Efficient and Effective Algorithms for Revenue Maximization in Social Advertising

TL;DR

This paper introduces new efficient algorithms for revenue maximization in social advertising, improving approximation ratios and outperforming existing methods in experiments on multiple datasets.

Contribution

The paper presents novel approximation algorithms for social advertising revenue maximization, with significant improvements over prior ratios and practical efficiency.

Findings

Algorithms outperform existing methods in solution quality.

Algorithms are more computationally efficient.

Experimental results on four datasets validate improvements.

Abstract

We consider the revenue maximization problem in social advertising, where a social network platform owner needs to select seed users for a group of advertisers, each with a payment budget, such that the total expected revenue that the owner gains from the advertisers by propagating their ads in the network is maximized. Previous studies on this problem show that it is intractable and present approximation algorithms. We revisit this problem from a fresh perspective and develop novel efficient approximation algorithms, both under the setting where an exact influence oracle is assumed and under one where this assumption is relaxed. Our approximation ratios significantly improve upon the previous ones. Furthermore, we empirically show, using extensive experiments on four datasets, that our algorithms considerably outperform the existing methods on both the solution quality and computation efficiency.