Equities

Dependency Network-Based Portfolio Design with Forecasting and VaR Constraints ArXiv ID: 2507.20039 “View on arXiv” Authors: Zihan Lin, Haojie Liu, Randall R. Rojas Abstract This study proposes a novel portfolio optimization framework that integrates statistical social network analysis with time series forecasting and risk management. Using daily stock data from the S&P 500 (2020-2024), we construct dependency networks via Vector Autoregression (VAR) and Forecast Error Variance Decomposition (FEVD), transforming influence relationships into a cost-based network. Specifically, FEVD breaks down the VAR’s forecast error variance to quantify how much each stock’s shocks contribute to another’s uncertainty information we invert to form influence-based edge weights in our network. By applying the Minimum Spanning Tree (MST) algorithm, we extract the core inter-stock structure and identify central stocks through degree centrality. A dynamic portfolio is constructed using the top-ranked stocks, with capital allocated based on Value at Risk (VaR). To refine stock selection, we incorporate forecasts from ARIMA and Neural Network Autoregressive (NNAR) models. Trading simulations over a one-year period demonstrate that the MST-based strategies outperform a buy-and-hold benchmark, with the tuned NNAR-enhanced strategy achieving a 63.74% return versus 18.00% for the benchmark. Our results highlight the potential of combining network structures, predictive modeling, and risk metrics to improve adaptive financial decision-making. ...

Optimal mean-variance portfolio selection under regime-switching-induced stock price shocks ArXiv ID: 2507.19824 “View on arXiv” Authors: Xiaomin Shi, Zuo Quan Xu Abstract In this paper, we investigate mean-variance (MV) portfolio selection problems with jumps in a regime-switching financial model. The novelty of our approach lies in allowing not only the market parameters – such as the interest rate, appreciation rate, volatility, and jump intensity – to depend on the market regime, but also in permitting stock prices to experience jumps when the market regime switches, in addition to the usual micro-level jumps. This modeling choice is motivated by empirical observations that stock prices often exhibit sharp declines when the market shifts from a bullish'' to a bearish’’ regime, and vice versa. By employing the completion-of-squares technique, we derive the optimal portfolio strategy and the efficient frontier, both of which are characterized by three systems of multi-dimensional ordinary differential equations (ODEs). Among these, two systems are linear, while the first one is an $\ell$-dimensional, fully coupled, and highly nonlinear Riccati equation. In the absence of regime-switching-induced stock price shocks, these systems reduce to simple linear ODEs. Thus, the introduction of regime-switching-induced stock price shocks adds significant complexity and challenges to our model. Additionally, we explore the MV problem under a no-shorting constraint. In this case, the corresponding Riccati equation becomes a $2\ell$-dimensional, fully coupled, nonlinear ODE, for which we establish solvability. The solution is then used to explicitly express the optimal portfolio and the efficient frontier. ...

FinDPO: Financial Sentiment Analysis for Algorithmic Trading through Preference Optimization of LLMs ArXiv ID: 2507.18417 “View on arXiv” Authors: Giorgos Iacovides, Wuyang Zhou, Danilo Mandic Abstract Opinions expressed in online finance-related textual data are having an increasingly profound impact on trading decisions and market movements. This trend highlights the vital role of sentiment analysis as a tool for quantifying the nature and strength of such opinions. With the rapid development of Generative AI (GenAI), supervised fine-tuned (SFT) large language models (LLMs) have become the de facto standard for financial sentiment analysis. However, the SFT paradigm can lead to memorization of the training data and often fails to generalize to unseen samples. This is a critical limitation in financial domains, where models must adapt to previously unobserved events and the nuanced, domain-specific language of finance. To this end, we introduce FinDPO, the first finance-specific LLM framework based on post-training human preference alignment via Direct Preference Optimization (DPO). The proposed FinDPO achieves state-of-the-art performance on standard sentiment classification benchmarks, outperforming existing supervised fine-tuned models by 11% on the average. Uniquely, the FinDPO framework enables the integration of a fine-tuned causal LLM into realistic portfolio strategies through a novel ’logit-to-score’ conversion, which transforms discrete sentiment predictions into continuous, rankable sentiment scores (probabilities). In this way, simulations demonstrate that FinDPO is the first sentiment-based approach to maintain substantial positive returns of 67% annually and strong risk-adjusted performance, as indicated by a Sharpe ratio of 2.0, even under realistic transaction costs of 5 basis points (bps). ...

