Главная
Study mode:
on
1
Quantifying bias in machine decisions
2
Summary
3
Pretrial detention A detailed case study
4
Key assumptions
5
From features to decisions
6
Risk distributions
7
From risk to decisions Threshold rules
8
A double standard
9
Fairness of a single threshold
10
Popular mathematical definitions of fairness
11
Discrimination with calibrated scores
12
Classification parity
13
False positive rate parity
14
Error rate disparities in Broward County
15
Calculating false positive rates
16
Infra-marginality
17
The problem with false positive rates
18
Are the data biased?
19
Biased labels
20
Biased predictors
Description:
Explore the complexities of fairness in machine learning decisions through this 46-minute lecture by Sharad Goel from Stanford University. Delve into recent developments in fairness research, examining quantitative methods for measuring bias in algorithmic decision-making. Investigate a detailed case study on pretrial detention, analyzing key assumptions, risk distributions, and threshold rules. Examine popular mathematical definitions of fairness, including classification parity and false positive rate parity. Critically evaluate the challenges of applying these fairness metrics, such as infra-marginality and potential biases in data labels and predictors. Gain insights into the nuanced considerations necessary for developing and assessing fair machine learning systems in real-world applications.

The Measure and Mismeasure of Fairness

Simons Institute
Add to list
0:00 / 0:00