We forecast cost-per-click in paid search by approximating latent competition through semantic, behavioral, and geographic signals derived from Google Ads auction logs.
Mar 13, 2026
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.
Dec 8, 2025
We develop interpretable deep learning models for forecasting online advertising costs, providing insights into competitive bidding dynamics.
Jan 1, 2024
We develop interpretable deep learning models for online advertising revenue forecasting, balancing predictive accuracy with model transparency.
Nov 16, 2021