Paper: arXiv 2503.05254
Authors: Adele Ravagnani, Fabrizio Lillo
Abstract
Devising models of the limit order book that realistically reproduce the market response to exogenous trades is extremely challenging and fundamental in order to test trading strategies. We propose a novel explainable model for small tick assets, the Non-Markovian Zero Intelligence, which is a variant of the well-known Zero Intelligence model. The main modification is that the probability of limit orders’ signs (buy/sell) is not constant but is a function of the exponentially weighted mid-price return, representing the past price dynamics, and can be interpreted as the reaction of traders with reservation prices to the price trend. With numerical simulations and analytical arguments, we show that the model predicts a concave price path during a metaorder execution and to a price reversion after the execution ends, as empirically observed. We analyze in-depth the mechanism at the root of the arising concavity, the components which constitute the price impact in our model, and the dependence of the results on the two main parameters, namely the time scale and the strength of the reaction of traders to the price trend.
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 stochastic processes and analytical arguments to model the limit order book, but lacks direct backtesting, statistical metrics, or implementation details, relying instead on conceptual simulations and theoretical derivations.
Research Flowchart
flowchart TD A["Research Goal<br>Develop an explainable LOB model<br>for metaorder price impact"] --> B["Methodology: Non-Markovian ZI Model"] B --> C["Key Innovation<br>Limited order sign = f<br>EWMA mid-price return"] B --> D["Simulation<br>Numerical LOB simulations"] B --> E["Validation<br>Analytical approximation"] C --> F D --> F["Analysis<br>Metaorder execution paths<br>Impact decomposition"] E --> F F --> G["Key Findings"] G --> H["1. Concave price impact during metaorder"] G --> I["2. Price reversion post-execution"] G --> J["3. Mechanism: Trend reaction creates liquidity imbalance"] G --> K["4. Dependence on time scale & reaction strength"]
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 introduces the Non‑Markovian Zero Intelligence (NMZI) model, a variant of the Zero Intelligence model where the probability of a limit order being a buy or sell depends on an exponentially weighted mid‑price return.
Source sentence
We propose a novel explainable model for small tick assets, the Non-Markovian Zero Intelligence, which is a variant of the well-known Zero Intelligence model.
Assumes 6
- The probability that a limit order is a sell/buy is a function of the exponentially weighted mid‑price return, representing past price dynamics. model
Source sentence
The main modification is that the probability of limit orders' signs (buy/sell) is not constant but is a function of the exponentially weighted mid-price return, representing the past price dynamics, and can be interpreted as the reaction of traders with reservation prices to the price trend.
- The model focuses on small‑tick assets. market
Source sentence
We propose a novel explainable model for small tick assets, the Non-Markovian Zero Intelligence, which is a variant of the well-known Zero Intelligence model.
- Two main parameters govern the model: a time‑scale (memory) and the strength of traders' reaction to the price trend. model
Source sentence
In our model, the reaction of these traders occurs with a time scale that corresponds to the memory we employ in the evaluation of the price dynamics, and its strength is tuned by a parameter that enters the definition of the probability that a limit order is a sell/buy. Throughout the paper, we study how our results and market impact dynamics depend on these two parameters.
- Limit orders, market orders and cancellations follow independent Poisson processes in the baseline ZI model. model
Source sentence
In the original model, limit orders, market orders and cancellations in the LOB are modeled as three inde-pendent Poisson processes.
Show 2 more
- Metaorders are executed at a constant speed (constant trading rate). execution
Source sentence
As expected, the larger the total volume, the stronger the increase of the mid-price during the execution of the metaorder.
- The simulated order‑book dynamics are calibrated on real LOBSTER data for Tesla on a single day. data
Source sentence
We use the LOBSTER dataset1 for the small-tick asset Tesla on January 5, 2015, which has a tick-size equal to 0.01$. After the pre-processing2, we end up with 170, 416 events.
Data
- LOBSTER dataset (Tesla, Jan 5 2015) order-book public
Source sentence
We use the LOBSTER dataset1 for the small-tick asset Tesla on January 5, 2015, which has a tick-size equal to 0.01$. After the pre-processing2, we end up with 170, 416 events.
Costs
Not applicable
Finds 5
- The NMZI model predicts a concave mid‑price path during metaorder execution and a reversion after execution, matching empirical observations. theoretical
Source sentence
With numerical simulations and analytical arguments, we show that the model predicts a concave price path during a metaorder execution and to a price reversion after the execution ends, as empirically observed. During the execution of a metaorder, the concavity of the market impact emerges.
- The impact coefficient estimated from simulations with metaorder execution is (5.063 ± 0.011) ticks, consistent with the ZI‑only estimate of ≈4.9 ticks. statistical figure from elsewhere in the paper
Source sentence
By fitting the difference between the mid-price at the end and at the beginning of the execution, i.e. mT −m0, as a function of Q and referring to Eq. (2), we obtain a coefficient equal to (5.063±0.011) ticks. This is consistent with ˆk estimated without any execution and the coefficients estimated with a metaorder execution and different trading intervals.
- Larger total metaorder volume leads to a stronger increase of the mid‑price during execution. performance
Source sentence
As expected, the larger the total volume, the stronger the increase of the mid-price during the execution of the metaorder.
- Increasing the memory parameter (1/β₂) lengthens the concave regime and enhances the reversion mechanism. theoretical
Source sentence
For fixed values of ∆and α, as 1/β2 increases so do ¯R∗and τ ∗. This means that considering a longer memory in the evaluation of the price trend leads to a longer concave regime and so, to a better reproduction of the behavior of the market impact we observe in real markets.
- In the stationary regime, both the immediate impact and the reversion component stabilize to constant values, yielding a linear impact. theoretical
Source sentence
In the stationary regime, the overall child MOs’ impact stabilizes to a stationary value. In the stationary regime, the impact stabilizes to a constant value8.
Checked by others
Supported by
- Metaorder modelling and identification from public data
Compare the findings
This paper: The NMZI model predicts a concave mid‑price path during metaorder execution and a reversion after execution, matching empirical observations.
That paper: The execution profile of synthetic metaorders is concave, indicating non‑linear impact during execution.
- A Bayesian theory of market impact
Compare the findings
This paper: The impact coefficient estimated from simulations with metaorder execution is (5.063 ± 0.011) ticks, consistent with the ZI‑only estimate of ≈4.9 ticks.
That paper: The impact is independent of the meta‑order execution protocol in the regime t≪ν⁻².
Contradicted by
- Optimal liquidation with temporary and permanent price impact, an application to cryptocurrencies
Compare the findings
This paper: In the stationary regime, both the immediate impact and the reversion component stabilize to constant values, yielding a linear impact.
That paper: Power functional forms fit the calibrated temporary and permanent impact data better than linear forms, with lower residuals and higher R‑squared.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.