Want to develop meaningful, innovative, and data-driven software products? Don‹t start by evaluating machine learning algorithms. The first step is to find and verify an AI/ML use case so that AI/ML helps you solve a relevant problem. However, the overall process from use case discovery to deployment and operation of ML models is not a trivial undertaking.
Day 1: In this interactive training, we convey the possibilities of ML/AI and show which problems are predestined for it. Then we briefly introduce you to the basic ideas, concepts, and patterns of Domain-driven Design.
In the first practical part we get to know Event Storming and the ML Design Canvas. Event Storming is a method from Collaborative Modeling and Knowledge Crunching. It helps domain experts, technical experts, developers and all other team members to develop a common understanding of the business domain. This then allows us to identify use cases for innovative AI/ML technologies.
Day 2: We collaboratively formulate ML problems based on the use cases we have found. We do this on the ML Design Canvas. Then we structure the ML project on the Canvas and specify all components for the training and prediction phases. Afterwards, we talk about the Data Landscape Canvas to clarify the data availability.