CyberSec Research

We develop a rotation-invariant neural network that provides the global minimum-variance portfolio by jointly learning how to lag-transform historical returns and how to regularise both the eigenvalues and the marginal volatilities of large equity covariance matrices. This explicit mathematical mapping offers clear interpretability of each module's role, so the model cannot be regarded as a pure black-box. The architecture mirrors the analytical form of the global minimum-variance solution yet remains agnostic to dimension, so a single model can be calibrated on panels of a few hundred stocks and applied, without retraining, to one thousand US equities-a cross-sectional jump that demonstrates robust out-of-sample generalisation. The loss function is the future realized minimum portfolio variance and is optimized end-to-end on real daily returns. In out-of-sample tests from January 2000 to December 2024 the estimator delivers systematically lower realised volatility, smaller maximum drawdowns, and higher Sharpe ratios than the best analytical competitors, including state-of-the-art non-linear shrinkage. Furthermore, although the model is trained end-to-end to produce an unconstrained (long-short) minimum-variance portfolio, we show that its learned covariance representation can be used in general optimizers under long-only constraints with virtually no loss in its performance advantage over competing estimators. These gains persist when the strategy is executed under a highly realistic implementation framework that models market orders at the auctions, empirical slippage, exchange fees, and financing charges for leverage, and they remain stable during episodes of acute market stress.

This paper presents a machine learning driven framework for sectoral stress testing in the Indian financial market, focusing on financial services, information technology, energy, consumer goods, and pharmaceuticals. Initially, we address the limitations observed in conventional stress testing through dimensionality reduction and latent factor modeling via Principal Component Analysis and Autoencoders. Building on this, we extend the methodology using Variational Autoencoders, which introduces a probabilistic structure to the latent space. This enables Monte Carlo-based scenario generation, allowing for more nuanced, distribution-aware simulation of stressed market conditions. The proposed framework captures complex non-linear dependencies and supports risk estimation through Value-at-Risk and Expected Shortfall. Together, these pipelines demonstrate the potential of Machine Learning approaches to improve the flexibility, robustness, and realism of financial stress testing.

Forecasting central bank policy decisions remains a persistent challenge for investors, financial institutions, and policymakers due to the wide-reaching impact of monetary actions. In particular, anticipating shifts in the U.S. federal funds rate is vital for risk management and trading strategies. Traditional methods relying only on structured macroeconomic indicators often fall short in capturing the forward-looking cues embedded in central bank communications. This study examines whether predictive accuracy can be enhanced by integrating structured data with unstructured textual signals from Federal Reserve communications. We adopt a multi-modal framework, comparing traditional machine learning models, transformer-based language models, and deep learning architectures in both unimodal and hybrid settings. Our results show that hybrid models consistently outperform unimodal baselines. The best performance is achieved by combining TF-IDF features of FOMC texts with economic indicators in an XGBoost classifier, reaching a test AUC of 0.83. FinBERT-based sentiment features marginally improve ranking but perform worse in classification, especially under class imbalance. SHAP analysis reveals that sparse, interpretable features align more closely with policy-relevant signals. These findings underscore the importance of integrating textual and structured signals transparently. For monetary policy forecasting, simpler hybrid models can offer both accuracy and interpretability, delivering actionable insights for researchers and decision-makers.

Financial institutions increasingly adopt customer-centric strategies to enhance profitability and build long-term relationships. While Customer Lifetime Value (CLV) is a core metric, its calculations often rely solely on single-entity data, missing insights from customer activities across multiple firms. This study introduces the Potential Customer Lifetime Value (PCLV) framework, leveraging Open Banking (OB) data to estimate customer value comprehensively. We predict retention probability and estimate Potential Contribution Margins (PCM) from competitor data, enabling PCLV calculation. Results show that OB data can be used to estimate PCLV per competitor, indicating a potential upside of 21.06% over the Actual CLV. PCLV offers a strategic tool for managers to strengthen competitiveness by leveraging OB data and boost profitability by driving marketing efforts at the individual customer level to increase the Actual CLV.

Extending Buehler et al.'s 2019 Deep Hedging paradigm, we innovatively employ deep neural networks to parameterize convex-risk minimization (CVaR/ES) for the portfolio tail-risk hedging problem. Through comprehensive numerical experiments on crisis-era bootstrap market simulators -- customizable with transaction costs, risk budgets, liquidity constraints, and market impact -- our end-to-end framework not only achieves significant one-day 99% CVaR reduction but also yields practical insights into friction-aware strategy adaptation, demonstrating robustness and operational viability in realistic markets.

