Applying Deep Learning to Meitu Community Recommendation: Embedding, Recall, and Ranking Models
The talk by Meitu senior algorithm expert Chen Wenqiang details how deep‑learning‑driven embedding, recall, and ranking techniques—including Item2vec, twin‑tower DNNs, and multi‑task NFwFM—are applied to improve click‑through rates, follow conversions, and user engagement in Meitu's content community.
Speaker: Chen Wenqiang, Senior Algorithm Expert at Meitu, responsible for the design and deployment of recommendation algorithms for the Meitu community.
Abstract: In the process of socializing Meitu’s content platform, massive high‑quality content and rich user behavior data have been accumulated; recommendation algorithms connect content consumers and producers, offering significant value for platform growth. This session explores how Meitu leverages deep learning to boost click‑through rate, follow conversion, and average watch time in its community recommendation scenario.
Agenda: 1. Overview and challenges of personalized recommendation in the Meitu community. 2. Embedding techniques used in the recall stage, including Item2vec‑based item embeddings and the application of YouTubeNet and twin‑tower DNN models. 3. Development and deployment of Meitu’s ranking models, covering the iterative evolution of the NFwFM model and the exploration of multi‑task NFwFM for multi‑objective prediction.
Video and supporting PPT are available for download.
Speaker Bio: Chen Wenqiang leads algorithm design and implementation for Meitu’s community recommendation business, with many years of practical experience in recommendation and optimization algorithms.
Related articles: "The three most important problems for the next stage of recommendation systems," "JD e‑commerce recommendation system practice," and information about the DataFun knowledge‑sharing platform.
Signed-in readers can open the original source through BestHub's protected redirect.
This article has been distilled and summarized from source material, then republished for learning and reference. If you believe it infringes your rights, please contactand we will review it promptly.
DataFunTalk
Dedicated to sharing and discussing big data and AI technology applications, aiming to empower a million data scientists. Regularly hosts live tech talks and curates articles on big data, recommendation/search algorithms, advertising algorithms, NLP, intelligent risk control, autonomous driving, and machine learning/deep learning.
How this landed with the community
Was this worth your time?
0 Comments
Thoughtful readers leave field notes, pushback, and hard-won operational detail here.