An AI Streaming Machine Learning Tutorial with Spotfire® 1.1

Overview

AI is a large field. This Accelerator serves as an example of how to make more efficient decisions, in real-time or in batch, by leveraging machine learning. This template intends to aid a user to apply supervised and unsupervised machine learning to historic data and deploy it into action in batch or in real-time. The types of actions can be diverse: providing a dashboard for employee decision support (Augmented Intelligence) or taking an action, like changing the settings of a machine or sending an offer to a customer (Artificial Intelligence). This template can be used any time you want to identify rows in your data for special treatment. It has been successfully applied to the following industries and use cases, because, across use cases, the data changes as does the meaning of respective columns and rows, but the mathematics and the technical setup are the same. Some examples include:

• fighting financial crime, such as AML, trade surveillance, collection scoring, and fraud
• industrial application, such as spotting defective or maverick lots, predicting machine failure or machine suboptimal behavior
• customer relationships, such as improved customer support and offer management

This template was created as a tutorial to serve as a source of inspiration for experienced data scientists, demonstrating how to put machine learning into production, but also aimed at business users who want to learn how to set up a machine learning strategy in their businesses. This template is an integral part of Spotfire's Risk Management Accelerator but can be used independently.