Explainable AI: Building trust in business decision-making

Business application of split and compare quantiles

Salient Features in Action

Post-Deployment Analysis

Business Risk Analysis

Financial Decision-Making with SCQ

Effective Decision-Making

Granular Risk Assessment

0.001-480 48.0-60.0 60.0-67.0 67.0-73.0 73.0-78.0 78.0-82.0 82.0-86.0 86.0-89.0 89.0-92.5 92.5-86.0

20000

8000

506.27 279.96 307.58 268.13

1580.21

17500

7000

1651.50

Similarly, in the SCQ plot, we can replace probabilities with corresponding monetary values. Doing so allows us to analyze the total monetary value that we will get at a chosen probability threshold. For instance, at a 67% decision threshold, the total monetary transaction value can be estimated at $17288.51K. However, there is a possibility of losing $3508.1K due to model error. In such a scenario, stakeholders would like to select a decision threshold or bins of decision thresholds that minimize the dollar value loss resulting from model errors. By doing so, businesses can optimize their decision-making processes and minimize their overall monetary losses.

611.96

1611.72

15020

6000

667.03

2157.11

12000

5000

845.18

2185.72

10200

4000

856.11

2171.89

7500

3000

1411.31

2122.26

5000

2000

2121.81

1871.97

2114.03

2000

1000

1734.79

0

0

Conclusion

Traditional practices in explainable artificial intelligence (XAI) have typically been limited to basic model explainability and data visualization. However, it's vital to take things one step further, dissect the model and understand the potential risks associated with errors in the model. Surprisingly, a lower error rate doesn't necessarily equal lower financial loss and vice versa. As such, it's crucial not just to analyze the model’s errors statistically but also from a monetary standpoint before making a decision on the threshold. It is important to note that stakeholders may prefer choosing bins of different thresholds instead of a single flat decision boundary. This approach can provide a better trade-off between the monetary value of the model's errors and its accuracy.

Authors

Supriya Panigrahi Consultant, Fractal Dimension

Sray Agarwal

Sakshi Gulyani Consultant, Fractal Dimension

Principal Consultant, Fractal Dimension

© 2023 Fractal Analytics Inc. All rights reserved

06

Made with FlippingBook - PDF hosting