From 3d9723daeacd4b8dc9ab272054e143b500e3ae90 Mon Sep 17 00:00:00 2001 From: Tremo Date: Mon, 4 Dec 2023 21:34:29 +0200 Subject: [PATCH] adding missing conclusion --- ...ech-behind-tiktoks-addicitve-recommendation-system.md | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/_posts/2023-12-04-the-tech-behind-tiktoks-addicitve-recommendation-system.md b/_posts/2023-12-04-the-tech-behind-tiktoks-addicitve-recommendation-system.md index d5b6138..7e378b9 100644 --- a/_posts/2023-12-04-the-tech-behind-tiktoks-addicitve-recommendation-system.md +++ b/_posts/2023-12-04-the-tech-behind-tiktoks-addicitve-recommendation-system.md @@ -61,4 +61,11 @@ Additionally, to prevent the embedding memory from expanding too rapidly, a prob ## Conclusion -TikTok’s recommendation system played a main role in its success and +TikTok’s recommendation system played a main role in its success and widespread use. I tried in this blog post to shed some light on the underlying technologies used, especially the online training, which helps them recommend real-time personalized content that keeps users staring at their phones for hours. + +**References:** + +1. [How TikTok recommends content | TikTok Help Center](https://support.tiktok.com/en/using-tiktok/exploring-videos/how-tiktok-recommends-content) +2. [Monolith: Real Time Recommendation System With Collisionless Embedding Table (arxiv.org)](https://arxiv.org/pdf/2209.07663.pdf) +3. [*An Empirical Investigation of Personalization Factors on TikTok (arxiv.org)](https://arxiv.org/pdf/2201.12271v1.pdf) +4. [cs.princeton.edu/courses/archive/spring21/cos598D/icde_2021_camera_ready.pdf](https://www.cs.princeton.edu/courses/archive/spring21/cos598D/icde_2021_camera_ready.pdf)