Eigenvalue Distribution of Empirical Correlation Matrices for Multiscale Complex Systems and Application to Financial Data ArXiv ID: 2507.14325 “View on arXiv” Authors: Luan M. T. de Moraes, Antônio M. S. Macêdo, Giovani L. Vasconcelos, Raydonal Ospina Abstract We introduce a method for describing eigenvalue distributions of correlation matrices from multidimensional time series. Using our newly developed matrix H theory, we improve the description of eigenvalue spectra for empirical correlation matrices in multivariate financial data by considering an informational cascade modeled as a hierarchical structure akin to the Kolmogorov statistical theory of turbulence. Our approach extends the Marchenko-Pastur distribution to account for distinct characteristic scales, capturing a larger fraction of data variance, and challenging the traditional view of noise-dressed financial markets. We conjecture that the effectiveness of our method stems from the increased complexity in financial markets, reflected by new characteristic scales and the growth of computational trading. These findings not only support the turbulent market hypothesis as a source of noise but also provide a practical framework for noise reduction in empirical correlation matrices, enhancing the inference of true market correlations between assets. ...

Towards Realistic and Interpretable Market Simulations: Factorizing Financial Power Law using Optimal Transport ArXiv ID: 2507.09863 “View on arXiv” Authors: Ryuji Hashimoto, Kiyoshi Izumi Abstract We investigate the mechanisms behind the power-law distribution of stock returns using artificial market simulations. While traditional financial theory assumes Gaussian price fluctuations, empirical studies consistently show that the tails of return distributions follow a power law. Previous research has proposed hypotheses for this phenomenon – some attributing it to investor behavior, others to institutional demand imbalances. However, these factors have rarely been modeled together to assess their individual and joint contributions. The complexity of real financial markets complicates the isolation of the contribution of a single component using existing data. To address this, we construct artificial markets and conduct controlled experiments using optimal transport (OT) as a quantitative similarity measure. Our proposed framework incrementally introduces behavioral components into the agent models, allowing us to compare each simulation output with empirical data via OT distances. The results highlight that informational effect of prices plays a dominant role in reproducing power-law behavior and that multiple components interact synergistically to amplify this effect. ...

To Trade or Not to Trade: An Agentic Approach to Estimating Market Risk Improves Trading Decisions ArXiv ID: 2507.08584 “View on arXiv” Authors: Dimitrios Emmanoulopoulos, Ollie Olby, Justin Lyon, Namid R. Stillman Abstract Large language models (LLMs) are increasingly deployed in agentic frameworks, in which prompts trigger complex tool-based analysis in pursuit of a goal. While these frameworks have shown promise across multiple domains including in finance, they typically lack a principled model-building step, relying instead on sentiment- or trend-based analysis. We address this gap by developing an agentic system that uses LLMs to iteratively discover stochastic differential equations for financial time series. These models generate risk metrics which inform daily trading decisions. We evaluate our system in both traditional backtests and using a market simulator, which introduces synthetic but causally plausible price paths and news events. We find that model-informed trading strategies outperform standard LLM-based agents, improving Sharpe ratios across multiple equities. Our results show that combining LLMs with agentic model discovery enhances market risk estimation and enables more profitable trading decisions. ...

