Test levels and risk-based testing · Question 19 of 60
Into which three areas can ML-specific risks be divided along the ML workflow?
1 answer is correct. Easy
Show answer
Answer
- B Development, input data and model
Explanation
One way is to divide risks along the ML workflow into three areas: development (algorithm, model development, framework), input data (training and production data) and model (the generated ML model). Another way is to categorize them according to the quality characteristics of ISO/IEC 25059.