요즘은 추천시스템 위주의 공부를 하고 있습니다.
- Practice & Project: 공부하는 과정에서 기록으로 남기고 싶은 내용을 정리합니다.
- Reference: 다양한 레퍼런스 아카이빙합니다.
- 추천 모델 구현, 2023
repository
- bandit 공부, 2025
repository
- udemy 강의 deployment of ml models, 2022
repository
- bentoml tutorial, 2022
repository
- mlops tutorial, 2023
repository
- udemy 강의 ml testing monitoring, 2023
repository
- FastAPI study, 2023
repository
- Dacon 신용카드 사용자 연체 예측 AI 경진대회, 2022
code
- Kaggle Credit Card Fraud Detection, 2022
code
- 네트워크임베딩 대학원수업 기말 프로젝트 (Anomaly Detection with Graph Embedding Ensemble)
pdf
- 모델 구현 (라이브러리화), 2023
repository
- Brady Neal - Causal Inference
review
- Causal Inference for the Brave and True
review
- DoWhy tutorial
review
- Heterogeneous Treatment Effect Estimation tutorial
review
- nlp study, 2020
repository
- hugginface text classification, 2022
repository
- 개인 블로그 공부 정리
blog
- Algorithm
- Collaborative Filtering for Implicit Feedback Data, 2008
- BPR: Bayesian Personalized Ranking from Implicit Feedback, UAI 2009
- Context-Aware Recommender Systems, 2011
- Neural Collaborative Filtering, 2017 IWWWC
- Fatorization Machines, 2009
- Wide & Deep Learning for Recommender Systems, 2016
- DeepFM: A Factorization-Machine based Neural Network for CTR Prediction, 2017
- AutoRec: Autoencoders Meet Collaborative Filtering, 2015 WWW
- Training Deep AutoEncoders for Collaborative Filtering, 2017
- Variational Autoencoders for Collaborative Filtering, 2018
- Deep content-based music recommendation, 2013 NIPS
- Deep Learning Recommendation Model for Personalization and Recommendation Systems (DLRM), 2019
- DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systems 2020
- Real-time Personalization using Embeddings for Search Ranking at Airbnb, KDD 2018
- Sampling-Bias-Corrected Neural Modeling for Large Corpus Item Recommendations, 2019
- Mixed Negative Sampling for Learning Two-tower Neural Networks in Recommendations, 2020
- Algorithm - text, image
- Joint Training of Ratings and Reviews with Recurrent Recommender Nerworks, 2017 ICLR
- Image-based Recommendations on Styles and Substitutes, 2015 SIGIR
- VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback, 2016 AAAI
- Deep Neural Networks for YouTube Recommendations, 2016 RecSys
- Recommending What Video to Watch Next: A Multitask Ranking System, 2019 RecSys
- Algorithm - session-based, sequential
- Session-based Recommendations with Recurrent Neural Networks, 2015 ICLR
- BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer, 2019
- SASRec: Self-Attentive Sequential Recommendation, 2018
- Positive, Negative and Neutral: Modeling Implicit Feedback in Session-based News Recommendation, SIGIR 2022
- Algorithm - graph
- PageRank: Standing on the shoulders of giant, 2010
- DeepWalk: Online Learning of Social Representations, 2014
- SEMI-SUPERVISED CLASSIFICATION WITH GRAPH CONVOLUTIONAL NETWORKS, 2017
- Inductive Representation Learning on Large Graphs, 2017
- Graph Attention Networks, 2018
- Graph Convolutional Neural Networks for Web-Scale Recommender Systems, 2018 Pinterest