A Regression-Based Share Market Prediction Model for Bangladesh ArXiv ID: 2507.18643 “View on arXiv” Authors: Syeda Tasnim Fabiha, Rubaiyat Jahan Mumu, Farzana Aktar, B M Mainul Hossain Abstract Share market is one of the most important sectors of economic development of a country. Everyday almost all companies issue their shares and investors buy and sell shares of these companies. Generally investors want to buy shares of the companies whose market liquidity is comparatively greater. Market liquidity depends on the average price of a share. In this paper, a thorough linear regression analysis has been performed on the stock market data of Dhaka Stock Exchange. Later, the linear model has been compared with random forest based on different metrics showing better results for random forest model. However, the amount of individual significance of different factors on the variability of stock price has been identified and explained. This paper also shows that the time series data is not capable of generating a predictive linear model for analysis. ...

From Rattle to Roar: Optimizer Showdown for MambaStock on S&P 500 ArXiv ID: 2508.04707 “View on arXiv” Authors: Alena Chan, Maria Garmonina Abstract We evaluate the performance of several optimizers on the task of forecasting S&P 500 Index returns with the MambaStock model. Among the most widely used algorithms, gradient-smoothing and adaptive-rate optimizers (for example, Adam and RMSProp) yield the lowest test errors. In contrast, the Lion optimizer offers notably faster training. To combine these advantages, we introduce a novel family of optimizers, Roaree, that dampens the oscillatory loss behavior often seen with Lion while preserving its training speed. ...

Large-scale portfolio optimization with variational neural annealing ArXiv ID: 2507.07159 “View on arXiv” Authors: Nishan Ranabhat, Behnam Javanparast, David Goerz, Estelle Inack Abstract Portfolio optimization is a routine asset management operation conducted in financial institutions around the world. However, under real-world constraints such as turnover limits and transaction costs, its formulation becomes a mixed-integer nonlinear program that current mixed-integer optimizers often struggle to solve. We propose mapping this problem onto a classical Ising-like Hamiltonian and solving it with Variational Neural Annealing (VNA), via its classical formulation implemented using autoregressive neural networks. We demonstrate that VNA can identify near-optimal solutions for portfolios comprising more than 2,000 assets and yields performance comparable to that of state-of-the-art optimizers, such as Mosek, while exhibiting faster convergence on hard instances. Finally, we present a dynamical finite-size scaling analysis applied to the S&P 500, Russell 1000, and Russell 3000 indices, revealing universal behavior and polynomial annealing time scaling of the VNA algorithm on portfolio optimization problems. ...

Beating the Best Constant Rebalancing Portfolio in Long-Term Investment: A Generalization of the Kelly Criterion and Universal Learning Algorithm for Markets with Serial Dependence ArXiv ID: 2507.05994 “View on arXiv” Authors: Duy Khanh Lam Abstract In the online portfolio optimization framework, existing learning algorithms generate strategies that yield significantly poorer cumulative wealth compared to the best constant rebalancing portfolio in hindsight, despite being consistent in asymptotic growth rate. While this unappealing performance can be improved by incorporating more side information, it raises difficulties in feature selection and high-dimensional settings. Instead, the inherent serial dependence of assets’ returns, such as day-of-the-week and other calendar effects, can be leveraged. Although latent serial dependence patterns are commonly detected using large training datasets, this paper proposes an algorithm that learns such dependence using only gradually revealed data, without any assumption on their distribution, to form a strategy that eventually exceeds the cumulative wealth of the best constant rebalancing portfolio. Moreover, the classical Kelly criterion, which requires independent assets’ returns, is generalized to accommodate serial dependence in a market modeled as an independent and identically distributed process of random matrices. In such a stochastic market, where existing learning algorithms designed for stationary processes fail to apply, the proposed learning algorithm still generates a strategy that asymptotically grows to the highest rate among all strategies, matching that of the optimal strategy constructed under the generalized Kelly criterion. The experimental results with real market data demonstrate the theoretical guarantees of the algorithm and its performance as expected, as long as serial dependence is significant, regardless of the validity of the generalized Kelly criterion in the experimental market. This further affirms the broad applicability of the algorithm in general contexts. ...