A Sequential Pattern Detection and Sentiment Analysis Combined Approach to the Churn Prediction Problem in Client Relationship Management Environments

The cost of losing profitable customers in competitive markets is driving companies to engage in customer retention. Therefore, anticipating client churn (i.e., cancellation) becomes essential. Among the researches on churn prediction models, we highlight those that are based on sequential pattern detection. Although promising, such initiatives do not take into account the sentiments present in the client’s interactions with the company. Given the above, this article proposes a method that generates churn prediction models from the combination of sequential pattern detection with sentiment extraction from the interactions with the clients. Experimental results confirm the adequacy of the proposed method.