Optimizing the Timing of Social Media Posts with Historical Data

Google Drive Link

Modern companies regularly use social media to communicate with their customers. In addition to the content, the popularity of a social media post may depend on the season, the day of the week, and the time of the day. We show how the timing of a post can be optimized based on historical data on previous posts and their popularity. We promote a prescriptive approach based on recent advances in causal inference and consider optimizing the timing of Facebook posts by a large Finnish consumers’ cooperative using historical data. We express the understanding of the causal relations in the form of a directed acyclic graph, use a state-of-the-art identification algorithm to obtain a formula for the causal effect, and finally estimate the required conditional probabilities with Bayesian generalized additive models. As a result, we obtain estimates for the expected popularity of a post for different counterfactual choices of timing.