- LookAlike
- Bandit
- Explore, Exploit, and Explain: Personalizing Explainable Recommendations with Bandits, 2018 spotify
epsilon-greedy
,explanation
- Deep neural network marketplace recommenders in online experiments, 2018
epsilon-greedy
,hybrid item-representation
- A Batched Multi-Armed Bandit Approach to News Headline Testing, 2019
thomson-sampling
,batched MAB
- A Contextual-Bandit Approach to Personalized News Article Recommendation, 2012
LinUCB
- Contextual User Browsing Bandits for Large-Scale Online Mobile Recommendation, 2020 Alibaba
UBM-LinUCB
,contextual combinatorial bandit
- An Empirical Evaluation of Thompson Sampling, 2011 Yahoo
- An Efficient Bandit Algorithm for Realtime Multivariate Optimization, 2018 Amazon
thomson-sampling
- Cascading Bandits: Learning to Rank in the Cascade Model, 2015
cascade bandit
- Carousel Personalization in Music Streaming Apps with Contextual Bandits, 2020 Deezer
cascade bandit
,semi-personalized
- Cascading Bandits: Optimizing Recommendation Frequency in Delayed Feedback Environments, 2023
cascade bandit
- Deep Bayesian Bandits: Exploring in Online Personalized Recommendations, 2020 Twitter
deep Bayesian bandits
,ad display
- A Sleeping, Recovering Bandit Algorithm for Optimizing Recurring Notifications, 2020 Duolingo
- Explore, Exploit, and Explain: Personalizing Explainable Recommendations with Bandits, 2018 spotify
- LLM
- LLM-Based Aspect Augmentations for Recommendation Systems, 2023
item aspect generation
- Language-Based User Profiles for Recommendation, 2024
LFM
- Harnessing Large Language Models for Text-Rich Sequential Recommendation, 2024
text sequential summarize
SFT
- The Unequal Opportunities of Large Language Models: Revealing Demographic Bias through Job Recommendation, 2023
bias
- Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction, 2023 google research
prediction
- LLMs for User Interest Exploration in Large-scale Recommendation Systems, 2024 google
hybrid
SFT
- Comparing Human and LLM Ratings of Music-Recommendation Quality with User Context, 2024
LLM-as-a-judge
- Playlist Search Reinvented: LLMs Behind the Curtain, 2024 amazon music
content enrichment
synthesizing training data
judges for evaluation
- A Multi-Agent Conversational Recommender System, 2024
multi-agent
conversational rec sys
- BETTER GENERALIZATION WITH SEMANTIC IDS: A CASE STUDY IN RANKING FOR RECOMMENDATIONS, 2024 google
id-based
- LLM-Based Aspect Augmentations for Recommendation Systems, 2023
- Push
- Personalized Push Notifications for News Recommendation, 2019 DGP media
location considered
- Predicting which type of push notification content motivates users to engage in a self-monitoring app, 2018
statistics analysis
heavy user, heavy content
- Near Real-time Optimization of Activity-based Notifications, 2018 LinkedIn
- Notification Volume Control and Optimization System at Pinterest, 2018 Pinterest
noti volume
- Personalized Push Notifications for News Recommendation, 2019 DGP media
- Search, Query, IR
