System and method for managing routing of customer calls to agents
摘要
說明書
In illustrative embodiments, the predictive model incorporated a logistic regression model with l1 regularization, for the lapse-only target. In one illustrative embodiment, this model was trained on all customers with individual-level data. In another illustrative embodiment, this model was trained on all customers with zip-level data. At a 70% resource constraint, the model with individual-level data was tested to provide an 11% reduction in lapse rate, while the model with zip-level data was tested to provide an 8% reduction in lapse rate. At a 60% resource constraint, the model with individual-level data was tested to provide a 14% reduction in lapse rate, while the model with zip-level data was tested to provide an 11% reduction in lapse rate.
While various aspects and embodiments have been disclosed, other aspects and embodiments are contemplated. The various aspects and embodiments disclosed are for purposes of illustration and are not intended to be limiting, with the true scope and spirit being indicated by the following claims.
