Performance analysis of keyword advertising campaign using gender-brand effect of search queries

Performance analysis of keyword advertising campaign using gender-brand effect of search queries
Performance Analysis of Keyword Advertising Campaign Using Gender-Brand Effect of Search Queries

In this research, we analyze the relationship among (1) the performance metrics of a sponsored search campaign, (2) the gender orientation of queries, and (3) the occurrence of branded terms in queries.

The aim of this research is to investigate the effectiveness of increased personalization of search engine advertising in order to improve the consumer’s online experience.

We segregate keyphrases from a dataset covering thirty-three consecutive months from a major US retailer consisting of 7 million daily records of a real time keyword advertising campaign into three gender categories (male, female and neutral) each with two groups (branded and unbranded) term usage.

Using ANOVA, we analyze the effect of gender and brand keyphrases on critical sponsored search performance metrics of impressions, clicks, cost-per-clicks, sales revenue, orders, items purchased and return on advertising.

Research findings show that the combination of brand focus with the gender-orientation of keyphrases is a significant factor in predicting sponsored search performance and behavior. There are statistically significant variations in consumer behavior as measured by sponsored search metrics among the gender categories.

Specifically, females are more attracted to the use of branded terms than males, perhaps due to the trust and customer loyalty generated by brand image.

Our results establish that positive brand reputation creates dramatic influence on consumer’s loyalty over the brand and hence strongly affects their interests, activities and purchasing behavior in e-commerce environment.

Mukherjee, P. and  Jansen, B. J. (2014) Performance Analysis of Keyword Advertising Campaign Using Gender-Brand Effect of Search Queries. Electronic Commerce Research and Applications. 13(2), 139–149.