- Query2doc: Query Expansion with Large Language Models, 2023 Microsoft Research
query expansion
- Query Expansion by Prompting Large Language Models, 2023 Google Research
- An Interactive Query Generation Assistant using LLM-based Prompt Modification and User Feedback, 2023
- InPars: Data Augmentation for Information Retrieval using Large Language Models, 2022
- Generating Query Recommendations via LLMs, 2024 Spotify
query expansion
prompt
- Semantic Product Search, 2019 Amazon
product search
semantic
contrastive learning
tokenization
- Embedding-based Retrieval in Facebook Search, 2020 Facebook
social search
two-tower
ANN
negative sampling
- Unified Embedding Based Personalized Retrieval in Etsy Search, 2024 Etsy
two-tower
negative sampling
ANN
- Embedding based retrieval for long tail search queries in ecommerce, 2025
long tail
llm synthetic data
- Towards Personalized and Semantic Retrieval: An End-to-End Solution for E-commerce Search via Embedding Learning, 2020
two-tower
negative sampling
emb retrieval system
- Query2doc: Query Expansion with Large Language Models, 2023 Microsoft Research
- Diversity
- Algorithmic Effects on the Diversity of Consumption on Spotify, WWW 2020
- Bias
- Lessons Learned Addressing Dataset Bias in Model-Based Candidate Generation at Twitter, 2020 KDD IRS
- Popularity-Opportunity Bias in Collaborative Filtering, WSDM 2021
- Managing Popularity Bias in Recommender Systems with Personalized Re-ranking, 2019
- The Unfairness of Popularity Bias in Recommendation, 2019
- Explainable
- User Modeling
- Causality
- Survey
- Deep Learning based Recommender System: A Survey and New Perspectives, 2019
- A Survey on Causal Inference for Recommendation, 2024
- Fairness and Diversity in Recommender Systems: A Survey, 2024
- Recommender Systems in the Era of Large Language Models (LLMs), 2024
- Survey
- Perfomance Measure
- The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets
- The Relationship Between Precision-Recall and ROC Curves
- Predicting Good Probabilities With Supervised Learning
- Properties and benefits of calibrated classifiers
- The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets
- Cost-sensitive
- Sampling
- SMOTE, 2002
- SMOTE for learning from imbalanced data : progress and challenges, 2018
- Influence of minority class instance types on SMOTE imbalanced data oversampling
- Calibrating Probability with Undersampling for Unbalanced Classification .2015
- A Study of the Behavior of Several Methods for Balancing Machine Learning Training Data
- Dynamic Sampling in Convolutional Neural Networks for Imbalanced Data Classification
- Ensemble Learning
- Feature Selection
- Ensemble-based wrapper methods for feature selection and class imbalance learning, 2010
- A comparative study of iterative and non-iterative feature selection techniques for software defect prediction
- Learning feature representations of normality
- Outlier Detection with AutoEncoder Ensemble, 2017
- Auto-Encoding Variational Bayes ,2014
- Deep Variational Information Bottleneck, ICLR 2017
