An Improved Approach for Long Tail Advertising in Sponsored Search

• Published in: Database Systems for Advanced Applications Vol. 10178; pp. 169 - 184
• Main Authors: Budhiraja, Amar, Reddy, P. Krishna
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2017; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Computational advertising; Coverage Patterns; Data mining; Pattern mining; Sponsored search
• ISBN: 3319556983; 9783319556987
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-319-55699-4_11

Search queries follow a long tail distribution which results in harder management of ad space for sponsored search. During keyword auctions, advertisers also tend to target head query keywords, thereby creating an imbalance in demand for head and tail keywords. This leads to under-utilization of ad space of tail query keywords. In this paper, we have explored a mechanism that allows the advertisers to bid on concepts rather than keywords. The tail query keywords are utilized by allocating a mix of head and tail keywords related to the concept. In the literature, an effort has been made to improve sponsored search by extracting the knowledge of coverage patterns among the keywords of transactional query logs. In this paper, we propose an improved approach to allow advertisers to bid on high level concepts instead of keywords in sponsored search. The proposed approach utilizes the knowledge of level-wise coverage patterns to allocate incoming search queries to advertisers in an efficient manner by utilizing the long tail. Experimental results on AOL search query data set show improvement in ad space utilization and reach of advertisers.