A customer churn occurs when customers or subscribers stop doing business with a company or service. In the case of the telecom sector, it usually occurs when a customer leaves that company to start a new agreement with another competing company.
The aftermath of customer churn are long reaching. Your company loses every future opportunity with that customer. For example, the chance to upsell them with other products or services that you later implement in your business, while also inducing indirect costs in the form of brand reputation.
Because of that, one of the most important KPIs in a telecom company is churn ratio.
By applying artificial intelligence, the churn ratio can be reduced while reducing the costs. For that reason, we were contacted by a telecom company to develop a project that had the objective of preventing customer churn.
Usually, in churn prevention cases, the number of clients that abandon your company (positives) is a lot lower than those who continue being your customers (negatives). That means the data is not well balanced, which can complicate the data analysis and make the predictive model tend to always predict negative results.
Giving the complex nature of customer churn, we can assume that there is not just a single variable with a very high logistic correlation to our target.
As you can see from the graph above, none of the variables have more than 10% influence in churn decisions.
Our team studied different possibilites for this project, but the one which worked best was building our own predictive model and decreasing the negative effect that bad balanced data sets on most models. Those models indicated a lot of precision and specificity, however, as it is not a balanced data set, they are not good indicators. Also, the sensitivity for models that do not take unbalanced data sets into account can be really poor.
On the other hand, Artelnics' predictive model uses a self developed algorithm which minimizes the weighted quadratic error. By using it, the problems asociated with bad balanced data sets get solved, as it is in this case.
From this graph, you can see that our model has a relatively low precision, that means some clients our model predicts are going to churn when in reality they do not. However, knowing that the sensitivity is 75%, a low precision might indicate that those who the model predict as churn and do not abandon the company are high-risk customers.
The quality of the model can also be measured calculating the area under the ROC curve. In this case, the area is 0.78, which indicates a good performance.
Using our artificial intelligence technology in the telecom sector has a lot of benefits for companies, including churn prevention or customer targeting. With Artelnics technology, our customers can predict high-risk clients, generating more possibilites to stop that churn and continue generating benefits for the company.
As it was expressed before, stoping churn is very important because it generates direct and indirect costs while also denying every future possibility to obtain income from that customer.
Contact our team to see how we can help you achieving your goals.