Audit method clarifies when not trading is a mistake
When Is Inaction a Mistake? Continuation-Aware Auditing of PPO Trading Policies
Computational Engineering, Finance, and Science
Summary
Sometimes a trading strategy learned by a computer decides not to trade, but another ideal choice might have suggested trading. The authors created a way to check these situations without training new strategies. Their audit looks at whether the decision to stay put matches the current information and what would happen if the decision changed. They tested this on simulated data and real Bitcoin trading history, showing that adjusting certain decisions can make trading more profitable by reducing costs.
What this means in practice
- •For quantitative trading teams: Use the auditing method to identify when a trading algorithm’s decision to do nothing may miss profitable trades and adjust strategies accordingly.
- •For financial risk managers: Apply the audit to evaluate and reduce unnecessary trading activity that increases turnover costs in algorithmic portfolios.
Authors
Xingfei Zeng, Xin Zhong, Nanting Li, Ziyang Zhong, Lei Xiao, Guanghui Lu
Abstract
An optimal reference may recommend trading when a learned policy chooses inaction, but the recommendation depends on information and future decisions. We introduce a four-stage audit for frozen proximal policy optimization policies without retraining. It examines deployment occupancy, matches current information, tests isolated deviations under incumbent continuation, and evaluates repeated deployment of observation-based alternatives. In controlled linear-Gaussian simulations, information matching explains part of the disagreement, while continuation changes its interpretation. At unit observation noise, incumbent continuation reverses 99.3% of projected-hard missed-advantage mass; repeated projected-rule deployment improves all 50 policies. These comparisons distinguish isolated action changes from policy replacement. Historical Bitcoin/Tether (BTCUSDT) replay applies this deployment perspective to a hand-specified intervention selected using 2024 data and frozen for 2025. Daily net reward improves by 135.03 basis points, with gains in 46 of 50 policies, primarily through lower turnover costs. The audit clarifies what oracle-flagged inaction implies for deployed decision making.