| Resumo: | The world has been shaping itself for a digital overhaul, forcing many industries to radically adapt and find new and innovative procedures. In the health insurance industry, this transformation has pushed companies to expand from their traditional salesperson methods to more sophisticated online networks, with readily available solutions. In addition, a shift in logic has increased the leveraging power of customers, becoming drivers of innovation through the data that they provide to firms. Consequently, the main objective of this dissertation is to explore how collecting customer satisfaction data can aid in the prediction of the distribution channel of choice when buying health insurance. By working closely with a real company, Saúde Prime, we delve into the current state of the industry, identify key roles in the service-ecosystem, such as intermediaries, and examine how customers value health insurance services. To easily take advantage of this data, Machine Learning algorithms were used, due to their scalability and interpretability towards complex features. The predictive analysis introduces customer satisfaction metrics as a strong predictor of customer’s preferences in regard to the chosen channel - intermediary - for purchasing health insurance, connected to the level of technological literacy and the degree of importance given to the relationship with the mediator. Results indicate that most customers will opt for traditional channels, presenting a digital landscape still in its inception phase.
|
|---|