{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-neural-net-with-attention-for-multi","title":"Deep Neural Net with Attention for Multi-channel Multi-touch Attribution","arxiv_id":"1809.02230","date":"2018-09-06","proceeding":null,"authors":["Ning li","Sai Kumar Arava","Chen Dong","Zhenyu Yan","Abhishek Pani"],"abstract":"Customers are usually exposed to online digital advertisement channels, such\nas email marketing, display advertising, paid search engine marketing, along\ntheir way to purchase or subscribe products( aka. conversion). The marketers\ntrack all the customer journey data and try to measure the effectiveness of\neach advertising channel. The inference about the influence of each channel\nplays an important role in budget allocation and inventory pricing decisions.\nSeveral simplistic rule-based strategies and data-driven algorithmic strategies\nhave been widely used in marketing field, but they do not address the issues,\nsuch as channel interaction, time dependency, user characteristics. In this\npaper, we propose a novel attribution algorithm based on deep learning to\nassess the impact of each advertising channel. We present Deep Neural Net With\nAttention multi-touch attribution model (DNAMTA) model in a supervised learning\nfashion of predicting if a series of events leads to conversion, and it leads\nus to have a deep understanding of the dynamic interaction effects between\nmedia channels. DNAMTA also incorporates user-context information, such as user\ndemographics and behavior, as control variables to reduce the estimation biases\nof media effects. We used computational experiment of large real world\nmarketing dataset to demonstrate that our proposed model is superior to\nexisting methods in both conversion prediction and media channel influence\nevaluation.","url_abs":"http://arxiv.org/abs/1809.02230v1","url_pdf":"http://arxiv.org/pdf/1809.02230v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-neural-net-with-attention-for-multi","repo_url":"https://github.com/GregMurray30/MultiTouchAttribution","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"marketing","task_name":"Marketing"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1809.02230","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}