Optimization of viral marketing in online businesses using genetic algorithm based decision tree

The purpose of this study is to identify the components and develop a model to provide rules for optimizing viral marketing in businesses. It is an applied research and in terms of method, it is mixed (quantitative and qualitative). The statistical population of the research in the qualitative part includes 15 people in the three generations X, Y and Z (Millennium marketing generation) and in the quantitative part includes 460 online buyers. Data collection tools were used in the qualitative part of projection technique and in-depth interview. Interviews were analyzed and summarized using MAXQDA software, through which six components were identified, and then in a small part of 12 experts were used to determine the index of CVR, and then exploratory factor analysis was performed by SPSS software. Because selecting the most effective new components of viral marketing can have a huge impact on the accuracy of the viral marketing model in online businesses, To identify the most effective components, genetic metaheuristic algorithm was used, which is the software used in this section, WEKA and RAPIDMINER. Finally, the rules of viral marketing optimization were identified using the decision tree method. Findings in the qualitative section indicate that online persuasion, online trust, online support, online services, online attractiveness and online risk-taking are components of viral marketing. In the quantitative section and genetic algorithm, it was shown that the online risk component could not be used as an effective component for modeling and extracting viral marketing rules, so it was removed from the six components.