Enhancing Product Promotion in Social Networks: Leveraging Adaptive Discount-Offering and the Crowd Effect

Product promotion on social media platforms has revolutionized advertising, with the crowd effect playing a crucial role. This effect capitalizes on individuals' exposure to product opinions shared online. People are more likely to make purchases when they see others endorsing the product through likes and positive feedback. In our study, we integrate this crowd effect into our modeling of information diffusion on social networks. Our goal is to optimize influence through adaptive discount offering to prospective customers. To achieve this, we develop a model based on two widely used diffusion models, namely the independent cascade and linear threshold models. We formulate our decision problem as a Markov decision process. Then, we demonstrate that our problem does not satisfy the adaptive submodular property due to an additional global state variable, rendering the greedy policy suboptimal without performance guarantees. To tackle this challenge, we propose a rolling horizon method with fluid approximation, utilizing an offline upper bound to guide our online decision-making process. We also conduct numerical experiments to evaluate our method on random and real networks. Our method outperforms benchmark methods by a significant margin, achieving up to double the performance on random graphs and up to 63.12% improvement on real networks.