Yicheng Song 宋一丞

Image

Currently pursuing my Doctoral degree in Information Systems at Questrom School of Business, Boston University, advised by Prof. Nachiketa Sahoo and Prof. Chris Dellarocas. Previously, I received B.S. from Wuhan University in 2006 and Ph.D. of Computer Science from Institute of Computing Technology, Chinese Academy of Sciences in 2012.

 

 

595 commonwealth ave, office 519

Boston, MA 02215

Email: ycsong@bu.edu

Research Interests

  • Consumer's Path to Purchase
  • Online Media Market
  • Personalized Recommender Systems
  • Crowdfunding

Research Methods

  • Machine Learning
  • Bayesian Modeling
  • Economic Structural Modeling
  • Multimedia Mining
Go to Top

Projects

A MultiCategory Utility Model of Consumer Response to Content Recommendations

(with Nachiketa Sahoo,Elie Ofek)

Image

The diversity of a set of recommendations can improve consumers’ satisfaction with a personalized recommender system. However, diversifying a list of items for a one-shot recommendation sacrifices relevance, which can reduce its value. We identify a popular scenario, sessions of online news consumption, where one can increase the diversity of recommendations over an entire session while improving the relevance of each recommendation within the session. Our approach is based on a multi-category utility model that captures consumers’ preference towards different types of content, how quickly they satiate with one type and substitute it with another, and how they trade off potentially higher value from their own costly search efforts with the convenience of selecting from a recommended list to find new content. Taken together, these three elements enable us to characterize how utility maximizing consumers construct diverse “baskets” of content over the course of each session, and how likely they are to click on content recommended to them.

We estimate this model using a clickstream dataset from a large international media outlet and apply it to determine the most relevant content at different stages of online sessions. We find that recommendations based on our approach are not only more diverse over a session, better matching the diversity sought by individual consumers, but also 6%–14% more accurate than recommendations by optimized alternatives. Using a policy simulation, we estimate that following our approach would cause visitors to read 57% additional articles at the studied website, which has direct revenue implication for publishers.

Segment consumers based on their path-to-purchase

(with Nachiketa Sahoo, Shuba SrinivasanChris Dellarocas)

Image

The idea of path-to-purchase is often discussed in Research and Practice. We develop a method to identify the most common paths-to-purchase using multi-variate time-series datasets collected from CRM systems. The proposed approach involves using a generalized Vector Auto-Regression model to capture consumers’ movement from one activity to another (steps of the path), and at the same time identifying groups of consumers who have similar paths.

The proposed approach is evaluated on a large customer touch point dataset made available by the Wharton Customer Analytics Initiative. The multi-time period paths show distinct shopping behavior of customers in different groups. The value of knowing such paths is illustrated through an example application of targeted catalog mailing.