This study investigates the impact of data source diversity on the performance of cryptocurrency forecasting models by integrating various data categories, including technical indicators, on-chain metrics, sentiment and interest metrics, traditional market indices, and macroeconomic indicators. We introduce the Crypto100 index, representing the top 100 cryptocurrencies by market capitalization, and propose a novel feature reduction algorithm to identify the most impactful and resilient features from diverse data sources. Our comprehensive experiments demonstrate that data source diversity significantly enhances the predictive performance of forecasting models across different time horizons. Key findings include the paramount importance of on-chain metrics for both short-term and long-term predictions, the growing relevance of traditional market indices and macroeconomic indicators for longer-term forecasts, and substantial improvements in model accuracy when diverse data sources are utilized. These insights help demystify the short-term and long-term driving factors of the cryptocurrency market and lay the groundwork for developing more accurate and resilient forecasting models.

We consider the problem of optimal investment with random endowment in a Black--Scholes market for an agent with constant relative risk aversion. Using duality arguments, we derive an explicit expression for the optimal trading strategy, which can be decomposed into the optimal strategy in the absence of a random endowment and an additive shift term whose magnitude depends linearly on the endowment-to-wealth ratio and exponentially on time to maturity.

We introduce a novel neural-network-based approach to learning the generating function $G(\cdot)$ of a functionally generated portfolio (FGP) from synthetic or real market data. In the neural network setting, the generating function is represented as $G_{\theta}(\cdot)$, where $\theta$ is an iterable neural network parameter vector, and $G_{\theta}(\cdot)$ is trained to maximise investment return relative to the market portfolio. We compare the performance of the Neural FGP approach against classical FGP benchmarks. FGPs provide a robust alternative to classical portfolio optimisation by bypassing the need to estimate drifts or covariances. The neural FGP framework extends this by introducing flexibility in the design of the generating function, enabling it to learn from market dynamics while preserving self-financing and pathwise decomposition properties.

We consider a Bayesian diffusion control problem of expected terminal utility maximization. The controller imposes a prior distribution on the unknown drift of an underlying diffusion. The Bayesian optimal control, tracking the posterior distribution of the unknown drift, can be characterized explicitly. However, in practice, the prior will generally be incorrectly specified, and the degree of model misspecification can have a significant impact on policy performance. To mitigate this and reduce overpessimism, we introduce a distributionally robust Bayesian control (DRBC) formulation in which the controller plays a game against an adversary who selects a prior in divergence neighborhood of a baseline prior. The adversarial approach has been studied in economics and efficient algorithms have been proposed in static optimization settings. We develop a strong duality result for our DRBC formulation. Combining these results together with tools from stochastic analysis, we are able to derive a loss that can be efficiently trained (as we demonstrate in our numerical experiments) using a suitable neural network architecture. As a result, we obtain an effective algorithm for computing the DRBC optimal strategy. The methodology for computing the DRBC optimal strategy is greatly simplified, as we show, in the important case in which the adversary chooses a prior from a Kullback-Leibler distributional uncertainty set.

We present a reinforcement learning (RL)-driven framework for optimizing block-preconditioner sizes in iterative solvers used in portfolio optimization and option pricing. The covariance matrix in portfolio optimization or the discretization of differential operators in option pricing models lead to large linear systems of the form $\mathbf{A}\textbf{x}=\textbf{b}$. Direct inversion of high-dimensional portfolio or fine-grid option pricing incurs a significant computational cost. Therefore, iterative methods are usually used for portfolios in real-world situations. Ill-conditioned systems, however, suffer from slow convergence. Traditional preconditioning techniques often require problem-specific parameter tuning. To overcome this limitation, we rely on RL to dynamically adjust the block-preconditioner sizes and accelerate iterative solver convergence. Evaluations on a suite of real-world portfolio optimization matrices demonstrate that our RL framework can be used to adjust preconditioning and significantly accelerate convergence and reduce computational cost. The proposed accelerated solver supports faster decision-making in dynamic portfolio allocation and real-time option pricing.

By capturing outliers, volatility clustering, and tail dependence in the asset return distribution, we build a sophisticated model to predict the downside risk of the global financial market. We further develop a dynamic regime switching model that can forecast real-time risk regime of the market. Our GARCH-DCC-Copula risk model can significantly improve both risk- and alpha-based global tactical asset allocation strategies. Our risk regime has strong predictive power of quantitative equity factor performance, which can help equity investors to build better factor models and asset allocation managers to construct more efficient risk premia portfolios.

We present a continuous-time portfolio selection framework that reflects goal-based investment principles and mental accounting behavior. In this framework, an investor with multiple investment goals constructs separate portfolios, each corresponding to a specific goal, with penalties imposed on fund transfers between these goals, referred to as mental costs. By applying the stochastic Perron's method, we demonstrate that the value function is the unique constrained viscosity solution of a Hamilton-Jacobi-Bellman equation system. Numerical analysis reveals several key features: the free boundaries exhibit complex shapes with bulges and notches; the optimal strategy for one portfolio depends on the wealth level of another; investors must diversify both among stocks and across portfolios; and they may postpone reallocating surplus from an important goal to a less important one until the former's deadline approaches.

