Research


[DBLP] [Google Scholar]

Publication List Sorted by Year

Current Research Interests

At Etsy, we work on a wide range of challenging problems related to e-commerce such as

  • Personalization and Recommendation
  • Search and Discovery
  • Computational Advertising
  • Image Understanding and Deep Learning

Before joining Etsy, I have worked on Personalization algorithms and models, recommender systems and information retrieval, Large-scale machine learning, inference algorithms, probabilistic models and Computational advertising at Yahoo Research.

Recent publications include:

  • K. Aryafar, D. Guillory and L. Hong. An Ensemble-based Approach to Click-Through Rate Prediction for Promoted Listings at Etsy. To appear in the proceedings of AdKDD & TargetAd 2017 workshop, held in conjunction with the 23rd SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2017), Halifax, Nova Scotia, August, 2017.
  • Y. Ning, Y. Shi, L. Hong, H. Rangwala and N. Ramakrishnan. A Gradient-based Adaptive Learning Framework for Efficient Personal Recommendation. To appear in the proceedings of the 11th ACM Conference on Recommender Systems (RecSys 2017), Como, Italy, August, 2017. (Full Paper, 20.8% Acceptance)
  • T. Chen, L. Hong, Y. Shi and Y. Sun. Joint Text Embedding for Personalized Content-based Recommendation. 2017. [ArXiv]
  • T. Chen, Y. Sun, Y. Shi and L. Hong. On Sampling Strategies for Neural Network-based Collaborative Filtering. To appear in the proceedings of the 23rd SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2017), Halifax, Nova Scotia, August, 2017. (Full Paper, 17% Acceptance) [Local Copy] [Local Supplementary] [Code]
  • Q. Zhao, Y. Shi and L. Hong. GB-CENT: Gradient Boosted Categorical Embedding and Numerical Trees. In the proceedings of the 26th International Conference on World Wide Web (WWW 2017), Perth, Australia, April, 2017. (Full Paper, 17% Acceptance) [Local Copy] [DOI]
  • L. Hong, Y. Shi and S. Rajan. Learning Optimal Card Ranking from Query Reformulation. 2016. [ArXiv]
  • L. Hong and A. Boz. An Unbiased Data Collection and Content Exploitation/Exploration Strategy for Personalization. 2016. [ArXiv]
  • M. Qian, L. Hong, Y. Shi and S. Rajan. Structured Sparse Regression for Recommender Systems [Short Paper]. In the proceedings of the 24th ACM International  Conference on Information & Knowledge Management (CIKM 2015). Melbourne, Australia.[Local Copy] [DOI]
  • X. YiL. HongE. ZhongNN. Liu and S. RajanBeyond Clicks: Dwell Time in Personalization. In the proceedings of the 8th ACM Conference on Recommender Systems (RecSys 2014), Foster City, Silicon Valley, USA, October, 2014. (Full Paper, 23% Acceptance) [Local Copy] [DOI]

Ph.D. Dissertation

My dissertation research lies primarily on the interface between social media and applied machine learning where I develop state-of-the-art machine learning techniques to analyze social media data in a large scale in an effective and efficient way. My dissertation topic is “Mining and Understanding Online Conversational Media“, focusong on following research topics:

[Whole Dissertation]

Other Topics