Model deployment

One of the main purposes of this project is to produce good predictive models for the telco company to forecast Call Center calls on a daily basis and also to understand or even reduce subscriber churn, besides producing insights for some of the clients of this telco company. As discussed earlier, MLlib supports model export to Predictive Model Markup Language (PMML). Therefore, we export some developed models to PMML for this project so that the telco company can take them to integrate with their existing analytical and decision-making platforms.

In practice, the users for this project, executives of the telco company, are more interested in rule-based decision making to use some of our insights and also in score-based decision making to impact subscriber churns.

Specifically, as for this project, the client is interested in applying our results to (1) decide when an alert may be sent out if the number of service requests as forecasted will be very high, for which rules should...