A methodology based on Deep Learning for advert value calculation in CPM, CPC and CPA networks

Miralles-Pechuán, Luis; Rosso, Dafne; Jiménez, Fernando; García, Jose M.

doi:10.1007/s00500-016-2468-4

A methodology based on Deep Learning for advert value calculation in CPM, CPC and CPA networks

Journal

Soft Computing

ISSN

1432-7643

1433-7479

Date Issued

2016

Author(s)

Miralles-Pechuán, Luis

Rosso, Dafne

Jiménez, Fernando

García, Jose M.

Type

Resource Types::text::journal::journal article

DOI

10.1007/s00500-016-2468-4

URL

https://scripta.up.edu.mx/handle/20.500.12552/4410

Abstract

In this research, we propose a methodology for advert value calculation in CPM, CPC and CPA networks. Accurately estimating this value increases the three previous networks’ incomes by selecting the most profitable advert. By increasing income, publishers are better paid and improved services are afforded to advertisers. To develop this methodology, we propose a system based on traditional Machine Learning methods and Deep Learning methods. The system has two inputs and one output. The inputs are the user visit and the data about the advertiser. The output is the advert value expressed in dollars. Deep Learning predicts model behavior more precisely for many supervised problems. The three experiments carried out allow us to conclude that DL is a supervised method that is very efficient in the classification of spam adverts and in the estimation of the CTR. In the prediction of online sales, DLNN have shown, on average, worse performance than cubist and random forest methods, although better performance than model tree, model rules and linear regression methods.