Free GARP RAI Exam Questions

In cost complexity pruning, a bank uses a parameter, α, to balance the residual sum of squares (RSS) and the number of terminal nodes. What is the primary role of this parameter?

A financial services firm is using a neural network with multiple hidden layers to predict the likelihood of loan default (binary classification). They find that the model isn’t learning well with the logistic activation function in the hidden layers. Which activation function should they consider switching to improve learning?

A financial institution is implementing an AI model that uses proxies for loan approval decisions. Which of the following is a potential risk associated with using proxies?

A data scientist is tuning the ridge regression model’s hyperparameter, λ, to control the trade-off between model fit and complexity. If λ is set too high, what effect is most likely?

An insurance company uses two different AI models for policy approval, one for Group A and another for Group B. The confusion matrices for each group are as follows:Group A Confusion Matrix:True Positives: 50False Positives: 10False Negatives: 40True Negatives: 90Group B Confusion Matrix:True Positives: 30False Positives: 20False Negatives: 70True Negatives: 80What fairness technique should the company use to balance the performance between the two groups?