CyberSec Research

We study the optimal Market Making problem in a Limit Order Book (LOB) market simulated using a high-fidelity, mutually exciting Hawkes process. Departing from traditional Brownian-driven mid-price models, our setup captures key microstructural properties such as queue dynamics, inter-arrival clustering, and endogenous price impact. Recognizing the realistic constraint that market makers cannot update strategies at every LOB event, we formulate the control problem within an impulse control framework, where interventions occur discretely via limit, cancel, or market orders. This leads to a high-dimensional, non-local Hamilton-Jacobi-Bellman Quasi-Variational Inequality (HJB-QVI), whose solution is analytically intractable and computationally expensive due to the curse of dimensionality. To address this, we propose a novel Reinforcement Learning (RL) approximation inspired by auxiliary control formulations. Using a two-network PPO-based architecture with self-imitation learning, we demonstrate strong empirical performance with limited training, achieving Sharpe ratios above 30 in a realistic simulated LOB. In addition to that, we solve the HJB-QVI using a deep learning method inspired by Sirignano and Spiliopoulos 2018 and compare the performance with the RL agent. Our findings highlight the promise of combining impulse control theory with modern deep RL to tackle optimal execution problems in jump-driven microstructural markets.

We address finance-native collateral optimization under ISDA Credit Support Annexes (CSAs), where integer lots, Schedule A haircuts, RA/MTA gating, and issuer/currency/class caps create rugged, legally bounded search spaces. We introduce a certifiable hybrid pipeline purpose-built for this domain: (i) an evidence-gated LLM that extracts CSA terms to a normalized JSON (abstain-by-default, span-cited); (ii) a quantum-inspired explorer that interleaves simulated annealing with micro higher order QAOA (HO-QAOA) on binding sub-QUBOs (subset size n <= 16, order k <= 4) to coordinate multi-asset moves across caps and RA-induced discreteness; (iii) a weighted risk-aware objective (Movement, CVaR, funding-priced overshoot) with an explicit coverage window U <= Reff+B; and (iv) CP-SAT as single arbiter to certify feasibility and gaps, including a U-cap pre-check that reports the minimal feasible buffer B*. Encoding caps/rounding as higher-order terms lets HO-QAOA target the domain couplings that defeat local swaps. On government bond datasets and multi-CSA inputs, the hybrid improves a strong classical baseline (BL-3) by 9.1%, 9.6%, and 10.7% across representative harnesses, delivering better cost-movement-tail frontiers under governance settings. We release governance grade artifacts-span citations, valuation matrix audit, weight provenance, QUBO manifests, and CP-SAT traces-to make results auditable and reproducible.

This work analyzes the computational burden of pricing binary options in rare-event settings and introduces an adaptation of the adaptive multilevel splitting (AMS) method for financial derivatives. Standard Monte Carlo is inefficient for deep out of the money binaries due to discontinuous payoffs and low exercise probabilities, requiring very large samples for accurate estimates. An AMS scheme is developed for binary options under Black-Scholes and Heston dynamics, reformulating the rare-event problem as a sequence of conditional events. Numerical experiments compare the method to Monte Carlo and to other techniques such as antithetic variables and multilevel Monte Carlo (MLMC) across four contracts: European digital calls and puts, and Asian digital calls and puts. Results show up to a 200-fold computational gain for deep out-of-the-money cases while preserving unbiasedness. No evidence is found of prior applications of AMS to financial derivatives. The approach improves pricing efficiency for rare-event contracts such as parametric insurance and catastrophe linked securities. An open-source Rcpp implementation is provided, supporting multiple discretizations and importance functions.

The recent application of deep learning models to financial trading has heightened the need for high fidelity financial time series data. This synthetic data can be used to supplement historical data to train large trading models. The state-of-the-art models for the generative application often rely on huge amounts of historical data and large, complicated models. These models range from autoregressive and diffusion-based models through to architecturally simpler models such as the temporal-attention bilinear layer. Agent-based approaches to modelling limit order book dynamics can also recreate trading activity through mechanistic models of trader behaviours. In this work, we demonstrate how a popular agent-based framework for simulating intraday trading activity, the Chiarella model, can be combined with one of the most performant deep learning models for forecasting multi-variate time series, the TABL model. This forecasting model is coupled to a simulation of a matching engine with a novel method for simulating deleted order flow. Our simulator gives us the ability to test the generative abilities of the forecasting model using stylised facts. Our results show that this methodology generates realistic price dynamics however, when analysing deeper, parts of the markets microstructure are not accurately recreated, highlighting the necessity for including more sophisticated agent behaviors into the modeling framework to help account for tail events.

