Competition-Aware CPC Forecasting with Near-Market Coverage

TL;DR

This paper introduces a competition-aware approach to forecast CPC in paid search by leveraging semantic, behavioral, and geographic signals to approximate latent competition, improving stability and accuracy over various forecasting horizons.

Contribution

It presents a novel multi-signal framework combining semantic, behavioral, and geographic data to enhance CPC forecasting in auction markets, addressing partial observability of competition.

Findings

Competition-aware augmentation improves forecast stability.

Semantic and geographic priors enhance long-term accuracy.

Method outperforms statistical and neural baselines.

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.