Paper: arXiv 2307.04863
Authors: Timothée Fabre, Vincent Ragel
Abstract
Order placement tactics play a crucial role in high-frequency trading algorithms and their design is based on understanding the dynamics of the order book. Using high quality high-frequency data and a set of microstructural features, we exhibit strong state dependence properties of the fill probability function. We train a neural network to infer the fill probability function for a fixed horizon. Since we aim at providing a high-frequency execution framework, we use a simple architecture. A weighting method is applied to the loss function such that the model learns from censored data. By comparing numerical results obtained on both digital asset centralized exchanges (CEXs) and stock markets, we are able to analyze dissimilarities between feature importances of the fill probability of small tick crypto pairs and Euronext equities. The practical use of this model is illustrated with a fixed time horizon execution problem in which both the decision to post a limit order or to immediately execute and the optimal distance of placement are characterized. We discuss the importance of accurately estimating the clean-up cost that occurs in the case of a non-execution and we show it can be well approximated by a smooth function of market features. We finally assess the performance of our model with a backtesting approach that avoids the insertion of hypothetical orders and makes possible to test the order placement algorithm with orders that realistically impact the price formation process.
Complexity vs Empirical Score
- Math Complexity: 6.5/10
- Empirical Rigor: 8.0/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper employs advanced statistical methods (survival analysis, neural networks with censored data weighting) and introduces new microstructure features, indicating moderate-to-high mathematical complexity. It demonstrates strong empirical rigor through backtesting on real market data (CEX and equities), analysis of feature importances, and a realistic order placement router that accounts for market impact.
Research Flowchart
flowchart TD
A["Research Goal:<br>Model Fill Probability for Limit Order Placement"] --> B{"Data Sources"};
B --> C["High-Frequency Data:<br>Crypto CEX & Euronext Equities"];
C --> D["Computational Process:<br>NN Training with Censored Loss"];
D --> E["Outcome 1:<br>Learned Fill Probability Model"];
E --> F["Outcome 2:<br>Backtested Execution Strategy"];
D --> F;
F --> G["Outcome 3:<br>Feature Importance Differences<br>Crypto vs. Equities"];
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 simple neural network model to infer the fill probability function and a new backtest methodology for high‑frequency order placement that accounts for market impact.
Source sentence
We set an optimal execution problem where the agent needs to choose between posting a limit order and sending a marketable order. We propose a new backtest methodology that, by essence, takes into account the market impact of limit order insertion for better performance assessment.
Assumes 6
- Latency is negligible compared to the execution horizon. execution
Source sentence
We suppose in the rest of the discussion that ℓ is negligible compared to the time horizon T, for example ℓ/T < 10⁻³.
- Order lifetimes are independent of censoring variables. statistical
Source sentence
we assume that the order can be subject to independent right censoring modeled by a random variable Cn and the censoring variable is assumed independent from Ln.
- Fill probability is a smooth non‑linear function of market features. model
Source sentence
Section 4 discusses two survival analysis methods to compute fill probability on level 3 data and provides empirical evidence of smooth non‑linearity of the fill probability as a function of market features.
- Weighting of censored observations improves fill probability estimation. model
Source sentence
The significant presence of right censoring in the data set leads us to consider a loss weighting methodology
Show 2 more
- Tick size remains very small on Coinbase during the sample period. market
Source sentence
We chose to use Coinbase data for two reasons. First, the tick size remains very small during the covered period of time which is not the case for Bitstamp…
- Feature importance can be assessed with Shapley values on out‑of‑sample observations. model
Source sentence
We analyze the importance of features with Shapley values computed over out‑of‑sample observations using the SHAP library (Lundberg and Lee, 2017).
Data
- Coinbase order‑book data order-book proprietary
Source sentence
We have 1 month of data at our disposal, from 2022‑11‑05 to 2022‑12‑05 on BTC‑USD and ETH‑USD.
- BEDOFIH equity data order-book proprietary
Source sentence
August 31st, 2017— and validate it on 1.5 months —from September 1st, 2017 to October 15th, 2017.
Costs
Modeled
Coinbase fee policy ranging from 0.006 to 0.0005 (taker) and 0.004 to 0 (maker) depending on monthly turnover, used in the execution algorithm.
Source sentence
Table 3: Trading fees — Coinbase fee policy of spot trading on April 2023. Level
Finds 5
- Using handcrafted features and a state‑dependent market risk V improves the F‑score from 0.34 to 0.51 for BTC‑USD. performance
Source sentence
It demonstrates that a simple and interpretable neural network architecture
- The optimal placement distance scales linearly with the expected adverse price move V and inversely with the fill‑probability decay rate. theoretical
Source sentence
Equation 21 indicates that in this simple framework, the optimal distance should scale linearly with respect to the expected adverse price move V, and inversely with respect to the decay rate of the fill probability.
- Higher taker‑maker fee gaps push the algorithm to post more aggressive (inside‑spread) orders. performance
Source sentence
The algorithm tends to post aggressive orders when the taker‑maker fee gap ε⁻‑ε⁺ is large, pushing the optimal distance towards −ψ as this gap increases.
- Applying IPCW weighting deforms the fill probability similarly to the Kaplan‑Meier estimator, giving extra weight to highly censored configurations. statistical
Source sentence
The IPCW procedure deforms the fill probability in a similar way that the Kaplan‑Meier function does by giving extra weights to orders that were not executed under the horizon or posted in highly censored configurations.
- Feature importance differs between small‑tick crypto pairs and Euronext equities, especially regarding placement inside the spread versus deep in the book. predictive-accuracy
Source sentence
our work is the first to analyze the feature importance of the fill probability depending on the placement of the order, i.e. if the order is placed inside the spread, at the current best queue, or deep in the book.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 22 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.