Use of Grid Search in Hyper-Parameter Selection for Time Series Analysis: A Case Studywith Ad Mediation Software
Published in International Data Science & Engineering Symposium, 2019
The success of an Ad Mediation Software’s decision on from which ad network torequest ads and in which order depends on the ability to estimate eCPM (effective Cost Per Mille)value used to measure ad revenue. This value varies for different applications depending ondifferent external factors. It is not possible for domain experts to make successful predictions byanalyzing different sets of external factors for a large number of applications and to keep theseestimates constantly up to date. Therefore, eCPM values were automatically estimated separatelyfor each application based on different advertising spaces and different countries using time seriesanalysis. The ARIMA model was used to estimate and the hyper-parameters of the model wereoptimized by using grid search method. For most of the values obtained, it was found that thevalues obtained with the intuition of domain experts were closer to the actual values.
Recommended citation: Giray, G., Tahmaz, Ş., & Ünalır, M. O. (2019, May). Use of Grid Search in Hyper-Parameter Selection for Time Series Analysis: A Case Studywith Ad Mediation Software. In 1st International Data Science & Engineering Symposium (pp. 97-106).
Download Paper