Principle:HKUDS AI Trader Portfolio Metrics Calculation

Knowledge Sources	Sharpe Ratio Risk-Adjusted Returns
Domains	Quantitative_Finance, Performance_Analysis
Last Updated	2026-02-09 14:00 GMT

Overview

A quantitative finance technique that computes risk-adjusted performance metrics from portfolio time series data.

Description

Portfolio Metrics Calculation evaluates trading strategy performance using standard financial metrics. Given a time series of portfolio total values, it computes:

Cumulative Return (CR): Total percentage gain over the period
Sharpe Ratio: Risk-adjusted return using standard deviation of returns
Sortino Ratio (SR): Like Sharpe but penalizes only downside volatility
Maximum Drawdown (MDD): Largest peak-to-trough decline
Calmar Ratio: Annualized return divided by maximum drawdown
Volatility (Vol): Annualized standard deviation of returns
Win Rate: Percentage of profitable trading periods

These metrics are the standard toolkit for evaluating any quantitative trading strategy.

Usage

Use this principle after a backtesting simulation completes to evaluate agent performance. The metrics enable comparison between different LLM agents and against market benchmarks.

Theoretical Basis

Key formulas:

$C R = \frac{V_{f i n a l} - V_{i n i t i a l}}{V_{i n i t i a l}}$

$S h a r p e = \frac{\bar{r} - r_{f}}{σ_{r}} \times \sqrt{N}$

$S o r t i n o = \frac{\bar{r} - r_{f}}{σ_{d o w n s i d e}} \times \sqrt{N}$

$M D D = \max_{t} \frac{P e a k_{t} - T r o u g h_{t}}{P e a k_{t}}$

Where:

$\bar{r}$ = mean return
$r_{f}$ = risk-free rate
$σ_{r}$ = standard deviation of returns
$σ_{d o w n s i d e}$ = standard deviation of negative returns only
$N$ = annualization factor (252 for daily, 252*6.5 for hourly, 365 for crypto)

Related Pages

Uses Heuristic

Heuristic:HKUDS_AI_Trader_Sortino_Ratio_Capping

Implemented By

Implementation:HKUDS_AI_Trader_Calculate_Metrics

Page Connections

Double-click a node to navigate. Hold to expand connections.

Principle

Implementation

Heuristic

Environment