|
on Financial Markets |
| By: | Abraham Itzhak Weinberg |
| Abstract: | Financial market prediction is a challenging application of machine learning, where even small improvements in directional accuracy can yield substantial value. Most models struggle to exceed 55--57\% accuracy due to high noise, non-stationarity, and market efficiency. We introduce a hybrid ensemble framework combining quantum sentiment analysis, Decision Transformer architecture, and strategic model selection, achieving 60.14\% directional accuracy on S\&P 500 prediction, a 3.10\% improvement over individual models. Our framework addresses three limitations of prior approaches. First, architecture diversity dominates dataset diversity: combining different learning algorithms (LSTM, Decision Transformer, XGBoost, Random Forest, Logistic Regression) on the same data outperforms training identical architectures on multiple datasets (60.14\% vs.\ 52.80\%), confirmed by correlation analysis ($r>0.6$ among same-architecture models). Second, a 4-qubit variational quantum circuit enhances sentiment analysis, providing +0.8\% to +1.5\% gains per model. Third, smart filtering excludes weak predictors (accuracy $ |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2512.15738 |
| By: | Siqi Shao; Arshia Ghasemi; Hamed Farahani; R. A. Serota |
| Abstract: | We argue that negative skew and positive mean of the distribution of stock returns are largely due to the broken symmetry of stochastic volatility governing gains and losses. Starting with stochastic differential equations for stock returns and for stochastic volatility we argue that the distribution of stock returns can be effectively split in two - for gains and losses - assuming difference in parameters of their respective stochastic volatilities. A modified Jones-Faddy skew t-distribution utilized here allows to reflect this in a single organic distribution which tends to meaningfully capture this asymmetry. We illustrate its application on distribution of daily S&P500 returns, including analysis of its tails. |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2512.23640 |
| By: | Elisa Ossola; Irina Trifan |
| Abstract: | We develop an empirical application on a large dataset of European stock returns, in order to estimate the risk premia. We propose an application of the Three-Pass Estimation Method (3PEM) by Xiu and Giglio (2021) as a multipurpose tool in asset pricing. By assuming the Fama–French Five-Factor model (Fama and French (2015)) as baseline model, we show that the 3PEM yields risk premium estimates that are more economically plausible and statistically robust than those obtained using the traditional two-pass estimation method (2PEM). Moreover, we extend the results by Xiu and Giglio (2021) showing that the 3PEM is able to detect noise in tradable factors. Furthermore, the method is used to denoise the observed factors, providing purified versions that better capture the systematic components of risk. We also identify noisy factors, and yield denoised factor series that improve the estimation of stock-level exposures and expected returns. |
| Keywords: | three-pass estimator, Empirical asset pricing, PCA, large panels. |
| JEL: | G12 C58 C55 |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:mib:wpaper:565 |
| By: | Anusha Chari; Peter Blair Henry; Yanru Lee; Paolo Mauro |
| Abstract: | Despite the scarcity of infrastructure in emerging-market and developing economies (EMDEs), in the absence of readily accessible data on the historical performance of EMDE infrastructure as an asset class, private investors are reluctant to finance infrastructure projects in these countries. We begin to fill this information gap by computing the financial returns from equity investments in primarily unlisted firms in EMDEs made by the International Finance Corporation, the private-sector arm of the World Bank Group. The public market equivalent of 266 equity investments in core infrastructure by the IFC, with starting dates from 1961 to March 2020, was 1.17 using the S&P 500 as a benchmark, and 1.26 using the MSCI Emerging Markets Index. On average, over the past six decades, equity stakes in emerging-market infrastructure backed by the IFC thus delivered higher returns than investments in portfolios of publicly listed equities. Data from the full sample of IFC equity investments reveal that, on average, a diversified portfolio of investments in infrastructure-related sectors, and indeed, in all sectors more generally, generated significant positive financial returns, albeit with variation across decades. |
| JEL: | F21 G11 G24 H54 O16 O19 |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:34537 |
| By: | Xiang-Li Lim; Puja Singh; Richard Stobo |
| Abstract: | This paper examines the uptake of AI in securities markets and recent approaches to its regulation and supervision, complementing work by IMF and standard setters’ initiatives. It highlights the adoption of AI across financial services, the growing use of GenAI, and the associated risks, including data, performance, new cybersecurity threats, and broader financial stability risks. While AI offers benefits, its adoption warrants caution given the potential for material risks that could undermine financial sector’s reputation and soundness. The paper highlights how authorities are responding, providing a stocktake of regulatory and supervisory developments. While the paper compares advanced economies (AEs) and emerging markets and developing economies (EMDEs), it highlights the significant heterogeneity within EMDEs, in terms of technology adoption and capacity. Finally, the paper summarizes key take-aways and identifies practices that authorities could consider adopting as part of their supervisory frameworks. |
| Date: | 2025–12–24 |
| URL: | https://d.repec.org/n?u=RePEc:imf:imftnm:2025/016 |
| By: | 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. |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2512.24526 |
| By: | Pengpeng Li; Shi-Dong Liang |
| Abstract: | Based on the analog between the stochastic dynamics and quantum harmonic oscillator, we propose a market force driving model to generalize the Black-Scholes model in finance market. We give new schemes of option pricing, in which we can take various unexpected market behaviors into account to modify the option pricing. As examples, we present several market forces to analyze their effects on the option pricing. These results provide us two practical applications. One is to be used as a new scheme of option pricing when we can predict some hidden market forces or behaviors emerging. The other implies the existence of some risk premium when some unexpected forces emerge. |
| Date: | 2026–01 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2601.00293 |
| By: | Inna Abramova; John M. Barrios |
| Abstract: | Private equity (PE) has moved rapidly into professional services, yet its impact on accounting, where licensing regimes, reputational capital, and partnership governance traditionally limit external ownership, remains poorly understood. We examine how PE ownership alters the organization and market structure of accounting firms using data from 1999-2024 that link more than 3, 600 PE transactions to detailed information on mergers and acquisitions (M&A), labor markets, and audit pricing. PE investment increases sharply after 2020 and extends to both CPA-licensed audit firms and non-CPA advisory practices, with most activity in large mid-tier PCAOB-registered firms. After PE entry, firms grow faster: non-audit revenues rise, employment expands, and cross-state M&A accelerates, consistent with platform-building and consolidation. These adjustments have market-level implications. PE investment raises labor-market concentration in key accounting occupations and drives up ERISA audit fees in a standardized setting, as confirmed by a synthetic difference-in-differences design. Our results reveal a key tension at the core of professions: preserving independence and competition in a market increasingly driven by financial capital. |
| JEL: | G23 G34 J44 L2 L4 L84 M4 M41 M42 |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:34575 |