Go to Top

Papers

Working Papers
  • Yicheng Song, Nachiketa Sahoo, Shuba Srinivasan, Chrysanthos Dellarocas: Uncovering Characteristic Paths to Purchase of Consumers. 2nd round, Revised and Resubmitted to Information Systems Research (ISR)
  • Yicheng Song, Nachiketa Sahoo, Elie Ofek: ”When Diversity Becomes Relevant” A MultiCategory Utility Model of Consumer Response to Content Recommendations. Major Revision, invited to resubmit to Management Science.
  • Yicheng Song: Evolution of Ecosystem in Online Crowdfunding Communities.
Journal Papers
  • Yicheng Song, Yongdong Zhang, Juan Cao, Jinhui Tang, Xingyu Gao, Jintao Li: A Unified Geolocation Framework for Web Videos. ACM Transactions on Intelligent Systems and Technology 5(3): 49 (2014) [Top Journal in Intelligent Systems, 2014 Impact Factor: 9.39]
  • Yicheng Song, Yongdong Zhang, Juan Cao, Tian Xia, Wu Liu, JinTao Li: Web Video Geolocation by Geotagged Social Resources. IEEE Transactions on Multimedia 14(2): 456-470 (2012) [Top Journal in Multimedia Technology, 2015 Impact Factor: 2.53]
  • Zhineng Chen, Juan Cao, Tian Xia, Yicheng Song, Yongdong Zhang, Jintao Li: Web video retagging. Multimedia Tools Appl. 55(1): 53-82 (2011)
Conference Papers
  • Yicheng Song, Nachiketa Sahoo, Elie Ofek: ‘‘When Diversity Becomes Relevant”—A Multi-Category Utility Model of Consumer Response to Content Recommendations. Stanford 2016 Conference on Digital Marketing
  • Yicheng Song, Nachiketa Sahoo, Elie Ofek: ‘‘When Diversity Becomes Relevant”—A Multi-Category Utility Model of Consumer Response to Content Recommendations. 2016 Conference in Information Systems and Technology (CIST16)
  • Yicheng Song, Nachiketa Sahoo, Elie Ofek: "When Diversity Becomes Relevant”—A Multi-Category Utility Model of Consumer Response to Content Recommendations. 2016 Workshop on Information Systems Economics (WISE 2016)
  • Yicheng Song, Nachiketa Sahoo, Elie Ofek: Discovering Content: A Multi-Category Utility Model Of Consumer Response To Recommendations. 2016 ISMS Marketing Science Conference
  • Yicheng Song, Nachiketa Sahoo, Elie Ofek: Discovering Content: A Multi-Category Utility Model Of Consumer Response To Recommendations. Statistical Challenges in eCommerce Research (SCECR 2016)
  • Yicheng Song, Nachiketa Sahoo, Elie Ofek: Discovering Content: A Multi-Category Utility Model Of Consumer Response To Recommendations. 2016 Winter Conference on Business Intelligence
  • Yicheng Song, Nachiketa Sahoo, Shuba Srinivasan, Chrysanthos Dellarocas: Uncovering Paths-to-Purchase of Heterogeneous Consumer Population using Clustered Multivariate Autoregression’’, 2015 ISMS Marketing Science Conference
  • Yicheng Song, Nachiketa Sahoo, Shuba Srinivasan, Chrysanthos Dellarocas: Uncovering Paths-to-Purchase of Heterogeneous Consumer Population using Clustered Multivariate Autoregression. 2015 Winter Conference on Business Intelligence
  • Yicheng Song, Nachiketa Sahoo, Shuba Srinivasan, Chrysanthos Dellarocas: Uncovering Path-to-Purchase Segments in Large Consumer Population using Clustered Multivariate Autoregression. Workshop on Information Technologies and Systems (WITS ’14). WITS 2014 Best Paper Award
  • Yicheng Song, Nachiketa Sahoo, Shuba Srinivasan, Chrysanthos Dellarocas: Identifying paths-to-purchase segments via Clustered Vector Autoregression. Statistical Challenges in eCommerce Research Symposium (SCECR ’14)
  • Yicheng Song, Juan Cao, Zhineng Chen, Yongdong Zhang, Jintao Li: Tag transformer. ACM Multimedia 2010.
  • Zhineng Chen, Juan Cao, Yicheng Song, Junbo Guo, Yongdong Zhang, Jintao Li: Context-oriented web video tag recommendation, WWW 2010.
  • Yicheng Song, Yongdong Zhang, Xu Zhang, Juan Cao, Jintao Li: Google challenge: incremental-learning for web video categorization on robust semantic feature space. ACM Multimedia 2009.

    Go to Top

Teaching

Lecturer
  • Managing Data Resources (IS465) Spring ’16
Teaching Assistant
  • Advanced Business Analytics: Data Mining (IS841) Fall ’13, Fall ’14
  • Managing Data Resources (IS465) Fall ’14, Fall ’15, Fall ’16
  • IT Applications in Management (IS717) Spring ’14
  • Data Management Resources (IS 889) Summer '16
Teaching Interests
  • Business Analytics
  • Database Management
  • Social Media
  • IT Applications in Management
  • Online Markets and IT Innovation

Go to Top

Honors and Awards

  • Hariri Graduate Fellowship, 2016 ($10,000)
  • Best Ph.D. Research Paper, 2015 Questrom School of Business Faculty Research Day
  • Winner of Best Paper Award, 2014 Workshop on Information Technologies and Systems (WITS 2014)
  • Boston University School of Management Doctoral Fellowship, 2012-2016
  • Bei Wei Scholarships, 2011 (RMB 10,000)
  • Excellent Student Leader, Graduate University of Chinese Academy of Science, 2009-2010
  • Merit Student, Graduate University of Chinese Academy of Science, 2008-2009
Go to Top

Skills

  • Statistical Packages: R, Matlab, SAS Enterprise Miner.
  • Programming Languages: C, Java, C#, SQL.
  • Experiences: Hadoop, Spark, WEKA, Large Scale Multimedia Retrieval, Multimedia Clustering/Classification, Computer Vision, Open CV, Product Search Engine, Chinese NLP
Go to Top

References

Nachiketa Sahoo, Questrom School of Business, Boston University

Chris Dellarocas, Questrom School of Business, Boston University

Shuba Srinivasan, Questrom School of Business, Boston University

Elie Ofek, Harvard Business SchoolGo to Top

Disclaimer