We study optimal consumption and retirement using a Cobb-Douglas utility and a simple model in which an interesting bifurcation arises. With high wealth, individuals plan to retire. With low wealth they plan to never retire. At a critical level of initial wealth they may choose to defer this decision, leading to a continuum of wealth trajectories with identical utilities.

Project portfolio management is an essential process for organizations aiming to optimize the value of their R&D investments. In this article, we introduce a new tool designed to support the prioritization of projects within project portfolio management. We label this tool the PIT-plot, an acronym for Project Impact Tornado plot, with reference to the similarity to the Tornado plot often used for sensitivity analyses. Many traditional practices in portfolio management focus on the properties of the projects available to the portfolio. We are with the PIT-plot changing the perspective and focus not on the properties of the projects themselves, but on the impact that the projects may have on the portfolio. This enables the strategic portfolio management to identify and focus on the projects of largest impact to the portfolio, either for the purpose of risk mitigation or for the purpose of value-adding efforts.

The emerging cryptocurrency market presents unique challenges for investment due to its unregulated nature and inherent volatility. However, collective price movements can be explored to maximise profits with minimal risk using investment portfolios. In this paper, we develop a technical framework that utilises historical data on daily closing prices and integrates network analysis, price forecasting, and portfolio theory to identify cryptocurrencies for building profitable portfolios under uncertainty. Our method utilises the Louvain network community algorithm and consensus clustering to detect robust and temporally stable clusters of highly correlated cryptocurrencies, from which the chosen cryptocurrencies are selected. A price prediction step using the ARIMA model guarantees that the portfolio performs well for up to 14 days in the investment horizon. Empirical analysis over a 5-year period shows that despite the high volatility in the crypto market, hidden price patterns can be effectively utilised to generate consistently profitable, time-agnostic cryptocurrency portfolios.

We investigate multi-period mean-risk portfolio optimization for long-horizon Defined Contribution plans, focusing on buffered Probability of Exceedance (bPoE), a more intuitive, dollar-based alternative to Conditional Value-at-Risk (CVaR). We formulate both pre-commitment and time-consistent Mean-bPoE and Mean-CVaR portfolio optimization problems under realistic investment constraints (e.g., no leverage, no short selling) and jump-diffusion dynamics. These formulations are naturally framed as bilevel optimization problems, with an outer search over the shortfall threshold and an inner optimization over rebalancing decisions. We establish an equivalence between the pre-commitment formulations through a one-to-one correspondence of their scalarization optimal sets, while showing that no such equivalence holds in the time-consistent setting. We develop provably convergent numerical schemes for the value functions associated with both pre-commitment and time-consistent formulations of these mean-risk control problems. Using nearly a century of market data, we find that time-consistent Mean-bPoE strategies closely resemble their pre-commitment counterparts. In particular, they maintain alignment with investors' preferences for a minimum acceptable terminal wealth level-unlike time-consistent Mean-CVaR, which often leads to counterintuitive control behavior. We further show that bPoE, as a strictly tail-oriented measure, prioritizes guarding against catastrophic shortfalls while allowing meaningful upside exposure, making it especially appealing for long-horizon wealth security. These findings highlight bPoE's practical advantages for Defined Contribution investment planning.

We propose a novel distributionally robust $Q$-learning algorithm for the non-tabular case accounting for continuous state spaces where the state transition of the underlying Markov decision process is subject to model uncertainty. The uncertainty is taken into account by considering the worst-case transition from a ball around a reference probability measure. To determine the optimal policy under the worst-case state transition, we solve the associated non-linear Bellman equation by dualising and regularising the Bellman operator with the Sinkhorn distance, which is then parameterized with deep neural networks. This approach allows us to modify the Deep Q-Network algorithm to optimise for the worst case state transition. We illustrate the tractability and effectiveness of our approach through several applications, including a portfolio optimisation task based on S\&{P}~500 data.

In this paper, we introduce a model-based deep-learning approach to solve finite-horizon continuous-time stochastic control problems with jumps. We iteratively train two neural networks: one to represent the optimal policy and the other to approximate the value function. Leveraging a continuous-time version of the dynamic programming principle, we derive two different training objectives based on the Hamilton-Jacobi-Bellman equation, ensuring that the networks capture the underlying stochastic dynamics. Empirical evaluations on different problems illustrate the accuracy and scalability of our approach, demonstrating its effectiveness in solving complex, high-dimensional stochastic control tasks.