Abstract
In the field of advertising technology, it is a key task to forecast posterior click distribution since 66% of advertising transactions depend on cost per click model. However, due to the General Data Protection Regulation, machine learning techniques to forecast posterior click distribution based on the sequences of an identified user’s actions are restricted in European countries. To overcome this barrier, we introduce a contextual behavior concept for the advertising network environment and propose a new hybrid model, which we call the Long Short Term Memory—Hawkes model by combining a stochastic-based generative model and a machine learning-based predictive model. Also, to meet the computational efficiency for the heavy demand in mobile advertisement market, we define gradient exponential kernel with just three hyper parameters to minimize residuals. We have carefully tested our proposed model with production data and found that the LSTM-Hawkes model reduces the Mean Squared Error by at least 27.1% and up to 83.8% on average in comparison to the existing Hawkes Process based algorithm, Hawkes Intensity Process, as well as 39.77% on average in comparison to Multivariate Linear Regression. We have also found that our proposed model improves the forecast accuracy by about 21.2% on average.
Highlights
For the first time in 2017, global digital advertisement expenditure was 41% of the global advertising market, which exceeded the TV advertisement expenditure by 6%
We evaluated the forecasting accuracy of the posterior distribution of a click event from a single advertising network
Let ti be a point process with intensity λ(ti) whose PDF is Eq (10) and si be equal to λ(ti) of Eq (5), si becomes a unit rate Poisson process transformed by a Hawkes model
Summary
For the first time in 2017, global digital advertisement expenditure was 41% of the global advertising market, which exceeded the TV advertisement expenditure by 6%. The mobile advertisement in digital marketing recorded 37.6% of the global growth rate, which is an impressive increase, enough to draw attention in the worldwide advertisement market [1]. These reports [2,3,4] substantiate that the mobile advertising market is leading the growth in the global advertising market. Despite the rapid market growth, there is a controversial issue that Ad Tech faces. General Data Protection Regulation (GDPR) [5] has been actively enforced by EU since 25 May 2018
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have