Social media optimization: Identifying an optimal strategy for increasing network size on Facebook

• We build a novel expert system to create an optimal strategy for increasing network size on Facebook.
• An unprecedented variety of data (426 predictors) were obtained from 5488 Facebook users.
• The system is built using Random Forest and a Genetic Algorithm.
• It is a viable strategy for increasing network size.
• A list with the top predictors is provided.

This paper aims to create an expert system that yields an optimal strategy for increasing network size on Facebook. Data were obtained from 5488 Facebook users by means of a custom-built Facebook application. We computed a total of 426 variables. Using these data we estimated a predictive model of network size which is subsequently used in a prescriptive model. The former is estimated with Random Forest and the latter with a Genetic Algorithm. The results indicate that the proposed expert system can identify an optimal social media strategy. The system delivers concrete recommendations about, for example, the optimal time between status updates. The analysis reveals that network size can be increased by 61% if the optimal strategy is adopted. This study contributes to literature in the following two ways. First it devises a novel prescriptive social media expert system relying on an unprecedented variety of social media data. The results indicate that the system is effective and a viable strategic tool for increasing network size. Second it provides a list of the top drivers allowing future research to build similar systems efficiently.