Paper: arXiv 2306.17178
Authors: Cong Zheng, Jiafa He, Can Yang
Abstract
This work is about optimal order execution, where a large order is split into several small orders to maximize the implementation shortfall. Based on the diversity of cryptocurrency exchanges, we attempt to extract cross-exchange signals by aligning data from multiple exchanges for the first time. Unlike most previous studies that focused on using single-exchange information, we discuss the impact of cross-exchange signals on the agent’s decision-making in the optimal execution problem. Experimental results show that cross-exchange signals can provide additional information for the optimal execution of cryptocurrency to facilitate the optimal execution process.
Complexity vs Empirical Score
- Math Complexity: 7.5/10
- Empirical Rigor: 4.0/10
- Quadrant: Lab Rats — high math complexity, limited empirical testing
Why this score: The paper employs advanced reinforcement learning methods and stochastic control theory, indicating high mathematical complexity. However, it relies on backtesting on cryptocurrency data without detailed implementation code or robust statistical validation, placing it in the Lab Rats quadrant.
Research Flowchart
flowchart TD A["Research Goal:<br>Optimal Execution with<br>Cross-Exchange Signals"] --> B["Methodology:<br>Align High-Freq Data<br>from Multiple Exchanges"] B --> C["Inputs:<br>Multi-Exchange<br>Order Book Data"] C --> D["Computation:<br>Reinforcement Learning Agent<br>for Order Splitting"] D --> E["Process:<br>Execute Orders to Maximize<br>Implementation Shortfall"] E --> F["Outcome:<br>Cross-Exchange Signals<br>Enhance Execution Performance"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes a reinforcement‑learning based optimal execution framework that incorporates cross‑exchange signals to predict cryptocurrency price changes.
Source sentence
we attempted for the first time to use cross-exchange signals to predict asset price changes.
Assumes 3
- The agent’s own orders have no impact on market price in the baseline model. execution
Source sentence
So far, we have always assumed that our own orders have no impact on the market price.
- A flat execution fee of 3 basis points is incurred per trade. market
Source sentence
It can be seen that considering the execution fee of 3 bps, the IS of the TWAP execution algorithm is about -3.1 bps
- Cross‑exchange signals may be delayed due to network latency between exchange servers. data
Source sentence
due to the different locations of servers of different exchanges, there may be network delay issues in the process of obtaining cross-exchange signals
Data
- Binance perpetual data crypto-onchain public
Source sentence
Our work focuses on analyzing perpetual data from several top-ranked cryptocurrency exchanges, including Binance, OKEx, and Bybit.
- OKEx perpetual data crypto-onchain public
Source sentence
Our work focuses on analyzing perpetual data from several top-ranked cryptocurrency exchanges, including Binance, OKEx, and Bybit.
- Bybit perpetual data crypto-onchain public
Source sentence
Our work focuses on analyzing perpetual data from several top-ranked cryptocurrency exchanges, including Binance, OKEx, and Bybit.
Costs
Unclear - sources disagree
Source sentence (the authors' words)
It can be seen that considering the execution fee of 3 bps, the IS of the TWAP execution algorithm is about -3.1 bps
Finds 3
- Cross‑exchange order‑flow signals consistently outperform single‑exchange signals in predictive power across all time horizons. predictive-accuracy
Source sentence
In Figure A and Figure B, we observe that the cross-exchange signal consistently outperforms the single-exchange signal in terms of predictive power, regardless of the prediction time scale.
- The RL agent using cross‑exchange signals (PPOcross) achieves lower implementation shortfall than TWAP and single‑exchange RL (PPOsingle) on both Bybit and OKEx. performance
Source sentence
Compared to the TWAP execution algorithm, the agent further gains 0.68 bps of improvement. This result further proves that cross-exchange signals can provide additional improvement compared to using only single-exchange signals.
- Using cross‑exchange signals increases variance of execution outcomes, likely due to network‑delay induced signal inaccuracies. statistical
Source sentence
We can understand this as follows: due to the different locations of servers of different exchanges, there may be network delay issues
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 13 related papers). Coverage is partial, so this is neither replication nor refutation.
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.