Business Insights through Text
The BIT LAB
We explore, examine, and extract consumer behavior or market insights through abundantly available, yet severely untapped text data. Via a variety of methodologies including causal inference, generative models, deep learning, neural NLP, bayesian statistics, interpretable machine learning, etc spanning topics such as social media analytics, digital consumer management, persuasion, patents, and promotion, our studies are focused on providing empirical evidence and empirical generalization to develop or extend consumer behavior and market theories.
Doctoral Students
Samuel Levy
Sam Levy is a Marketing Ph.D. candidate in the Tepper School of Business, CMU. He uses and combines Bayesian {statistics, machine learning and econometrics} to (1) build predictive models of browsing and buying behavior using unstructured data (2) flexibly model consumer behavior and make policy recommendations for pricing and promotional strategies.
|
Zhaoqi Cheng
Zhaoqi Cheng is an Information Systems PhD student at Boston University, Questrom School of Business. He combines machine learning with econometrics models to explore large-scale data with text-heavy attributes, such as patent files, online forums and user reviews. He is currently working on generative models related to the representation and characterization of innovations.
|
Chen Jing
Chen Jing is a PhD student in Quantitative Marketing at Questrom School of Business, Boston University. His research interests include applying machine learning, econometrics, and statistical models to study brand communication, corporate social responsibility, and brand activism.
|
Chengfeng Mao
Chengfeng Mao is an incoming PhD student in Marketing at the MIT Sloan School of Management. He obtained his master's degree in Computer Science at Carnegie Mellon University. His research interests include applying machine learning to draw business and economic insights from unstructured data, such as text, image, and network graph.
|
