Book Image

Artificial Intelligence with Power BI

By : Mary-Jo Diepeveen
Book Image

Artificial Intelligence with Power BI

By: Mary-Jo Diepeveen

Overview of this book

The artificial intelligence (AI) capabilities in Power BI enable organizations to quickly and easily gain more intelligent insights from unstructured and structured data. This book will teach you how to make use of the many AI features available today in Power BI to quickly and easily enrich your data and gain better insights into patterns that can be found in your data. You’ll begin by understanding the benefits of AI and how it can be used in Power BI. Next, you’ll focus on exploring and preparing your data for building AI projects and then progress to using prominent AI features already available in Power BI, such as forecasting, anomaly detection, and Q&A. Later chapters will show you how to apply text analytics and computer vision within Power BI reports. This will help you create your own Q&A functionality in Power BI, which allows you to ask FAQs from another knowledge base and then integrate it with PowerApps. Toward the concluding chapters, you’ll be able to create and deploy AutoML models trained in Azure ML and consume them in Power Query Editor. After your models have been trained, you’ll work through principles such as privacy, fairness, and transparency to use AI responsibly. By the end of this book, you’ll have learned when and how to enrich your data with AI using the out-of-the-box AI capabilities in Power BI.
Table of Contents (18 chapters)
Part 1: AI Fundamentals
Part 2: Out-of-the-Box AI Features
Part 3: Create Your Own Models

Creating fair models

Fairness is a complicated concept that is often used to reflect the equal treatment of different groups. We want a trained model to perform equally well across different groups. To ensure fairness, we need to assess whether a model is fair. If the model shows that it treats groups unfairly, we can retrain that model and force it to perform equally across groups.

Identifying unfairness in models

Imagine that we train a model to predict whether high school students will be successful when they continue their studies at a university. The model's predictions may influence a student's decision to apply to a university. As this is an important life decision, we want to make sure that the model predicts it correctly for both female and male students. We may also want to assess whether the model predicts it correctly for different minority groups.

Depending on the use case and the features you include when training a model, you may wish to identify so...