Paper: arXiv 2407.15038
Authors: Qiqin Zhou
Abstract
In the contemporary financial landscape, accurately predicting the probability of filling a Request-For-Quote (RFQ) is crucial for improving market efficiency for less liquid asset classes. This paper explores the application of explainable AI (XAI) models to forecast the likelihood of RFQ fulfillment. By leveraging advanced algorithms including Logistic Regression, Random Forest, XGBoost and Bayesian Neural Tree, we are able to improve the accuracy of RFQ fill rate predictions and generate the most efficient quote price for market makers. XAI serves as a robust and transparent tool for market participants to navigate the complexities of RFQs with greater precision.
Complexity vs Empirical Score
- Math Complexity: 7.0/10
- Empirical Rigor: 4.0/10
- Quadrant: Lab Rats — high math complexity, limited empirical testing
Why this score: The paper employs advanced mathematical and statistical concepts (Bayesian Neural Trees, probabilistic modeling, data generation via functions) but relies entirely on a simulated dataset for its analysis, lacking real-world data or backtesting results.
Research Flowchart
flowchart TD
A["Research Goal: Predict RFQ Fill Probability<br>and Optimize Quote Prices"] --> B
subgraph B ["Data & Inputs"]
B1["Historical RFQ Data"]
B2["Market Conditions<br>Liquidity & Volatility"]
end
B --> C
subgraph C ["Key Methodology: Machine Learning Models"]
C1["Logistic Regression"]
C2["Random Forest"]
C3["XGBoost"]
C4["Bayesian Neural Tree"]
end
C --> D["Computational Process:<br>Train Models & Evaluate Performance"]
D --> E
subgraph E ["Key Findings & Outcomes"]
E1["Improved Prediction Accuracy<br>for RFQ Fulfillment"]
E2["Generated Efficient<br>Quote Prices for Market Makers"]
E3["XAI Provides Transparency &<br>Explanations for Market Participants"]
end
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 new hybrid model called Bayesian Neural Tree (BNT) that combines decision tree explainability with neural network predictive power, and a market‑maker utility function to optimize quote prices.
Source sentence
To balance the trade-off between model performance and model explainability, we propose a new model framework: Bayesian Neural Tree (BNT).
Assumes 6
- Side is a binary variable following a Bernoulli distribution with probability 0.5. data
Source sentence
Side is binary variable and we assume it follows a a Bernoulli distribution with probability p = 0.5.
- There are exactly 4 participants in each RFQ, with CounterParty drawn uniformly from [0,3]. data
Source sentence
We assume there are in all 4 participants in RFQ so CounterParty is generated uniformly from [0, 3].
- Competition (number of competitors) is uniformly distributed between 1 and 4. data
Source sentence
Competition is generated uniformly from [1, 4] since there are at most 4 participants in the RFQ process.
- Status (RFQ filled or missed) follows a Bernoulli distribution independent of Side. data
Source sentence
Status is the target of our prediction and is also a binary variable. We assume it follows a Bernoulli distribution that is independent of Side.
Show 2 more
- Bid‑ask spread evolves according to a Geometric Brownian Motion. model
Source sentence
The spread at each time step t then can be updated using a Geometric Brownian Motion model: St+1 = St exp( µ∆t + σSϵt √∆t ).
- Mid‑price updates use stochastic processes with normal shocks for bid and ask. model
Source sentence
Bt+1 = Mt −St+1 2 + ϵB At+1 = Mt + St+1 2 + ϵA where ϵB ∼N(0, σ2 B) and ϵA ∼N(0, σ2 A) are random shocks drawn from normal distributions.
Data
- synthetic RFQ dataset synthetic unknown
Source sentence
In Section III, we first proposed a simulation algorithm to produce hypothetical RFQ data that are otherwise not available to the public because of the regulatory constraints that limit the sharing and distribution of real RFQ data.
Costs
Not applicable
Finds 5
- The Bayesian Neural Network model achieves about 90% accuracy on out‑of‑sample data. performance
Source sentence
The Bayesian Neural Network model accuracy on out of sample dataset is around 90%.
- Ensembling multiple models (Lasso Logistic, Random Forest, XGBoost, Bayesian Neural Network) improves out‑of‑sample accuracy and mitigates over‑fitting. performance
Source sentence
Ensembling successfully mitigates the problem overfitting and improve accuracy on out-of-sample data.
- The most important features for predicting RFQ fill are response, MOM5, MOM20 and counterparty. predictive-accuracy
Source sentence
As we can see in figure 5, the most importance features are response, MOM5, MOM20 and counterparty.
- When simulating quote prices, the model fills 4 out of 5 out‑of‑sample RFQs and secures positive utility for all. performance
Source sentence
Among all 5 RFQs out of sample, we are able to fill 4 RFQ and secure positive utility values on all 5 of them.
- Bayesian Neural Tree balances good predictive performance with strong explainability due to its hierarchical tree structure. theoretical
Source sentence
We found that Bayesian Neural Tree has balanced off a good performance and a strong explainability with its hierarchical tree structure.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 34 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.