You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: content/english/technical-tools/BDT.md
+11-16Lines changed: 11 additions & 16 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -57,11 +57,6 @@ team:
57
57
name: Mackenzie Jorgensen
58
58
bio: |
59
59
PhD-candidate Computer Science, King’s College London
60
-
web_app:
61
-
title: Bias detection tool
62
-
icon: fas fa-cloud
63
-
id: web-app
64
-
content: ''
65
60
type: bias-detection-tool
66
61
---
67
62
@@ -75,7 +70,7 @@ The tool identifies potentially unfairly treated groups of similar users by an A
75
70
76
71
##### How is my data processed?
77
72
78
-
The tool is privacy preserving. It uses computing power of your own computer to analyze a dataset. In this architectural setup, data is processed entirely on your device and it not uploaded to any third party, such as cloud providers. This local-only feature allows organisations to securely use the tool with proprietary data. The used software is also available as <ahref="https://pypi.org/project/unsupervised-bias-detection/"target="_blank">pip package</a> `unsupervised-bias-detection`. [](https://pypi.org/project/unsupervised-bias-detection/)
73
+
The tool is privacy preserving. It uses computing power of your own computer to analyze a dataset. In this architectural setup, data is processed entirely on your device and it not uploaded to any third party, such as cloud providers. This local-only feature allows organisations to securely use the tool with proprietary data. The used software is also available as <ahref="https://pypi.org/project/unsupervised-bias-detection/"target="_blank">pip package</a> `unsupervised-bias-detection`. [](https://pypi.org/project/unsupervised-bias-detection/)
The bias detection tool currently works for tabular numerical and categorical data. The *Hierarchical Bias-Aware Clustering* (HBAC) algorithm processes input data according to the k-means or k-modes clustering algorithm. The HBAC-algorithm is introduced by Misztal-Radecka and Indurkya in a [scientific article](https://www.sciencedirect.com/science/article/abs/pii/S0306457321000285) as published in *Information Processing and Management* (2021). Our implementation of the HBAC-algorithm can be found on <ahref="https://github.com/NGO-Algorithm-Audit/unsupervised-bias-detection/blob/master/README.md"target="_blank">Github</a>.
107
+
The bias detection tool currently works for tabular numerical and categorical data. The _Hierarchical Bias-Aware Clustering_ (HBAC) algorithm processes input data according to the k-means or k-modes clustering algorithm. The HBAC-algorithm is introduced by Misztal-Radecka and Indurkya in a [scientific article](https://www.sciencedirect.com/science/article/abs/pii/S0306457321000285) as published in *Information Processing and Management* (2021). Our implementation of the HBAC-algorithm can be found on <ahref="https://github.com/NGO-Algorithm-Audit/unsupervised-bias-detection/blob/master/README.md"target="_blank">Github</a>.
***Quantitative-qualitative joint method**: Data-driven bias testing combined with the balanced and context-sensitive judgment of human experts;
121
-
***Unsupervised bias detection**: No user data needed on protected attributes;
122
-
***Bias scan tool**: Scalable method based on statistical learning to detect algorithmic bias;
123
-
***Detects complex bias**: Identifies unfairly treated groups characterized by mixture of features, detects intersectional bias;
124
-
***Model-agnostic**: Works for all AI systems;
125
-
***Open-source and not-for-profit**: Easy to use and available for the entire AI auditing community.
115
+
-**Quantitative-qualitative joint method**: Data-driven bias testing combined with the balanced and context-sensitive judgment of human experts;
116
+
-**Unsupervised bias detection**: No user data needed on protected attributes;
117
+
-**Bias scan tool**: Scalable method based on statistical learning to detect algorithmic bias;
118
+
-**Detects complex bias**: Identifies unfairly treated groups characterized by mixture of features, detects intersectional bias;
119
+
-**Model-agnostic**: Works for all AI systems;
120
+
-**Open-source and not-for-profit**: Easy to use and available for the entire AI auditing community.
