Churn prediction is the process of creating a predictive model that estimates the likelihood of a customer canceling their service in a future period of time. Churn prediction is used to understand churn drivers, evaluate retention programs, and calculate the customer lifetime value. In this article, I will use my experience as a Director of … Read more
The difference between predictive and prescriptive analytics is that predictive analytics makes a prediction under business as usual conditions, and prescriptive analytics is focused on measuring the incremental impact of your action. If predictive analytics assesses the baseline, prescriptive analytics estimate how much you can change that baseline.
While propensity model does inform us about the natural likelihood to churn without any intervention, it tells us nothing about our ability to change customer behavior and stay longer.
Amazon Comprehend is a Natural Language Processing (NLP) platform available as a service on AWS. It’s a collection of pre-trained and operational NLP models that can be used with no or little coding through the point and click interface. In addition to point and click interface, you can call the services through the API directly from the terminal or python.
You likely saw this chart summarizing three different types of analytics before: descriptive, predictive, and prescriptive. Let me walk you through different types of analytics by using a simple marketing example.
SAS has created a special feature in Enterprise Miner called Incremental Response modeling that helps you find relevant input attributes differentiating between customers have higher incremental response rates and those that don’t. A modeling procedure can predict uplift for every customer and then put customers into deciles based on their potential incremental response due to a marketing campaign.
Uplift modeling is generally harder to execute than response or propensity modeling. While response follows known customer traits (demographics, lifestage, transience, change in circumstances), uplift can be dependent on variables not commonly used for analysis. After watching a few failed attempts to create uplift models, I can identify the most common barrier in creating an valid uplift model: marketing programs that are ineffective.