Portfolio Construction

Generative AI-enhanced Sector-based Investment Portfolio Construction ArXiv ID: 2512.24526 “View on arXiv” Authors: Alina Voronina, Oleksandr Romanko, Ruiwen Cao, Roy H. Kwon, Rafael Mendoza-Arriaga Abstract This paper investigates how Large Language Models (LLMs) from leading providers (OpenAI, Google, Anthropic, DeepSeek, and xAI) can be applied to quantitative sector-based portfolio construction. We use LLMs to identify investable universes of stocks within S&P 500 sector indices and evaluate how their selections perform when combined with classical portfolio optimization methods. Each model was prompted to select and weight 20 stocks per sector, and the resulting portfolios were compared with their respective sector indices across two distinct out-of-sample periods: a stable market phase (January-March 2025) and a volatile phase (April-June 2025). Our results reveal a strong temporal dependence in LLM portfolio performance. During stable market conditions, LLM-weighted portfolios frequently outperformed sector indices on both cumulative return and risk-adjusted (Sharpe ratio) measures. However, during the volatile period, many LLM portfolios underperformed, suggesting that current models may struggle to adapt to regime shifts or high-volatility environments underrepresented in their training data. Importantly, when LLM-based stock selection is combined with traditional optimization techniques, portfolio outcomes improve in both performance and consistency. This study contributes one of the first multi-model, cross-provider evaluations of generative AI algorithms in investment management. It highlights that while LLMs can effectively complement quantitative finance by enhancing stock selection and interpretability, their reliability remains market-dependent. The findings underscore the potential of hybrid AI-quantitative frameworks, integrating LLM reasoning with established optimization techniques, to produce more robust and adaptive investment strategies. ...

Beyond Binary Screens: A Continuous Shariah Compliance Index for Asset Pricing and Portfolio Design ArXiv ID: 2512.22858 “View on arXiv” Authors: Abdulrahman Qadi, Akash Sharma, Francesca Medda Abstract Binary Shariah screens vary across standards and apply hard thresholds that create discontinuous classifications. We construct a Continuous Shariah Compliance Index (CSCI) in $[“0,1”]$ by mapping standard screening ratios to smooth scores between conservative ``comfort’’ bounds and permissive outer bounds, and aggregating them conservatively with a sectoral activity factor. Using CRSP/Compustat U.S. equities (1999-2024) with lagged accounting inputs and monthly rebalancing, we find that CSCI-based long-only portfolios have historical risk-adjusted performance similar to an emulated binary Islamic benchmark. Tightening the minimum compliance threshold reduces the investable universe and diversification and is associated with lower Sharpe ratios. The framework yields a practical compliance gradient that supports portfolio construction, constraint design, and cross-standard comparisons without reliance on pass/fail screening. ...

Deep Generative Models for Synthetic Financial Data: Applications to Portfolio and Risk Modeling ArXiv ID: 2512.21798 “View on arXiv” Authors: Christophe D. Hounwanou, Yae Ulrich Gaba Abstract Synthetic financial data provides a practical solution to the privacy, accessibility, and reproducibility challenges that often constrain empirical research in quantitative finance. This paper investigates the use of deep generative models, specifically Time-series Generative Adversarial Networks (TimeGAN) and Variational Autoencoders (VAEs) to generate realistic synthetic financial return series for portfolio construction and risk modeling applications. Using historical daily returns from the S and P 500 as a benchmark, we generate synthetic datasets under comparable market conditions and evaluate them using statistical similarity metrics, temporal structure tests, and downstream financial tasks. The study shows that TimeGAN produces synthetic data with distributional shapes, volatility patterns, and autocorrelation behaviour that are close to those observed in real returns. When applied to mean–variance portfolio optimization, the resulting synthetic datasets lead to portfolio weights, Sharpe ratios, and risk levels that remain close to those obtained from real data. The VAE provides more stable training but tends to smooth extreme market movements, which affects risk estimation. Finally, the analysis supports the use of synthetic datasets as substitutes for real financial data in portfolio analysis and risk simulation, particularly when models are able to capture temporal dynamics. Synthetic data therefore provides a privacy-preserving, cost-effective, and reproducible tool for financial experimentation and model development. ...

