utility

Utility functions for Bayesian optimization.

Key Concepts:

• Samples:

  A PyTensor tensor variable (pt.TensorVariable) representing samples drawn from the posterior distributions of the model outputs. These samples capture the uncertainty in the model predictions and are essential for computing expected utilities and risk measures in Bayesian optimization.

• Budgets:

  A PyTensor tensor variable representing a set of monetary budgets allocated to different assets, investments, or channels. Each element corresponds to the budget for a specific option in the optimization process.

Functions

adjusted_value_at_risk_score([...])	Calculate adjusted Value at Risk (AVaR) score.
average_response(samples, budgets)	Compute the average response of the posterior predictive distribution.
conditional_value_at_risk([confidence_level])	Calculate the Conditional Value at Risk (CVaR) at a specified confidence level.
diversification_ratio(samples, budgets)	Calculate the Diversification Ratio of a portfolio to evaluate risk distribution.
mean_tightness_score([alpha, confidence_level])	Calculate the mean tightness score.
portfolio_entropy(samples, budgets)	Calculate the entropy of a portfolio's asset weights to assess diversification.
raroc([risk_free_rate])	Calculate the Risk-Adjusted Return on Capital (RAROC).
sharpe_ratio([risk_free_rate])	Calculate the Sharpe Ratio.
tail_distance([confidence_level])	Calculate the absolute distance between the mean and the quantiles.
value_at_risk([confidence_level])	Calculate the Value at Risk (VaR) at a specified confidence level.