We present a systematic trading framework that forecasts short-horizon market risk, identifies its underlying drivers, and generates alpha using a hybrid machine learning ensemble built to trade on the resulting signal. The framework integrates neural networks with tree-based voting models to predict five-day drawdowns in the S&P 500 ETF, leveraging a cross-asset feature set spanning equities, fixed income, foreign exchange, commodities, and volatility markets. Interpretable feature attribution methods reveal the key macroeconomic and microstructural factors that differentiate high-risk (crash) from benign (non-crash) weekly regimes. Empirical results show a Sharpe ratio of 2.51 and an annualized CAPM alpha of +0.28, with a market beta of 0.51, indicating that the model delivers substantial systematic alpha with limited directional exposure during the 2005--2025 backtest period. Overall, the findings underscore the effectiveness of hybrid ensemble architectures in capturing nonlinear risk dynamics and identifying interpretable, potentially causal drivers, providing a robust blueprint for machine learning-driven alpha generation in systematic trading.

Execution algorithms are vital to modern trading, they enable market participants to execute large orders while minimising market impact and transaction costs. As these algorithms grow more sophisticated, optimising them becomes increasingly challenging. In this work, we present a reinforcement learning (RL) framework for discovering optimal execution strategies, evaluated within a reactive agent-based market simulator. This simulator creates reactive order flow and allows us to decompose slippage into its constituent components: market impact and execution risk. We assess the RL agent's performance using the efficient frontier based on work by Almgren and Chriss, measuring its ability to balance risk and cost. Results show that the RL-derived strategies consistently outperform baselines and operate near the efficient frontier, demonstrating a strong ability to optimise for risk and impact. These findings highlight the potential of reinforcement learning as a powerful tool in the trader's toolkit.

We introduce M2VN: Multi-Modal Volatility Network, a novel deep learning-based framework for financial volatility forecasting that unifies time series features with unstructured news data. M2VN leverages the representational power of deep neural networks to address two key challenges in this domain: (i) aligning and fusing heterogeneous data modalities, numerical financial data and textual information, and (ii) mitigating look-ahead bias that can undermine the validity of financial models. To achieve this, M2VN combines open-source market features with news embeddings generated by Time Machine GPT, a recently introduced point-in-time LLM, ensuring temporal integrity. An auxiliary alignment loss is introduced to enhance the integration of structured and unstructured data within the deep learning architecture. Extensive experiments demonstrate that M2VN consistently outperforms existing baselines, underscoring its practical value for risk management and financial decision-making in dynamic markets.

Portfolio managers rely on correlation-based analysis and heuristic methods that fail to capture true causal relationships driving performance. We present a hybrid framework that integrates statistical causal discovery algorithms with domain knowledge from two complementary sources: a financial knowledge graph extracted from SEC 10-K filings and large language model reasoning. Our approach systematically enhances three representative causal discovery paradigms, constraint-based (PC), score-based (GES), and continuous optimization (NOTEARS), by encoding knowledge graph constraints algorithmically and leveraging LLM conceptual reasoning for hypothesis generation. Evaluated on a synthetic financial dataset of 500 firms across 18 variables, our KG+LLM-enhanced methods demonstrate consistent improvements across all three algorithms: PC (F1: 0.622 vs. 0.459 baseline, +36%), GES (F1: 0.735 vs. 0.367, +100%), and NOTEARS (F1: 0.759 vs. 0.163, +366%). The framework enables reliable scenario analysis with mean absolute error of 0.003610 for counterfactual predictions and perfect directional accuracy for intervention effects. It also addresses critical limitations of existing methods by grounding statistical discoveries in financial domain expertise while maintaining empirical validation, providing portfolio managers with the causal foundation necessary for proactive risk management and strategic decision-making in dynamic market environments.

