CTR Prediction Frameworks

Deep learning frameworks and model collections specifically for Click-Through Rate (CTR) prediction and related tasks like conversion rate estimation. Includes implementations of CTR algorithms (FM, DeepFM, DIN, etc.), recommender system models, and computational advertising tools. Does NOT include general recommendation systems without CTR focus, or prediction tasks unrelated to ad/click modeling.

There are 20 ctr prediction frameworks tracked. 8 score above 50 (established tier). The highest-rated is NVIDIA-Merlin/HugeCTR at 61/100 with 1,051 stars.

Get all 20 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=ml-frameworks&subcategory=ctr-prediction-frameworks&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Framework	Score	Tier	Stars	Language
1	NVIDIA-Merlin/HugeCTR HugeCTR is a high efficiency GPU framework designed for Click-Through-Rate...	61	Established	1,051	C++
2	shenweichen/DeepCTR-Torch 【PyTorch】Easy-to-use,Modular and Extendible package of deep-learning based...	60	Established	3,389	Python
3	shenweichen/DeepCTR Easy-to-use,Modular and Extendible package of deep-learning based CTR models .	60	Established	8,007	Python
4	UlionTse/mlgb MLGB is a library that includes many models of CTR Prediction & Recommender...	56	Established	1,048	Python
5	cnkuangshi/LightCTR Lightweight and Scalable framework that combines mainstream algorithms of...	51	Established	671	C++
6	wzhe06/SparkCTR CTR prediction model based on spark(LR, GBDT, DNN)	51	Established	924	Scala
7	shenweichen/DSIN Code for the IJCAI'19 paper "Deep Session Interest Network for...	51	Established	447	Python
8	imsheridan/DeepRec 推荐、广告工业界经典以及最前沿的论文、资料集合/ Must-read Papers on Recommendation System and CTR Prediction	51	Established	1,021	—
9	liyinxiao/Ranking_Papers Papers on recommendation system / search ranking.	47	Emerging	47	—
10	yuh-yang/MBHT-KDD22 [KDD'22] Multi-Behavior Hypergraph-Enhanced Transformer for Next-Item Recommendation	44	Emerging	70	Python
11	mJackie/RecSys 计算广告/推荐系统/机器学习(Machine Learning)/点击率(CTR)/转化率(CVR)预估/点击率预估	43	Emerging	2,073	—
12	bytedance/LargeBatchCTR Large batch training of CTR models based on DeepCTR with CowClip.	43	Emerging	174	Python
13	Prayforhanluo/CTR_Algorithm 一些经典的CTR算法的复现; LR, FM, FFM, AFM, DeepFM, xDeepFM, PNN, DCN, DCNv2, DIFM,...	41	Emerging	275	Jupyter Notebook
14	auxten/go-ctr Go DeepLearning based Recommendation Framework	39	Emerging	236	Go
15	qian135/ctr_model_zoo some ctr model, implemented by PyTorch, such as Factorization Machines,...	35	Emerging	70	Jupyter Notebook
16	jingpeicomp/product-relation-mining 商品关联关系挖掘，使用Spring Boot开发框架和Spark...	34	Emerging	33	Java
17	Gavince/MTL 学习并复现经典的推荐系统多目标任务，如：SharedBottom、ESMM、MMoE、PLE	32	Emerging	41	Jupyter Notebook
18	BARL-SSL/reptrix Library that provides metrics to assess representation quality	31	Emerging	24	Jupyter Notebook
19	RunlongYu/CELS 【PyTorch】Easy-to-use package of Cognitive Evolutionary Search (CELS) for...	30	Emerging	21	Python
20	BinFuPKU/CTRRecommenderModels I have surveyed the technology and papers of CTR & Recommender System, and ...	21	Experimental	56	Jupyter Notebook

Comparisons in this category

DeepCTR-Torch and DeepCTR (60 vs 60) DeepCTR and ctr_model_zoo (60 vs 35) DeepCTR-Torch and ctr_model_zoo (60 vs 35) DeepRec and RecSys (51 vs 43)