Basis Immunity: Isotropy as a Regularizer for Uncertainty ArXiv ID: 2511.13334 “View on arXiv” Authors: Florent Segonne Abstract Diversification is a cornerstone of robust portfolio construction, yet its application remains fraught with challenges due to model uncertainty and estimation errors. Practitioners often rely on sophisticated, proprietary heuristics to navigate these issues. Among recent advancements, Agnostic Risk Parity introduces eigenrisk parity (ERP), an innovative approach that leverages isotropy to evenly allocate risk across eigenmodes, enhancing portfolio stability. In this paper, we review and extend the isotropy-enforced philosophy of ERP proposing a versatile framework that integrates mean-variance optimization with an isotropy constraint acting as a geometric regularizer against signal uncertainty. The resulting allocations decompose naturally into canonical portfolios, smoothly interpolating between full isotropy (closed-form isotropic-mean allocation) and pure mean-variance through a tunable isotropy penalty. Beyond methodology, we revisit fundamental concepts and clarify foundational links between isotropy, canonical portfolios, principal portfolios, primal versus dual representations, and intrinsic basis-invariant metrics for returns, risk, and isotropy. Applied to sector trend-following, the isotropy constraint systematically induces negative average-signal exposure – a structural, parameter-robust crash hedge. This work offers both a practical, theoretically grounded tool for resilient allocation under signal uncertainty and a pedagogical synthesis of modern portfolio concepts. ...

Diffolio: A Diffusion Model for Multivariate Probabilistic Financial Time-Series Forecasting and Portfolio Construction ArXiv ID: 2511.07014 “View on arXiv” Authors: So-Yoon Cho, Jin-Young Kim, Kayoung Ban, Hyeng Keun Koo, Hyun-Gyoon Kim Abstract Probabilistic forecasting is crucial in multivariate financial time-series for constructing efficient portfolios that account for complex cross-sectional dependencies. In this paper, we propose Diffolio, a diffusion model designed for multivariate financial time-series forecasting and portfolio construction. Diffolio employs a denoising network with a hierarchical attention architecture, comprising both asset-level and market-level layers. Furthermore, to better reflect cross-sectional correlations, we introduce a correlation-guided regularizer informed by a stable estimate of the target correlation matrix. This structure effectively extracts salient features not only from historical returns but also from asset-specific and systematic covariates, significantly enhancing the performance of forecasts and portfolios. Experimental results on the daily excess returns of 12 industry portfolios show that Diffolio outperforms various probabilistic forecasting baselines in multivariate forecasting accuracy and portfolio performance. Moreover, in portfolio experiments, portfolios constructed from Diffolio’s forecasts show consistently robust performance, thereby outperforming those from benchmarks by achieving higher Sharpe ratios for the mean-variance tangency portfolio and higher certainty equivalents for the growth-optimal portfolio. These results demonstrate the superiority of our proposed Diffolio in terms of not only statistical accuracy but also economic significance. ...

3S-Trader: A Multi-LLM Framework for Adaptive Stock Scoring, Strategy, and Selection in Portfolio Optimization ArXiv ID: 2510.17393 “View on arXiv” Authors: Kefan Chen, Hussain Ahmad, Diksha Goel, Claudia Szabo Abstract Large Language Models (LLMs) have recently gained popularity in stock trading for their ability to process multimodal financial data. However, most existing methods focus on single-stock trading and lack the capacity to reason over multiple candidates for portfolio construction. Moreover, they typically lack the flexibility to revise their strategies in response to market shifts, limiting their adaptability in real-world trading. To address these challenges, we propose 3S-Trader, a training-free framework that incorporates scoring, strategy, and selection modules for stock portfolio construction. The scoring module summarizes each stock’s recent signals into a concise report covering multiple scoring dimensions, enabling efficient comparison across candidates. The strategy module analyzes historical strategies and overall market conditions to iteratively generate an optimized selection strategy. Based on this strategy, the selection module identifies and assembles a portfolio by choosing stocks with higher scores in relevant dimensions. We evaluate our framework across four distinct stock universes, including the Dow Jones Industrial Average (DJIA) constituents and three sector-specific stock sets. Compared with existing multi-LLM frameworks and time-series-based baselines, 3S-Trader achieves the highest accumulated return of 131.83% on DJIA constituents with a Sharpe ratio of 0.31 and Calmar ratio of 11.84, while also delivering consistently strong results across other sectors. ...