The ongoing progress in quantum technologies has fueled a sustained exploration of their potential applications across various domains. One particularly promising field is quantitative finance, where a central challenge is the pricing of financial derivatives-traditionally addressed through Monte Carlo integration techniques. In this work, we introduce two hybrid classical-quantum methods to address the option pricing problem. These approaches rely on reconstructing Fourier series representations of statistical distributions from the outputs of Quantum Machine Learning (QML) models based on Parametrized Quantum Circuits (PQCs). We analyze the impact of data size and PQC dimensionality on performance. Quantum Accelerated Monte Carlo (QAMC) is employed as a benchmark to quantitatively assess the proposed models in terms of computational cost and accuracy in the extraction of Fourier coefficients. Through the numerical experiments, we show that the proposed methods achieve remarkable accuracy, becoming a competitive quantum alternative for derivatives valuation.

News spreads rapidly across languages and regions, but translations may lose subtle nuances. We propose a method to align sentences in multilingual news articles using optimal transport, identifying semantically similar content across languages. We apply this method to align more than 140,000 pairs of Bloomberg English and Japanese news articles covering around 3500 stocks in Tokyo exchange over 2012-2024. Aligned sentences are sparser, more interpretable, and exhibit higher semantic similarity. Return scores constructed from aligned sentences show stronger correlations with realized stock returns, and long-short trading strategies based on these alignments achieve 10\% higher Sharpe ratios than analyzing the full text sample.

The financial market is known to be highly sensitive to news. Therefore, effectively incorporating news data into quantitative trading remains an important challenge. Existing approaches typically rely on manually designed rules and/or handcrafted features. In this work, we directly use the news sentiment scores derived from large language models, together with raw price and volume data, as observable inputs for reinforcement learning. These inputs are processed by sequence models such as recurrent neural networks or Transformers to make end-to-end trading decisions. We conduct experiments using the cryptocurrency market as an example and evaluate two representative reinforcement learning algorithms, namely Double Deep Q-Network (DDQN) and Group Relative Policy Optimization (GRPO). The results demonstrate that our news-aware approach, which does not depend on handcrafted features or manually designed rules, can achieve performance superior to market benchmarks. We further highlight the critical role of time-series information in this process.

Covariance matrices estimated from short, noisy, and non-Gaussian financial time series-particularly cryptocurrencies-are notoriously unstable. Empirical evidence indicates that these covariance structures often exhibit power-law scaling, reflecting complex and hierarchical interactions among assets. Building on this insight, we propose a power-law covariance model to characterize the collective dynamics of cryptocurrencies and develop a hybrid estimator that integrates Random Matrix Theory (RMT) with Residual Neural Networks (ResNets). The RMT component regularizes the eigenvalue spectrum under high-dimensional noise, while the ResNet learns data-driven corrections to recover latent structural dependencies. Monte Carlo simulations show that ResNet-based estimators consistently minimize both Frobenius and minimum-variance (MV) losses across diverse covariance models. Empirical experiments on 89 cryptocurrencies (2020-2025), using a training period ending at the local BTC maximum in November 2021 and testing through the subsequent bear market, demonstrate that a two-step estimator combining hierarchical filtering with ResNet corrections yields the most profitable and balanced portfolios, remaining robust under market regime shifts. These findings highlight the potential of combining RMT, deep learning, and power-law modeling to capture the intrinsic complexity of financial systems and enhance portfolio optimization under realistic conditions.

We present a fast and robust calibration method for stochastic volatility models that admit Fourier-analytic transform-based pricing via characteristic functions. The design is structure-preserving: we keep the original pricing transform and (i) split the pricing formula into data-independent inte- grals and a market-dependent remainder; (ii) precompute those data-independent integrals with GPU acceleration; and (iii) approximate only the remaining, market-dependent pricing map with a small neural network. We instantiate the workflow on a rough volatility model with tempered-stable jumps tailored to power-type volatility derivatives and calibrate it to VIX options with a global-to-local search. We verify that a pure-jump rough volatility model adequately captures the VIX dynamics, consistent with prior empirical findings, and demonstrate that our calibration method achieves high accuracy and speed.

Estimating risk measures such as large loss probabilities and Value-at-Risk is fundamental in financial risk management and often relies on computationally intensive nested Monte Carlo methods. While Multi-Level Monte Carlo (MLMC) techniques and their weighted variants are typically more efficient, their effectiveness tends to deteriorate when dealing with irregular functions, notably indicator functions, which are intrinsic to these risk measures. We address this issue by introducing a novel MLMC parametrization that significantly improves performance in practical, non-asymptotic settings while maintaining theoretical asymptotic guarantees. We also prove that antithetic sampling of MLMC levels enhances efficiency regardless of the regularity of the underlying function. Numerical experiments motivated by the calculation of economic capital in a life insurance context confirm the practical value of our approach for estimating loss probabilities and quantiles, bridging theoretical advances and practical requirements in financial risk estimation.

