最好通過電子版和網路查詢，Ctrl + F，儘量不要用肉眼去找，效率極低。

Netflix：80% 被觀看的電影來自推薦
[1] Gomez-Uribe C A, Hunt N. The Netflix recommender system: Algorithms, business value, and innovation[J]. ACM Transactions on Management Information Systems (TMIS), 2015, 6(4): 13.

Amazon：亞馬遜有30%的頁面瀏覽量來自於個性化推薦系統
[2] Sharma A, Hofman J M, Watts D J. Estimating the causal impact of recommendation systems from observational data[C]//Proceedings of the Sixteenth ACM Conference on Economics and Computation. ACM, 2015: 453-470.

Google新聞：38%的點選量來自推薦
[3] Das A S, Datar M, Garg A, et al. Google news personalization: scalable online collaborative filtering[C]//Proceedings of the 16th international conference on World Wide Web. ACM, 2007: 271-280.

The click-through numbers that we report are from running our experiments over a large user fraction of the entire Google News traffic (millions of users) over a period of 5-6 months. We observe that, on an average, CVBiased and CSBiased are better by 38% as compared with the baseline Popular.

推薦系統-蔣凡 2.5.2小節
實驗在實時資料上對比了新技術和一種非個性化的方法，這種方法將文章根據最近的熱度排序。為了對比兩種方法，推薦列表中間隔插入了兩種演算法的推薦物品。實驗結論根據物品得到的使用者點選數衡量，個性化方法明顯佔優勢（大約38%），個性化 > Popular > 不使用推薦，推理，Google新聞有38%的點選量來自推薦。
https://zhuanlan.zhihu.com/p/30898729

[4] Smith B, Linden G. Two decades of recommender systems at Amazon. com[J]. Ieee internet computing, 2017, 21(3): 12-18.

Youtube的推薦佔了總視訊點選的60%。
https://blog.csdn.net/DASlab/article/details/48598095
[5] Davidson J, Liebald B, Liu J, et al. The YouTube video recommendation system[C]// Acm Conference on Recommender Systems. 2010.

Amazon：亞馬遜20%~30%的銷售來於推薦系統。-項亮《推薦系統實踐》Page7
Amazon：亞馬遜35%的收入來自其推薦引擎。
35% of Amazon.com’s revenue is generated by its recommendation engine.

http://rejoiner.com/resources/amazon-recommendations-secret-selling-online/

**如需轉載，請註明出處：**https://mp.csdn.net/mdeditor/84931230