What is a template?

This article explains the concept of templates in the AI & Analytics Engine

The AI & Analytics Engine provides templates to automatically build complete machine learning solutions and pipelines from start to finish, resulting in consumable outputs that are ready for integration into production systems.

Each template is tailored to a specific use case such as “customer churn prediction”, “customer lifetime value prediction”, “next-best offer optimization”, “demand forecasting”, which are targeted at specific industries such as banking, telecommunications, digital marketing, etc.

Inputs required by a template

Templates require users to provide only non-technical inputs – such as the business problem definition (e.g. how do you define churn?), domain-knowledge inputs (where/in which time frames can potential signals about customer’s future intent be found), and connections to their data sources (e.g. files, database/data warehouse/data lake connections, etc.).

The Engine then automatically builds a full end-to-end solution that is ready for consumption.

An illustration of how the AI & Analytics Engine builds an end-to-end solution with the customer churn prediction template

Example:

The Customer Churn Prediction template requires users to provide the following inputs:

The template provides a way for users without technical data science or ML background to tap into the power of machine learning. It only requires users to convey their business problem and provide domain-knowledge inputs.

1. Connection to a transactional data source

   1. semantic mapping of columns

2. Optional connection to a customer information data source

   1. semantic mapping of columns

3. Provide a definition of churn:

   1. how much inactivity and over what time frame indicates churn?

   2. how many days in advance should the prediction be made?

4. Provide domain-knowledge inputs:

   1. what time windows usually contain early signals of churn?

   2. among the general characteristics of customers, which ones might help in predicting churn?

Benefits of using the AI & Analytics Engine’s templates:

• It provides a complete repeatable, maintainable, auditable, and fully production-ready machine learning workflows

• It speeds up the process of bringing ML to production and getting to predictive insights and value from data rather quickly

• It increases productivity for both non-technical and technical users:

  • It automates mundane tasks in the ML workflow

  • It allows technical users to focus on high value tasks such as:

    • Business-problem formulation

    • Applying domain expertise