|
on Market Microstructure |
| By: | Ayoub Jhabli; Tarek Alskaif; Kwabena E. Bennin; Bedir Tekinerdogan; Joost M. E. Pennings |
| Abstract: | As renewable energy integration accelerates, intraday continuous (IDC) electricity markets have become essential for short-term balancing. However, the simultaneous trading of overlapping contracts with varying granularities creates complex, hidden liquidity dependencies that are critical to market stability but remain poorly understood. This paper proposes a multivariate State-Dependent Hawkes Process (SDHP) to model cross-product liquidity dynamics between Quarter-Hourly and Hourly IDC contracts. To determine how cross-product effects vary under different market conditions, we classify the trading sessions into two distinct regimes: 'Normal' and 'Stressed', based on a composite metric of the bid-ask spread, mid-price volatility and queue imbalance. The model is calibrated on the first month of each quarter of 2024 using level 3 limit order book (LOB) data from the Dutch EPEX SPOT IDC market. We find that order flow is overwhelmingly self-driven, with roughly 95\% of orders arriving in reaction to earlier orders in both regimes. Cross-excitation runs mainly from the Quarter-Hourly to the Hourly contract, but this leadership weakens under stress: the ratio of cumulative cross-excitation falls from 2.8 to 1.5, so the two contracts influence each other almost equally. Stress also makes the Quarter-Hourly to Hourly channel much faster, cutting its mean lag from 6.05 to 0.93 seconds. The strong seasonal variation found in calm periods largely disappears under stress, where all four months converge to the same structure. |
| Date: | 2026–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2610.23619 |
| By: | Junyu Chen; Franklin Liu; Moshu Xu; Lijian Yang |
| Abstract: | Modeling limit order book (LOB) dynamics is central to market forecasting and execution-strategy evaluation. While diffusion models achieve strong empirical performance, existing LOB snapshot models typically lack a learned recurrent encoder and formal statistical guarantees. We introduce LOBGrad, a conditional DDPM framework for probabilistic LOB forecasting that combines an autoregressive RNN encoder with a diffusion-based generator. In particular, we establish an excess-risk oracle inequality for the one-step DDPM noise-prediction objective under exponential mixing and regularity assumptions. We further show that, under contractive dynamics, the dependence on the conditioning-window length can be reduced to a dependence on the latent-state dimension. Experiments on BTC/USDT, GOOGL, and META show that LOBGrad improves on its encoder-free diffusion ablation across all reported queue metrics and obtains competitive results against other baselines. It also reproduces the key stylized facts of LOB microstructure, and yields reasonably calibrated queue-based predictive intervals. A stylized downstream task illustrates the potential value of the generated forecasts. |
| Date: | 2026–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2610.25495 |
| By: | Skander Lejmi |
| Abstract: | A market maker provides liquidity by quoting prices to buy and sell an asset, earning the spread while managing inventory risk. We study market makers trained with multi-agent reinforcement learning on prediction markets, specifically Polymarket, whose thin order books pose distinct challenges. Three challenges underpin this research: adverse selection may cause a policy trained on real data to stop quoting; the consequences of a quote can arrive many steps after the action; and prediction-market L2 data does not identify individual orders needed for simulation. We address these challenges by reconstructing order-level LOBSTER-format data from Polymarket and training agents in JaxMARL-HFT on 417 real markets. We enrich the baseline market maker's observation space with the book and recent flow, redesign its actions and inventory controls, and propose a cooperative multi-agent decomposition into a quoter and a risk manager trained using recurrent Independent Proximal Policy Optimisation (IPPO) with RNN policies. We investigate reward shaping, particularly reward blending and post-fill markout, to mitigate credit-assignment difficulties between the agents. Our redesigned single-agent market maker quotes more frequently and incurs smaller held-out losses than the retrained JaxMARL-HFT baseline, although the contributions of jointly changed observations, actions and risk constraints are not separately identified. Decomposition alone performs poorly; careful reward design substantially improves the desk relative to the unshaped split and yields our best result. Models are evaluated on realised end-of-episode portfolio value on held-out markets. None establishes positive average portfolio value in periodic held-out evaluation, and each configuration was trained with one seed. The environment, data and protocol lay a foundation for makers that quote many linked markets at once. |
| Date: | 2026–10 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2610.26789 |