KDD 2021｜Meituan and multiple universities proposed a multi-task learning model, which has been applied to the scene of co-branded card acquisition

Many applications usually need to use targeted display advertising to acquire customers. For credit card advertising, due to the long link in user conversion, continuous and effective customer acquisition is more challenging than traditional advertising. This article combines the specific practice of Meituan’s joint credit card business and the paper published on KDD 2021 this year. This article introduces an adaptive information migration multitasking (AITM) framework through which the user’s multi-step transformation can be modeled. Sequence dependencies and improve end-to-end customer acquisition conversion rate. I hope to be helpful or inspiring to students who are engaged in related research.

Paper download: "Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertising"

Source code: https://github.com/xidongbo/AITM

Job Offers

Meituan's financial intelligence application team continues to recruit algorithm positions, and sincerely recruits outstanding algorithm engineers and experts, located in Beijing/Shanghai. Recruitment positions include:

Marketing Algorithm Engineer/Expert

• Serving various business scenarios of Meituan Finance, responsible for the algorithm design and development of marketing acquisition, retention and promotion scenarios, and integrated machine learning and optimization technology to solve financial marketing problems;
• Precipitate algorithm platform capabilities, improve the efficiency of algorithm applications, and provide intelligent solutions such as customer group mining, rights distribution, material matching, dynamic creativity, operational planning, and precise reach;
• Combining with Meituan's financial business scenarios, it explores and innovates cutting-edge artificial intelligence technologies such as deep learning, reinforcement learning, and knowledge graphs, and implements the precipitation and implementation of innovative technologies.

Control Algorithm Engineer/Expert

• Continuously improve the ability to identify financial risk behaviors through the development and optimization of machine learning models and strategies;
• Deeply understand the business, apply machine learning technology to improve the degree of automation of risk control work, and comprehensively improve business efficiency;
• Follow up with the cutting-edge technology of artificial intelligence, and explore the landing in financial risk control scenarios.

NLP algorithm engineer/expert

• Based on the Meituan financial business scenario, combined with natural language processing and machine learning related technologies, the intelligent dialogue robot is applied to financial marketing, risk management, customer service and other scenarios;
• Participate in the research and development of dialogue robot related projects, including but not limited to the development and optimization of related algorithms such as semantic understanding and multi-round dialogue management;
• Continue to follow up the development of related technologies in academia and industry, and quickly apply them to projects.

Interested students are welcome to send their resumes to: [e-mail] (the subject of the email indicates: Meituan Financial Intelligence Application Team).

references

• [1] Jiaqi Ma, Zhe Zhao, Xinyang Yi, Jilin Chen, Lichan Hong, and Ed H Chi. 2018. Modeling task relationships in multi-task learning with multi-gate mixture-of-experts. In KDD. 1930–1939.
• [2] Zhen Qin, Yicheng Cheng, Zhe Zhao, Zhe Chen, Donald Metzler, and Jingzheng Qin. 2020. Multitask Mixture of Sequential Experts for User Activity Streams. In KDD. 3083–3091.
• [3] Hongyan Tang, Junning Liu, Ming Zhao, and Xudong Gong. 2020. Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations. In RecSys. 269–278.
• [4] Yixuan Li, Jason Yosinski, Jeff Clune, Hod Lipson, and John E Hopcroft. 2016. Convergent Learning: Do different neural networks learn the same representations? In ICLR.
• [5] Matthew D Zeiler and Rob Fergus. 2014. Visualizing and understanding convolutional networks. In ECCV. 818–833.
• [6] Eric Tzeng, Judy Hoffman, Ning Zhang, Kate Saenko, and Trevor Darrell. 2014. Deep domain confusion: Maximizing for domain invariance. arXiv preprint arXiv:1412.3474 (2014).
• [7] Chen Gao, Xiangnan He, Dahua Gan, Xiangning Chen, Fuli Feng, Yong Li, Tat-Seng Chua, and Depeng Jin. 2019. Neural multi-task recommendation from multi-behavior data. In ICDE. 1554–1557.
• [8] Chen Gao, Xiangnan He, Danhua Gan, Xiangning Chen, Fuli Feng, Yong Li, Tat-Seng Chua, Lina Yao, Yang Song, and Depeng Jin. 2019. Learning to Recommend with Multiple Cascading Behaviors. TKDE (2019).
• [9] Xiao Ma, Liqin Zhao, Guan Huang, ZhiWang, Zelin Hu, Xiaoqiang Zhu, and Kun Gai. 2018. Entire space multi-task model: An effective approach for estimating post-click conversion rate. In SIGIR. 1137–1140.
• [10] Hong Wen, Jing Zhang, Yuan Wang, Fuyu Lv, Wentian Bao, Quan Lin, and Keping Yang. 2020. Entire Space Multi-Task Modeling via Post-Click Behavior Decomposition for Conversion Rate Prediction. In SIGIR. 2377–2386.
• [11] https://tianchi.aliyun.com/datalab/dataSet.html?dataId=408

Read more technical articles from the

the front | algorithm | backend | data | security | operation and maintenance | iOS | Android | test

| in the menu bar dialog box of the official account, and you can view the collection of technical articles from the Meituan technical team over the years.

| This article is produced by the Meituan technical team, and the copyright belongs to Meituan. Welcome to reprint or use the content of this article for non-commercial purposes such as sharing and communication, please indicate "the content is reproduced from the Meituan technical team". This article may not be reproduced or used commercially without permission. For any commercial activity, please send an email to [e-mail] to apply for authorization.