In this chapter, we discussed the end-to-end steps involved in a machine learning project, taking two common customer analytics use cases, churn analytics and customer segmentation, as examples. We considered structured data for building the models. Many of the techniques learned up until now where put into practice. We discussed data cleansing, feature engineering, and model efficacy. A robust and repeatable step-by-step plan, which puts equal importance on all phases of a machine learning project, is important to its success.

In the last chapter, we will continue with the same theme and discuss text analytics use cases. Text analytics is an example of using unstructured data to gain insight and build models. We will cover the end-to-end steps that need to be performed to analyze text. The use cases that will be covered are text clustering and classification.