Abstract:
|
SEKAID is a prediction methodology based on Shannon Entropy. From the analysis of clients’ insurance policy portfolios, it can be determined if the policy will be cancelled or not during a determined period of time. With the obtained results, marketing campaigns can be undertaken which allow the client loyalty of the portfolio to be improved. To demonstrate the effectiveness of this methodology, an automobile insurance portfolio is analyzed. A software application was developed to help perform the necessary tests in order to determine the most adequate configuration. |