126
121
127
122
##### By whom can the bias detection tool be used?
128
123
@@ -138,11 +133,11 @@ No. The bias detection tool serves as a starting point to assess potentially unf
138
133
139
134
##### How is my data processed?
140
135
141
-
The tool is privacy preserving. It uses computing power of your own computer to analyze a dataset. In this architectural setup, data is processed entirely on your device and it not uploaded to any third party, such as cloud providers. This local-only feature allows organisations to securely use the tool with proprietary data. The used software is also available as <ahref="https://pypi.org/project/unsupervised-bias-detection/"target="_blank">pip package</a> `unsupervised-bias-detection`. [](https://pypi.org/project/unsupervised-bias-detection/)
136
+
The tool is privacy preserving. It uses computing power of your own computer to analyze a dataset. In this architectural setup, data is processed entirely on your device and it not uploaded to any third party, such as cloud providers. This local-only feature allows organisations to securely use the tool with proprietary data. The used software is also available as <ahref="https://pypi.org/project/unsupervised-bias-detection/"target="_blank">pip package</a> `unsupervised-bias-detection`. [](https://pypi.org/project/unsupervised-bias-detection/)
142
137
143
138
##### In sum
144
139
145
-
Quantitative methods, such as unsupervised bias detection, are helpful to discover potentially unfair treated groups of similar users in AI systems in a scalable manner. Automated identification of cluster disparities in AI models allows human experts to assess observed disparities in a qualitative manner, subject to political, social and environmental traits. This two-pronged approach bridges the gap between the qualitative requirements of law and ethics, and the quantitative nature of AI (see figure). In making normative advice, on identified ethical issues publicly available, over time a [repository](/algoprudence/) of case reviews emerges. We call case-based normative advice for ethical algorithm *algoprudence*. Data scientists and public authorities can learn from our algoprudence and can criticise it, as ultimately normative decisions regarding fair AI should be made within democratic sight.
140
+
Quantitative methods, such as unsupervised bias detection, are helpful to discover potentially unfair treated groups of similar users in AI systems in a scalable manner. Automated identification of cluster disparities in AI models allows human experts to assess observed disparities in a qualitative manner, subject to political, social and environmental traits. This two-pronged approach bridges the gap between the qualitative requirements of law and ethics, and the quantitative nature of AI (see figure). In making normative advice, on identified ethical issues publicly available, over time a [repository](/algoprudence/) of case reviews emerges. We call case-based normative advice for ethical algorithm _algoprudence_. Data scientists and public authorities can learn from our algoprudence and can criticise it, as ultimately normative decisions regarding fair AI should be made within democratic sight.
146
141
147
142
[Read more](/algoprudence/how-we-work/) about algoprudence and how Algorithm Audit's builds it.
De bias detectie tool werkt momenteel alleen voor numeriek data. Volgens een hierarchisch schema clustert het *Hierarchical Bias-Aware Clustering* (HBAC) algoritme input data met behulp van k-means clustering algoritme. Op termijn kan de tool ook categorische data verwerken volgens k-modes clustering. Het HBAC-algoritme is geïntroduceerd door Misztal-Radecka en Indurkya in een [wetenschappelijk artikel](https://www.sciencedirect.com/science/article/abs/pii/S0306457321000285) in *Information Processing and Management* (2021). Onze implementatie van het HBAC-algoritme is open source en kan worden gevonden in [Github.](https://github.com/NGO-Algorithm-Audit/AI_Audit_Challenge)
96
+
De bias detectie tool werkt momenteel alleen voor numeriek data. Volgens een hierarchisch schema clustert het _Hierarchical Bias-Aware Clustering_ (HBAC) algoritme input data met behulp van k-means clustering algoritme. Op termijn kan de tool ook categorische data verwerken volgens k-modes clustering. Het HBAC-algoritme is geïntroduceerd door Misztal-Radecka en Indurkya in een [wetenschappelijk artikel](https://www.sciencedirect.com/science/article/abs/pii/S0306457321000285) in *Information Processing and Management* (2021). Onze implementatie van het HBAC-algoritme is open source en kan worden gevonden in [Github.](https://github.com/NGO-Algorithm-Audit/AI_Audit_Challenge)
102
97
103
98
[Download](https://github.com/NGO-Algorithm-Audit/Bias_scan/blob/master/classifiers/BERT_disinformation_classifier/test_pred_BERT.csv) een voorbeeld dataset om de bias detectie tool te gebruiken.
104
99
@@ -108,10 +103,10 @@ De bias detectie tool werkt momenteel alleen voor numeriek data. Volgens een hie
108
103
109
104
Welke input data kan de bias detectie tool verwerken? Een csv-bestand van maximaal 5GB met kolommen kenmerken (`features`), de voorspelde waarde (`pred_label`) en de echte waarde (`true_label`). Alleen de volgorde van de kolommen is van belang (eerst `features`, dan `pred_label`, dan `true_label`). Alle kolommen moeten numeriek en ongeschaald (niet gestandaardiseerd of genormaliseerd) zijn. Samengevat:
110
105
111
-
*`features`: ongeschaalde numerieke waarden, bijvoorbeeld `kenmerk_1`, `kenmerk_2`, ..., `kenmerk_n`;
0 commit comments