6

广告深度预估技术在美团到店场景下的突破与畅想

 2 years ago
source link: https://tech.meituan.com/2021/10/14/breakthrough-and-prospect-of-deep-ctr-prediction-in-meituan-ads.html
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
neoserver,ios ssh client

广告深度预估技术在美团到店场景下的突破与畅想

2021年10月14日 作者: 胡可 文章链接 2093字 5分钟阅读

471e2ec462720f6baf5c9924c40a338c2288824.png817cb6d6b4a4cd5fc176acc1172416ee3929205.png51ce68ed362da6a5841abd6ebbf0acd92071875.png

  • [1] Friedman J H . Greedy Function Approximation: A Gradient Boosting Machine[J]. Annals of Statistics, 2001, 29(5):1189-1232.
  • [2] Rendle S. Factorization machines[C]//2010 IEEE International conference on data mining. IEEE, 2010: 995-1000.
  • [3] HT Cheng, et al. Wide & Deep Learning for Recommender Systems, 2016
  • [4] Zhou, Guorui, et al. “Deep interest network for click-through rate prediction.” Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2018
  • [5] Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts. ACM, 2018.
  • [6] Wen, Ling, Chua. A closer look at strategies for memorization.[J]. Clavier Companion, 2014, 6(6):50-52.
  • [7] Huang J, Hu K, Tang Q, et al. Deep Position-wise Interaction Network for CTR Prediction[J]. arXiv preprint arXiv:2106.05482, 2021.
  • [8] Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction
  • [9] Qi, Yi, et al. “Trilateral Spatiotemporal Attention Network for User Behavior Modeling in Location-based Search”, CIKM 2021.
  • [10] Overcoming catastrophic forgetting in neural networks[J]. Proceedings of the National Academy of Sciences of the United States of America, 2017.
  • [11] M. Zinkevich. Online convex programming and generalized infinitesimal gradient ascent. In ICML, 2003.
  • [12] Optimized Cost per Click in Taobao Display Advertising[C]// the 23rd ACM SIGKDD International Conference. ACM, 2017.
  • [13] https://tech.meituan.com/2020/08/20/kdd-cup-debiasing-practice.html

美团到店广告平台广告算法团队立足广告场景,探索深度学习、强化学习、人工智能、大数据、知识图谱、NLP和计算机视觉前沿的技术发展,探索本地生活服务电商的价值。主要工作方向包括:

  • 触发策略:用户意图识别、广告商家数据理解,Query改写,深度匹配,相关性建模。
  • 质量预估:广告质量度建模。点击率、转化率、客单价、交易额预估。
  • 机制设计:广告排序机制、竞价机制、出价建议、流量预估、预算分配。
  • 创意优化:智能创意设计。广告图片、文字、团单、优惠信息等展示创意的优化。

岗位要求

  • 有三年以上相关工作经验,对CTR/CVR预估、NLP、图像理解,机制设计至少一方面有应用经验。
  • 熟悉常用的机器学习、深度学习、强化学习模型。
  • 具有优秀的逻辑思维能力,对解决挑战性问题充满热情,对数据敏感,善于分析/解决问题。
  • 计算机、数学相关专业硕士及以上学历。

具备以下条件优先

  • 有广告/搜索/推荐等相关业务经验。
  • 有大规模机器学习相关经验。

感兴趣的同学可投递简历至:[email protected](邮件标题请注明:美团广平算法团队)。


About Joyk


Aggregate valuable and interesting links.
Joyk means Joy of geeK