commerce recommendation, and the evolution of recall and ranking models that leverage real‑time interest vectors, dynamic multi‑interest modeling, knowledge graphs, long‑short‑term interest mining, and multi‑path fusion to deliver personalized music experiences.

AI algorithmsinterest evolutionknowledge graph

0 likes · 20 min read

NetEase Cloud Music Recommendation System: Architecture, Challenges, and AI‑Driven Solutions

DataFunTalk

Oct 23, 2020 · Artificial Intelligence

Feedback‑Aware Deep Matching Model for Music Recommendation in Tmall Genie

This article presents DeepMatch, a behavior‑sequence based deep learning recall model enhanced with play‑rate and intent‑type embeddings, describes its self‑attention architecture, factorized embedding parameterization, multitask loss design, distributed TensorFlow training tricks, and demonstrates significant offline and online improvements in music recommendation performance.

Self-AttentionTensorFlowdeep learning

0 likes · 15 min read

Feedback‑Aware Deep Matching Model for Music Recommendation in Tmall Genie

DataFunTalk

Aug 12, 2020 · Artificial Intelligence

Content-Based and Context-Aware Music Recommendation Systems

This article reviews music recommendation techniques, focusing on content-based methods using metadata and audio features, and context-aware approaches that incorporate environmental and user-related factors, highlighting challenges, classification of metadata, acoustic descriptors, and integration strategies for personalized music services.

audio featurescontent-basedcontext-aware

0 likes · 21 min read

Content-Based and Context-Aware Music Recommendation Systems

Tencent Music Tech Team

Nov 4, 2016 · Artificial Intelligence

How QQ Music Recommendation System Understands Your Preferences

The QQ Music recommendation system tackles cold‑start by first mixing Chinese and English tracks, then builds a six‑dimensional user profile (content, social, scenario, crowd, time, blacklist) and tags songs with six attributes, using content‑based, collaborative, matrix‑factorization and neural‑network models plus implicit co‑listening links, while acknowledging that final wisdom still comes from human listeners.

Cold Startcollaborative filteringmachine learning

0 likes · 11 min read

How QQ Music Recommendation System Understands Your Preferences