Network advertisement effect estimating method and network advertisement effect estimating system

Abstract

The invention discloses a network advertisement effect estimating method, which comprises the following steps of: classifying original data according to an impact factor of an advertisement effect; extracting an impact sub-factor of the advertisement effect from the impact factor of the advertisement effect, and establishing at least one estimating model by adopting regression analysis and a re-sampling algorithm (Bagging); selecting an optimal estimating model from the estimating models by a tenfold crossed validation method; and estimating the advertisement effect within a next prediction period by utilizing the optimal estimating model so as to obtain an advertisement estimated effect. By the application of an embodiment of the invention, the high-precision prediction of an advertisement delivery effect can be performed, and the estimated effect is diversified.

Description

technical field [0001] The present invention relates to the field of network technologies, and more specifically, to a method and system for estimating the effect of network advertisements. Background technique [0002] Online advertising is called online advertising or Internet advertising, which is an advertising behavior with the computer as the core and the computer network as the medium. The level of the network advertisement effect estimation result is closely related to the direct income of the network advertisement. The existing advertising effect estimation method is an estimation method based on experience, that is, according to the actual effect data of the advertising position in the previous forecast period, the average value is taken as the forecast result of the next forecast period. [0003] For example, at the end of November, you want to estimate the number of exposures for a certain advertising position in December. The number of exposures is the total n...

AI Technical Summary

Problems solved by technology

[0004] However, there are many factors that affect the effect of advertising, and the influencing factors are different in different cycles. It is impossible to make an accurate prediction of the effect in the next cycle based on the actual effect data of the advertising space in the previous forecast cycle.

In addition, the experience-based estimation method obtains a single estimation result for different advertisements on the same advertising space, and cannot make different effect estimations according to different delivery conditions.

Images