- Extracting and Composing Robust Features with Denoising Autoencoders, 2008
- Generatice Adversarial Nets, NIPS 2014
- Least Squares Generative Adversarial Networks ,2016
- Adversarial Autoencoders, 2016
- Generative Probabilistic Novelty Detection with Adversarial Autoencoders , NIPS 2018
- Deep Autoencoding Gaussian Mixture Model For Unsupervised Anomaly Detection, ICLR 2018
- Anomaly Detection with Robust Deep Autoencoders, KDD 2017
- Time Series and Streaming Anomaly Detection
- Anomaly Detection In Univariate Time-Series : A Survey on the state-of-the-art
- USAD : UnSupervised Anomaly Detection on multivariate time series, KDD2020
- Variational Attention for Sequence-to-Sequence Models, 2017
- A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencoder (2017)
- Outlier Detection for Time Series with Recurrent Autoencoder Ensembles , 2019
- Robust Anomaly Detection for Multivariate time series through Stochastic Recurrent Neural Network, KKD 2019
- Time Series Anomaly Detection with Multiresolution Ensemble Decoding, AAAI 2021
- An Improved Arima-Based Traffic Anomaly Detection Algorithm for Wireless Sensor Networks ,2016
- Time-Series Anomaly Detection Service at Microsoft, 2019
- Time Series Anomaly Detection Using Convolutional Neural Networks and Transfer Learning, 2019
- Abuse and Fraud Detection in Streaming Services Using Heuristic-Aware Machine Learning, 2022 Netflix
- Are Transformers Effective for Time Series Forecasting?, 2022
- Heterogeneous treatment effect estimation, uplift
- Causal Inference and Uplift Modeling A review of the literature, 2016
review
- Double machine learning for treatment and causal parameters, 2016
- Metalearners for estimation heterogeneous treatment effects using machine learning, 2019
- Estimation and Inference of Heterogeneous Treatment Effects using Random Forests, 2018
- Causal Inference and Uplift Modeling A review of the literature, 2016
- 네이버, 카카오, 당근, 우아한형제들, 토스 2024 conference
review
- 추천, 검색
- 카카오 AI 추천: 카카오페이지와 멜론으로 살펴보는 카카오 연관 추천
- 카카오 AI 추천: 토픽모델링과 MAB를 이용한 카카오 개인화 추천
- 카카오 AI 추천: 협업필터링 모델 선택 시의 기준에 대하여
- 카카오 AI 추천: 카카오의 콘텐츠 기반 필터링
- 우리 생활 속 추천 시스템, 어떻게 발전해왔고, 어떻게 발전해나가고 있는가? (카카오 김성진 팀장, 2021.12)
- 추천 기술이 마주하고 있는 현실적인 문제들 (카카오 김성진 리더, 2021.10)
- if(kakao)2019 멜론 플레이리스트 자동 생성
- if(kakao)2020 맥락과 취향 사이 줄타기
- 브런치 추천의 힘에 대한 6가지 기술
- if(kakao)dev2022 Sequential Recommendation System 카카오 서비스 적용기
- if(kakao)dev2022 Explainable Recommender System in 카카오웹툰
- LLM, 이미지
- 이미지까지 이해하는 Multimodal LLM의 학습 방법 밝혀내기, ifkakao2024
- 나만의 프로필 이미지를 만드는 Personalized T2I 모델 개발기, ifkakao2024
- AI Agent 기반 스마트 AI 마이 노트, ifkakao2024
- 업무 효율화를 위한 카카오 사내봇 개발기, ifkakao2024
- AI 를 통해 스팸을 대응하는 카카오의 노력, ifkakao2024
- LLM으로 음성인식 성능 개선하기, ifkakao2024
- CodeBuddy 와 함께하는 AI 코드리뷰, ifkakao2024
- AI Assistant와 통합 지식베이스를 통한 AI Native Company 구현, ifkakao2024
- 밑바닥부터 시작하는 LLM 개발기, ifkakao2024
- AI 기반 광고 콘텐츠 모니터링 기술 개발기, ifkakao2024
- 빠르고 비용효율적으로 LLM 서빙하기, ifkakao2024
- 서비스에 LLM 부스터 달아주기: 요약부터 AI Bot 까지, ifkakao2024
- ‘선물하기 와인탐험’ LLM 대화형 서비스 개발기, ifkakao2024
