jiajiewang0326 / Recall
介绍推荐系统几种算法的实现，可以作为模版在此基础上修改使用。
Stars: ✭ 67
Labels
Projects that are alternatives of or similar to Recall
Jupyter Themes
Custom Jupyter Notebook Themes
Stars: ✭ 8,879 (+13152.24%)
Mutual labels: jupyter-notebook
Contracode
Contrastive Code Representation Learning: functionality-based JavaScript embeddings through self-supervised learning
Stars: ✭ 66 (-1.49%)
Mutual labels: jupyter-notebook
Short Text Classification
SVM, FastText, TextCNN, BiGRU, CNN-BiGRU在短分本分类上的对比
Stars: ✭ 66 (-1.49%)
Mutual labels: jupyter-notebook
Jupyter tfbook
Jupyter Notebooks for TensorFlow Book
Stars: ✭ 66 (-1.49%)
Mutual labels: jupyter-notebook
Mimic Workshop
Introduction to MIMIC-III, the Critical Care Database
Stars: ✭ 65 (-2.99%)
Mutual labels: jupyter-notebook
Face Mask Detection
In this, I am attaching my code for building a CNN model to detect if a person is wearing face mask or not using the webcam of their PC.
Stars: ✭ 67 (+0%)
Mutual labels: jupyter-notebook
Introduction To Data Science
本Repository为中国人民大学朝乐门老师开源课程——《数据科学导论》
Stars: ✭ 66 (-1.49%)
Mutual labels: jupyter-notebook
Tex An mesh
Fully textured and animatable human body mesh reconstruction from a single image
Stars: ✭ 67 (+0%)
Mutual labels: jupyter-notebook
Ml Nlp
此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。
Stars: ✭ 10,826 (+16058.21%)
Mutual labels: jupyter-notebook
Sampling Free Epistemic Uncertainty
Code for the ICCV 2019 paper "Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagation"
Stars: ✭ 67 (+0%)
Mutual labels: jupyter-notebook
Hacktoberfest2020 Expert
Hacktoberfest 2020. Don't forget to spread love and if you like give me a ⭐️
Stars: ✭ 67 (+0%)
Mutual labels: jupyter-notebook
分享几个常用的召回推荐算法
1、Word2Vec计算物品相似度，我实际工作中也用它来计算两个菜肴之间的搭配度。
2、GNN作为一路召回。请关注我的另一个仓库：https://github.com/jiajiewang0326/KG_Based_Recommendation_with_GNNs
3、Userbased_CF
4、Itembased_CF。在很多推荐场景中，item数量远小于user数量，所以这个更适合，更高效。
5、热门召回。统计指定时间窗口的item的曝光量，点击量，从而计算CTR，按照CTR排序，选出topK个。因为这个代码涉及商业保密太多就不贴了。
6、基于地域、时间等推荐。我们做饮食推荐，而饮食习惯本身就有很强地域特点，而且蔬菜水果都是季节性的，此推荐模式在我们实际业务应用中反馈不错，获得了不错的收益。因为其中的规则都是企业资产就不贴了。
7、内容介绍、评论等文本内容挖掘作为一路召回。
8、基于标签的推荐
9、LFM
封装了几个常用推荐功能
Class_for_Recommendation
一部分数据集太大，可以自行下载：http://grouplens.org/datasets/movielens/1m)
说明：这个仓库里代码，都是我在快速试验效果阶段的产物，其中的方案后续经过多个大版本更新后应用或者被筛选淘汰，不涉商秘。
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].