ABSTRACT
Factorization machines (FMs) are a state-of-the-art model class for user response prediction in the computational advertising domain. Rapid growth of internet and mobile device usage has given rise to multiple customer touchpoints. This coupled with factors like high cookie churn rate results in a fragmented view of user activity at the advertiser»s end. Current literature assumes procured user signals as the absolute truth, which is contested by the absence of deterministic identity linkage across a user's multiple avatars. In this work, we characterize the data uncertainty using Robust Optimization (RO) paradigm to design approaches that are immune against perturbations. We propose two novel algorithms: robust factorization machine (RFM) and its field-aware variant (RFFM), under interval uncertainty. These formulations are generic and can find applicability in any classification setting under noise. We provide a distributed and scalable Spark implementation using parallel stochastic gradient descent. In the experiments conducted on three real-world datasets, the robust counterparts outperform the baselines significantly under perturbed settings. Our experimental findings reveal interesting connections between choice of uncertainty set and the noise-proofness of resulting models.
- Adroll. 2016. Factorization Machines. http://tech.adroll.com/blog/data-science/2015/08/25/factorization-machines.htmlGoogle Scholar
- Dimitris Bertsimas, David B. Brown, and Constantine Caramanis. 2011. Theory and Applications of Robust Optimization. SIAM Rev., Vol. 53, 3 (Aug.. 2011), 464--501. https://books.google.co.in/books?id=x6hoBG_MAYIC Google ScholarDigital Library
- Jun Wang, Weinan Zhang, and Shuai Yuan. 2016. Display Advertising with Real-Time Bidding (RTB) and Behavioural Targeting. CoRR Vol. abs/1610.03013 (2016). showeprint{arxiv}1610.03013 http://arxiv.org/abs/1610.03013 Google ScholarDigital Library
- Matei Zaharia, Reynold S. Xin, Patrick Wendell, Tathagata Das, Michael Armbrust, Ankur Dave, Xiangrui Meng, Josh Rosen, Shivaram Venkataraman, Michael J. Franklin, Ali Ghodsi, Joseph Gonzalez, Scott Shenker, and Ion Stoica. 2016. Apache Spark: A Unified Engine for Big Data Processing. Commun. ACM, Vol. 59, 11 (Oct.. 2016), 56--65. showISSN0001-0782 Google ScholarDigital Library
- Qian Zhao, Yue Shi, and Liangjie Hong. 2017. GB-CENT: Gradient Boosted Categorical Embedding and Numerical Trees Proceedings of the 26th International Conference on World Wide Web (WWW '17). International World Wide Web Conferences Steering Committee, Republic and Canton of Geneva, Switzerland, 1311--1319. Google ScholarDigital Library
- Martin Zinkevich, Markus Weimer, Lihong Li, and Alex J. Smola. 2010. Parallelized Stochastic Gradient Descent. Advances in Neural Information Processing Systems 23, bibfieldeditorJ. D. Lafferty, C. K. I. Williams, J. Shawe-Taylor, R. S. Zemel, and A. Culotta (Eds.). Curran Associates, Inc., 2595--2603. http://papers.nips.cc/paper/4006-parallelized-stochastic-gradient-descent.pdf Google ScholarDigital Library
Index Terms
- Robust Factorization Machines for User Response Prediction
Recommendations
Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising
WWW '18: Proceedings of the 2018 World Wide Web ConferenceClick-through rate (CTR) prediction is a critical task in online display advertising. The data involved in CTR prediction are typically multi-field categorical data, i.e., every feature is categorical and belongs to one and only one field. One of the ...
Field-aware Factorization Machines for CTR Prediction
RecSys '16: Proceedings of the 10th ACM Conference on Recommender SystemsClick-through rate (CTR) prediction plays an important role in computational advertising. Models based on degree-2 polynomial mappings and factorization machines (FMs) are widely used for this task. Recently, a variant of FMs, field-aware factorization ...
User Response Prediction in Online Advertising
Online advertising, as a vast market, has gained significant attention in various platforms ranging from search engines, third-party websites, social media, and mobile apps. The prosperity of online campaigns is a challenge in online marketing and is ...
Comments