Title | ||
---|---|---|
Do ads compete or collaborate?: designing click models with full relationship incorporated |
Abstract | ||
---|---|---|
Traditionally click models predict click-through rate (CTR) of an advertisement (ad) independent of other ads. Recent researches however indicate that the CTR of an ad is dependent on the quality of the ad itself but also of the neighboring ads. Using historical click-through data of a commercially available ad server, we identify two types (competing and collaborating) of influences among sponsored ads and further propose a novel click-model, Full Relation Model (FRM), which explicitly models dependencies between ads. On a test data, FRM shows significant improvement in CTR prediction as compared to earlier click models. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1145/2396761.2398528 | CIKM |
Keywords | Field | DocType |
significant improvement,click-through rate,neighboring ad,ctr prediction,historical click-through data,novel click-model,full relation model,test data,models dependency,click model,available ad server,full relationship | Data mining,Information retrieval,Computer science,Test data,Full Relation | Conference |
Citations | PageRank | References |
1 | 0.38 | 12 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xin Xin | 1 | 58 | 7.73 |
Irwin King | 2 | 6751 | 325.94 |
Ritesh Agrawal | 3 | 12 | 2.74 |
Michael R. Lyu | 4 | 10985 | 529.03 |
Heyan Huang | 5 | 173 | 61.47 |