Adaptive preference measurement with unstructured data

R Dew - Management Science, 2024 - pubsonline.informs.org
Many products are most meaningfully described using unstructured data such as text or
images. Unstructured data are also common in e-commerce, in which products are often …

Probabilistic machine learning: New frontiers for modeling consumers and their choices

R Dew, N Padilla, LE Luo, S Oblander, A Ansari… - International Journal of …, 2024 - Elsevier
Making sense of massive, individual-level data is challenging: marketing researchers and
analysts need flexible models that can accommodate rich patterns of heterogeneity and …

A theory-based explainable deep learning architecture for music emotion

H Fong, V Kumar, K Sudhir - Marketing Science, 2024 - pubsonline.informs.org
This paper develops a theory-based, explainable deep learning convolutional neural
network (CNN) classifier to predict the time-varying emotional response to music. We design …

A theory-based interpretable deep learning architecture for music emotion

H Fong, V Kumar, K Sudhir - Available at SSRN 4025386, 2023 - papers.ssrn.com
This paper develops a theory-based, explainable deep learning convolutional neural
network (CNN) classifier to predict the time-varying emotional response to music. We design …

Using quantum game theory to model competition

VR Rao, N Yang, S Zakerinia - Cornell SC Johnson College of …, 2024 - papers.ssrn.com
This paper examines the potential of quantum game theory in rethinking strategic
decisionmaking across foundational economic models. By embedding principles from …

Demand estimation with text and image data

G Compiani, I Morozov, S Seiler - 2023 - papers.ssrn.com
We propose a demand estimation method that allows researchers to estimate substitution
patterns from unstructured image and text data. We first employ a series of machine learning …

Unraveling multifaceted user preferences on content platforms: A Bayesian deep learning approach

M Yin, Z Cong, J Liu - Available at SSRN 5051742, 2024 - papers.ssrn.com
Given the increasing importance of user engagement on digital content platforms, this paper
proposes a Bayesian deep learning model, called the Multi-Dynamic Neural Poisson …

Learning Design Preferences through Design Feature Extraction and Weighted Ensemble

D Shin, S Lee, N Kang - arxiv preprint arxiv:2405.07193, 2024 - arxiv.org
Design is a factor that plays an important role in consumer purchase decisions. As the need
for understanding and predicting various preferences for each customer increases along …

Using AI for controllable stimuli generation: An application to gender discrimination with faces

LE Luo, O Toubia - Available at SSRN 4865798, 2024 - papers.ssrn.com
Natural stimuli involving unstructured data like images can be decomposed into many latent
features, which may be highly correlated and partially unobserved to the researcher. This …

Beyond Fake or Genuine--The Effect of Large Language Models (LLMs) on the Content and Sentiment of Product Reviews

L Ma, L Luo - USC Marshall School of Business Research Paper …, 2023 - papers.ssrn.com
Abstract “ChatGPT has revolutionized the way people engage with and create product
reviews... Its ability to understand and generate human-like text enables it to generate high …