THEME: Enhancing Thematic Investing with Semantic Stock Representations and Temporal Dynamics ArXiv ID: 2508.16936 “View on arXiv” Authors: Hoyoung Lee, Wonbin Ahn, Suhwan Park, Jaehoon Lee, Minjae Kim, Sungdong Yoo, Taeyoon Lim, Woohyung Lim, Yongjae Lee Abstract Thematic investing, which aims to construct portfolios aligned with structural trends, remains a challenging endeavor due to overlapping sector boundaries and evolving market dynamics. A promising direction is to build semantic representations of investment themes from textual data. However, despite their power, general-purpose LLM embedding models are not well-suited to capture the nuanced characteristics of financial assets, since the semantic representation of investment assets may differ fundamentally from that of general financial text. To address this, we introduce THEME, a framework that fine-tunes embeddings using hierarchical contrastive learning. THEME aligns themes and their constituent stocks using their hierarchical relationship, and subsequently refines these embeddings by incorporating stock returns. This process yields representations effective for retrieving thematically aligned assets with strong return potential. Empirical results demonstrate that THEME excels in two key areas. For thematic asset retrieval, it significantly outperforms leading large language models. Furthermore, its constructed portfolios demonstrate compelling performance. By jointly modeling thematic relationships from text and market dynamics from returns, THEME generates stock embeddings specifically tailored for a wide range of practical investment applications. ...

Predicting Realized Variance Out of Sample: Can Anything Beat The Benchmark? ArXiv ID: 2506.07928 “View on arXiv” Authors: Austin Pollok Abstract The discrepancy between realized volatility and the market’s view of volatility has been known to predict individual equity options at the monthly horizon. It is not clear how this predictability depends on a forecast’s ability to predict firm-level volatility. We consider this phenomenon at the daily frequency using high-dimensional machine learning models, as well as low-dimensional factor models. We find that marginal improvements to standard forecast error measurements can lead to economically significant gains in portfolio performance. This makes a case for re-imagining the way we train models that are used to construct portfolios. ...

LLM-Enhanced Black-Litterman Portfolio Optimization ArXiv ID: 2504.14345 “View on arXiv” Authors: Unknown Abstract The Black-Litterman model addresses the sensitivity issues of tra- ditional mean-variance optimization by incorporating investor views, but systematically generating these views remains a key challenge. This study proposes and validates a systematic frame- work that translates return forecasts and predictive uncertainty from Large Language Models (LLMs) into the core inputs for the Black-Litterman model: investor views and their confidence lev- els. Through a backtest on S&P 500 constituents, we demonstrate that portfolios driven by top-performing LLMs significantly out- perform traditional baselines in both absolute and risk-adjusted terms. Crucially, our analysis reveals that each LLM exhibits a dis- tinct and consistent investment style which is the primary driver of performance. We found that the selection of an LLM is therefore not a search for a single best forecaster, but a strategic choice of an investment style whose success is contingent on its alignment with the prevailing market regime. The source code and data are available at https://github.com/youngandbin/LLM-BLM. ...

LLMs for Time Series: an Application for Single Stocks and Statistical Arbitrage ArXiv ID: 2412.09394 “View on arXiv” Authors: Unknown Abstract Recently, LLMs (Large Language Models) have been adapted for time series prediction with significant success in pattern recognition. However, the common belief is that these models are not suitable for predicting financial market returns, which are known to be almost random. We aim to challenge this misconception through a counterexample. Specifically, we utilized the Chronos model from Ansari et al.(2024) and tested both pretrained configurations and fine-tuned supervised forecasts on the largest American single stocks using data from Guijarro-Ordonnez et al.(2022). We constructed a long/short portfolio, and the performance simulation indicates that LLMs can in reality handle time series that are nearly indistinguishable from noise, demonstrating an ability to identify inefficiencies amidst randomness and generate alpha. Finally, we compared these results with those of specialized models and smaller deep learning models, highlighting significant room for improvement in LLM performance to further enhance their predictive capabilities. ...