We investigate the performance of organic Large Language Model traffic (oLLM) versus traditional digital channels in e-commerce.

We analyze how intermediary online firms sustain trade despite sanctions and stigma, examining their market role and resilience strategies.

We provide the first comprehensive evidence of Apple's App Tracking Transparency policy's impact on e-commerce firms, finding substantial revenue declines particularly among smaller firms highly dependent on Meta advertising.

We study how the 2025 suspension of the U.S. de minimis exemption affected cross-border trade on Etsy, finding an 18% decline in non-U.S. seller sales and a net contraction in marketplace activity.

We analyze the impact of EU energy efficiency relabeling on consumer purchase decisions using quasi-experimental methods.

We examine Google's AI Overviews rollout as a staggered platform shock, finding that it reduces organic e-commerce traffic while only partially improving conversion quality of surviving visits.

We analyze how ChatGPT referrals shape basket structure and category concentration in e-commerce, finding that generative AI functions as a distinct form of shopping intermediation.

We develop neural product embeddings to predict sales of new products, addressing the challenge of forecasting with limited historical data.

We analyze conversion rates in e-commerce, examining factors that influence customer purchase decisions in online retail.

We analyze how ChatGPT is disrupting traditional search behavior and its implications for Google's market dominance.

We forecast cost-per-click in paid search by approximating latent competition through semantic, behavioral, and geographic signals derived from Google Ads auction logs.

We develop a multimodal hierarchical classification framework for cross-platform e-commerce product categorization, combining CLIP embeddings with late-fusion for state-of-the-art accuracy and a self-supervised recategorization pipeline for discovering fine-grained categories.

We develop interpretable deep learning models for forecasting online advertising costs, providing insights into competitive bidding dynamics.

We develop interpretable deep learning models for online advertising revenue forecasting, balancing predictive accuracy with model transparency.

We analyze how Ukrainian firms have adapted to operating during wartime, examining business resilience and survival strategies.