- 이상치탐지
- XAI
- 플랫폼
- 기타
- 추천
- LLM
- LLM, 이미지
- 이상치탐지
- 추천, 검색
- 이상치탐지
- 플랫폼
- 추천
- 추천
- 기타
- 추천, 검색
- (Deview2021) BERT로 만든 네이버 플레이스 비슷한 취향 유저 추천 시스템
- (Deview2021) Knowledge Graph에게 맛집과 사용자를 묻는다: GNN으로 맛집 취향 저격 하기
- (Deview2020) 유저가 좋은 작품(웹툰)을 만났을 때
- (Deview2020) 추천시스템 3.0: 딥러닝 후기시대에서 바이어스, 그래프, 그리고 인과관계의 중요성
- 홈피드: 네이버의 진입점에서 추천피드를 외치다! 추천피드 도입 고군분투기, DAN24
- 네이버 검색이 이렇게 좋아졌어? LLM의 Re-Ranking Ability 검색에 이식하기, DAN24
- 서치피드: SERP를 넘어 SURF로! 검색의 새로운 물결, DAN24
- 검색과 피드의 만남: LLM으로 완성하는 초개인화 서비스, DAN24
- 클립 크리에이터와 네이버 유저를 연결하기: 숏폼 컨텐츠 개인화 추천, DAN24
- LLM 기반 추천/광고 파운데이션 모델, DAN24
- 사용자 경험을 극대화하는 AI 기반 장소 추천 시스템 : LLM과 유저 데이터의 융합, DAN24
- LLM for Search: 꽁꽁 얼어붙은 검색 서비스 위로 LLM이 걸어다닙니다, DAN24
- 사람을 대신해야 진짜 AI지? : LLM 기반 임베딩부터 검색 품질 자동 평가 모델까지, DAN24
- SQM으로 네이버 검색 품질 췍↗!, DAN24
- AI, LLM
- 기타
- 추천, 검색
- 타겟팅
- 추천
- NDC21-데이터분석, 추천알고리즘 offline A/B 테스트 (feat: PAIGE 프로야구 서비스)
- 인과추론
- 추천
- 데이터야놀자2022, 뭐먹지 빌런을 무찌르는 GNN 기반 개인화 추천
- 추천, 검색
- 추천, 검색
- 추천
- 추천
- 개인화 추천 시스템 #3. 모델 서빙, 2025
- (2023 우아콘) 추천시스템 성장 일지: 데이터 엔지니어 편
- (2023 우아콘) 여기, 주문하신 '예측' 나왔습니다: 추천/ML에서 '예측'을 서빙한다는 것에 대하여
- 실시간 반응형 추천 개발 일지 1부: 프로젝트 소개, 2024
- 실시간 반응형 추천 개발 일지 2부: 벡터 검색, 그리고 숨겨진 요구사항과 기술 도입 의사 결정을 다루는 방법, 2025
- 그래프, 텍스트 인코더를 활용한 실시간 추천 검색어 모델링, 우아콘2024
- 취향 저격 맛집 추천, 더 똑똑하게: 추천 모델 성장 일지, 우아콘2024
- LLM
- 이상치탐지
- 기타
- 플랫폼
- 추천
- 플랫폼
- 추천, 검색
- The Rise (and Lessons Learned) of ML Models to Personalize Content on Home, 2021
- Introducing Natural Language Search for Podcast Episodes, spotify 2022
- Modeling Users According to Their Slow and Fast-Moving Interests, spotify 2022
- Socially-Motivated Music Recommendation, 2024
- Personalizing Audiobooks and Podcasts with graph-based models, 2024
- 추천, 검색
- 이상치탐지
- 추천, 검색
- 인과추론
- 추천, 검색
- 추천, 검색
- 이상치탐지
- 추천, 검색
- 추천, 검색
- 추천, 검색
- Innovating Faster on Personalization Algorithms at Netflix Using Interleaving, 2017
- Foundation Model for Personalized Recommendation, 2025
foundation model
- Next-Level Personalization: How 16k+ Lifelong User Actions Supercharge Pinterest’s Recommendations, 2025
TransActV2
lifelong user sequence
Next Action Loss
- 이상치탐지
- 인과추론
- 추천, 검색
- 이상치탐지
- 추천
- Transformers4Rec: A flexible library for Sequential and Session-based recommendation
- [22'Recsys] BERT4Rec 구현의 진실에 관하여 : A Systematic Review and Replicability Study of BERT4Rec for Sequential Recommendation
- Scaling deep retrieval with TensorFlow Recommenders and Vertex AI Matching Engine
- DLRM github
- DeepCTR github
- Two Tower Model Architecture: Current State and Promising Extensions, 2023
- 추천 시스템 서비스 적용을 위한 Elastic Search 도입기, 2022
- Recommendation Systems • Bias
- eugeneyan blog
- Search: Query Matching via Lexical, Graph, and Embedding Methods, 2021
- Patterns for Personalization in Recommendations and Search, 2021
- Real-time Machine Learning For Recommendations, 2021
- System Design for Recommendations and Search, 2021
- Improving Recommendation Systems & Search in the Age of LLMs, 2025
- Push Notifications: What to Push, What Not to Push, and How Often, 2023
- 인과추론