The hidden keywords: An algorithmic approach to uncovering the value of negative keywords in search advertising
Hieu Pham et al.
Abstract
This article introduces a new approach to refining keyword management in search engine advertising (SEA) for e‐commerce. We address a critical problem advertisers face in managing their SEA campaigns by identifying and excluding non‐performing search queries, commonly referred to as negative keywords, to enhance the efficiency of advertising campaigns. Utilizing advanced natural language techniques, we transform textual search queries into high‐dimensional vectors for semantic similarities. An optimization model then identifies the optimal subset of keywords for exclusion, minimizing unnecessary ad expenditure while maintaining sales. Unlike traditional approaches that depend on reactive measures, typically waiting for a predetermined threshold of non‐converting clicks, our method proactively identifies and excludes non‐performing keywords before significant ad costs are incurred, allowing for early intervention, and reducing wasteful expenditure. Our empirical analysis demonstrates significant cost savings and improved ad spend efficiency, offering businesses a strategic advantage in digital marketing. This study contributes a novel, data‐driven approach to SEA, empowering advertisers with actionable intelligence for managing their keyword strategies effectively.
Evidence weight
Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40
| F · citation impact | 0.50 × 0.4 = 0.20 |
| M · momentum | 0.50 × 0.15 = 0.07 |
| V · venue signal | 0.50 × 0.05 = 0.03 |
| R · text relevance † | 0.50 × 0.4 = 0.20 |
† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.