This paper introduces a semi-analytical method for pricing American options on assets (stocks, ETFs) that pay discrete and/or continuous dividends. The problem is notoriously complex because discrete dividends create abrupt price drops and affect the optimal exercise timing, making traditional continuous-dividend models unsuitable. Our approach utilizes the Generalized Integral Transform (GIT) method introduced by the author and his co-authors in a number of papers, which transforms the pricing problem from a complex partial differential equation with a free boundary into an integral Volterra equation of the second or first kind. In this paper we illustrate this approach by considering a popular GBM model that accounts for discrete cash and proportional dividends using Dirac delta functions. By reframing the problem as an integral equation, we can sequentially solve for the option price and the early exercise boundary, effectively handling the discontinuities caused by the dividends. Our methodology provides a powerful alternative to standard numerical techniques like binomial trees or finite difference methods, which can struggle with the jump conditions of discrete dividends by losing accuracy or performance. Several examples demonstrate that the GIT method is highly accurate and computationally efficient, bypassing the need for extensive computational grids or complex backward induction steps.

This study presents a three-step machine learning framework to predict bubbles in the S&P 500 stock market by combining financial news sentiment with macroeconomic indicators. Building on traditional econometric approaches, the proposed approach predicts bubble formation by integrating textual and quantitative data sources. In the first step, bubble periods in the S&P 500 index are identified using a right-tailed unit root test, a widely recognized real-time bubble detection method. The second step extracts sentiment features from large-scale financial news articles using natural language processing (NLP) techniques, which capture investors' expectations and behavioral patterns. In the final step, ensemble learning methods are applied to predict bubble occurrences based on high sentiment-based and macroeconomic predictors. Model performance is evaluated through k-fold cross-validation and compared against benchmark machine learning algorithms. Empirical results indicate that the proposed three-step ensemble approach significantly improves predictive accuracy and robustness, providing valuable early warning insights for investors, regulators, and policymakers in mitigating systemic financial risks.

In quantitative investing, return prediction supports various tasks, including stock selection, portfolio optimization, and risk management. Quantitative factors, such as valuation, quality, and growth, capture various characteristics of stocks. Unstructured financial data, like news and transcripts, has attracted growing attention, driven by recent advances in large language models (LLMs). This paper examines effective methods for leveraging multimodal factors and newsflow in return prediction and stock selection. First, we introduce a fusion learning framework to learn a unified representation from factors and newsflow representations generated by an LLM. Within this framework, we compare three representative methods: representation combination, representation summation, and attentive representations. Next, building on empirical observations from fusion learning, we explore the mixture model that adaptively combines predictions made by single modalities and their fusion. To mitigate the training instability observed in the mixture model, we introduce a decoupled training approach with theoretical insights. Finally, our experiments on real investment universes yield several insights into effective multimodal modeling of factors and news for stock return prediction.

Prediction markets, such as Polymarket, aggregate dispersed information into tradable probabilities, but they still lack a unifying stochastic kernel comparable to the one options gained from Black-Scholes. As these markets scale with institutional participation, exchange integrations, and higher volumes around elections and macro prints, market makers face belief volatility, jump, and cross-event risks without standardized tools for quoting or hedging. We propose such a foundation: a logit jump-diffusion with risk-neutral drift that treats the traded probability p_t as a Q-martingale and exposes belief volatility, jump intensity, and dependence as quotable risk factors. On top, we build a calibration pipeline that filters microstructure noise, separates diffusion from jumps using expectation-maximization, enforces the risk-neutral drift, and yields a stable belief-volatility surface. We then define a coherent derivative layer (variance, correlation, corridor, and first-passage instruments) analogous to volatility and correlation products in option markets. In controlled experiments on synthetic risk-neutral paths and real event data, the model reduces short-horizon belief-variance forecast error relative to diffusion-only and probability-space baselines, supporting both causal calibration and economic interpretability. Conceptually, the logit jump-diffusion kernel supplies an implied-volatility analogue for prediction markets: a tractable, tradable language for quoting, hedging, and transferring belief risk across venues such as Polymarket.