Explain results Need to speak data using a common language
8
Explainable Al, is it possible?
9
Helps avoid incompleteness issues Explanations fundamentally help identify gaps in problem formalization - incompleteness
10
Visualize how models work
11
How to understand a model
12
What data did the model use? Understand model data source limitations
13
Investigate model training data
14
Understand what matters
15
Explore relationships between variables
16
Examine decision rules Rules Fit Classifiers
17
Discover business rules from text fields
18
Analyze prediction explanations Global
19
Evaluate model performance
20
Understand how well a model fits the data
21
Examine where models make mistakes
22
Detect model changes over time
23
Time series
24
Visualize probability Workflows
25
Resources
Description:
Dive deeper into understanding and explaining machine learning terms and charts to business stakeholders using Jupyter Notebooks, Python, and Power BI in this 58-minute conference talk from PASS Data Community Summit. Explore real-world examples from healthcare, retail, marketing, banking, and other industries while learning about the differences between machine learning and artificial intelligence, automated machine learning processes, and the importance of explainable AI. Discover techniques for visualizing model workings, investigating training data, exploring variable relationships, examining decision rules, analyzing prediction explanations, evaluating model performance, and detecting model changes over time. Gain valuable insights into visualization best practices for explainable AI to effectively communicate complex machine learning concepts to non-technical audiences.