Competition-Aware CPC Forecasting with Near-Market Coverage

2026-03-13

AI Summary

This study addresses the instability in cost-per-click (CPC) prediction in paid search advertising caused by partially observable competitive environments. To this end, the authors propose a competition-aware spatiotemporal graph forecasting model that integrates keyword semantics—extracted via a pretrained Transformer—with CPC temporal dynamics aligned through dynamic time warping, as well as geographic market structure. These components jointly construct a semantic keyword graph and behavioral neighborhoods to approximate latent competitive states, which serve as relational priors in the graph-based model. Evaluated on a weekly CPC prediction task across 1,811 keywords, the proposed approach demonstrates significantly improved accuracy and robustness in medium- to long-term forecasting compared to statistical and classical time series baselines.

Technology Category

• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Cost-per-click (CPC) in paid search is a volatile auction outcome generated by a competitive landscape that is only partially observable from any single advertiser's history. Using Google Ads auction logs from a concentrated car-rental market (2021--2023), we forecast weekly CPC for 1,811 keyword series and approximate latent competition through complementary signals derived from keyword text, CPC trajectories, and geographic market structure. We construct (i) semantic neighborhoods and a semantic keyword graph from pretrained transformer-based representations of keyword text, (ii) behavioral neighborhoods via Dynamic Time Warping (DTW) alignment of CPC trajectories, and (iii) geographic-intent covariates capturing localized demand and marketplace heterogeneity. We extensively evaluate these signals both as stand-alone covariates and as relational priors in spatiotemporal graph forecasters, benchmarking them against strong statistical, neural, and time-series foundation-model baselines. Across methods, competition-aware augmentation improves stability and error profiles at business-relevant medium and longer horizons, where competitive regimes shift and volatility is most consequential. The results show that broad market-outcome coverage, combined with keyword-derived semantic and geographic priors, provides a scalable way to approximate latent competition and improve CPC forecasting in auction-driven markets.

Problem

• CPC forecasting
• latent competition
• paid search
• auction dynamics
• market volatility

Innovation

• competition-aware forecasting
• semantic keyword graph
• Dynamic Time Warping
• spatiotemporal graph neural networks
• latent competition approximation