|
on Financial Markets |
| By: | David Thesmar; Emil Verner |
| Abstract: | We construct a new long-run series of subjective expected equity returns from an independent equity analysis firm, spanning 1956-2024. These expected returns are strongly positively correlated with the earnings-price ratio, respond negatively to past returns, and predict future returns. These patterns contrast with subjective expectations of individual investors and professional forecasters, which are weakly or negatively correlated with our new measure. Disagreement between sophisticated and individual investors is associated with higher trading volume. Our findings are consistent with a model of heterogeneous beliefs, where naive investors extrapolate past returns, rather than past dividends, while sophisticated investors are close to rational. |
| JEL: | E44 E47 E7 G11 G12 G17 G40 |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:35286 |
| By: | Rahul Fernandes; Travis Desell |
| Abstract: | Portfolio optimization in real-world financial markets is notoriously difficult due to non-stationarity, noisy data, and high transaction costs. Standard predict-then-optimize methods first forecast returns and then solve for weights, compounding prediction errors and often failing under regime shifts. We propose an end-to-end framework that directly optimizes differentiable surrogates of key financial metrics - Sharpe ratio, Omega ratio, Conditional Value-at-Risk (CVaR), and Risk Parity - allowing neural networks to learn portfolio weights via backpropagation. Our expanding-window walk-forward procedure, applied to 50 S&P 500 stocks from 2007 to 2023, incorporates realistic bid-ask spread costs and rebalances quarterly. On the challenging out-of-sample test period (2022-2023), the best model - an AttentionLSTM with the Omega-CVaR-RiskParity loss - achieves an annualized Sharpe of 0.29 and a total compounded return of +7.86%, while the S&P 500 delivers -4.52% total return and an annualized Sharpe of -0.02. This outperforms the S&P 500 by 12.38 percentage points (a relative improvement of over 270%), while keeping tail risk (CVaR) nearly unchanged. The framework consistently outperforms the equal-weight portfolio, S&P 500, and traditional methods (MVP, HRP, NCO), demonstrating that embedding financial objectives directly into model training yields robust, economically meaningful outperformance even in adverse market conditions. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2605.28853 |
| By: | Ajay Kumar Verma; Shravya Barkam |
| Abstract: | This paper compares a series of contemporary portfolio construction approaches by employing ten U.S. stocks (TSLA, WMT, BAC, GS, LLY, MRK, GOOG, META, AAPL and XOM) in a time frame from September 2023 to December 2025. The paper explores both basic mean-variance optimization, constrained optimization, Fama French five factor regression modeling, Monte Carlo simulation, and the Black-Litterman model to determine how constraints to a solution, risk factors to a strategy, simulated approximations, and specific market views may all impact the outcome of portfolio allocation, performance and stability. Overall, the results show that standard optimization may result in highly concentrated portfolios, while constrained optimization leads to changes in portfolio allocations by altering the efficient frontier, five factor regression models suggest that a basic investment style of defensive large value and profitability exposure, Monte Carlo approximation is a viable technique to arrive at mean-variance optimal portfolios provided the simulations are high enough especially under a box constraint, the Black Litterman portfolio approach produces more economically intuitive allocations and greater stability compared to standard mean-variance optimization as the approach balances equilibrium returns with investor views. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2605.29413 |
| By: | Ajay Kumar Verma; Jul Jon Ramirez General; Yvan Landry Ndzonde Fonkou |
| Abstract: | This study looks at the statistical properties and predictability using deep learning methods of the U.S. aggregate bond index in daily observations spanning 2018 to February 2026. We first establish that index levels are extremely persistent and consistent with unitroot behavior (Dickey and Fuller), while log returns are covariance-stationary with weak linear dependence and pronounced volatility clustering characteristic of ARCH-type processes (Engle; Bollerslev). Motivated by the trade-off between stationarity and information retention, we construct a "stationary but maximally persistent" representation via fractional differencing (Granger and Joyeux; Hosking) following the procedure of L\'opez de Prado, and evaluate shorthorizon forecast using two neural paradigms: (i) Multilayer Perceptrons (MLPs) trained on lagged vectors with joint lag-length and hyperparameter tuning (Hornik et al.; Rumelhart et al.); and (ii) Convolutional Neural Networks (CNNs) trained on Gramian Angular Field (GAF) image encodings (Wang and Oates). Empirically, MLPs match the strong naive persistence benchmark on levels, collapse toward near-zero forecasts on returns, and achieve the strongest incremental performance on the fractionally differenced series, where moderate dependence remains but unit-root drift is attenuated. In contrast, CNN-GAF models deliver consistently negative out-of-sample R 2 across all three representations. Overall, the results imply that, for short-horizon forecasting of broad bond indices, the primary determinant of predictive performance is the transformation of the series-its degree of stationarity and memory-rather than architectural complexity. Lag-based models remain competitive under persistence, while GAFbased CNNs are better suited to pattern-based tasks than to persistence-dominated next-step prediction. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2605.27977 |
| By: | Kpante Emmanuel Gnandi (INSA Toulouse); Fredy Pokou (MRE, CRIStAL); Jules Sadefo Kamdem (MRE) |
| Abstract: | Transition-related financial markets are increasingly exposed to abrupt repricing episodes, elevated volatility, and heterogeneous macro-financial shocks. Under such conditions, conventional Gaussian-linear forecasting frameworks may provide an incomplete representation of the dependence structure linking fossil-energy, renewable-energy, technology, and utility-sector assets. This paper investigates whether transition-related financial returns exhibit residual non-linear predictability after controlling for heavy-tailed multivariate linear dynamics. To address this question, we develop a hybrid forecasting framework combining Student-t Vector Autoregressions with nonlinear recurrent residual learning architectures. The empirical analysis considers six major exchange-traded funds representing broad equity markets and key transition-sensitive sectors. The results reveal substantial departures from Gaussian-linear behavior, including excess kurtosis, volatility clustering, and remaining nonlinear dependence after econometric filtering. Out-of-sample forecasting experiments show that the proposed framework consistently improves predictive accuracy relative to conventional VAR models, standalone machine-learning methods, and alternative hybrid specifications. The forecasting gains become more pronounced during periods of macro-financial stress, particularly during the COVID-19 crisis and the Ukraine-related energy shock. Overall, the findings suggest that transition-related financial systems exhibit regime-sensitive and heavy-tailed predictive dynamics that are insufficiently captured by standard Gaussian-linear models alone. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2605.26890 |
| By: | Andreas Fagereng; Luigi Guiso; Marius A. K. Ring |
| Abstract: | Using administrative panel data on Norwegian investors’ portfolios, we document strong but slow portfolio allocation responses to a persistent wealth-tax-induced shock to the equity premium. Short-run responses resemble the modest sensitivity documented using surveys. The longer-run responses are much larger and can be rationalized by moderate risk aversion. We document that equity premium shocks affect stock market entry but not exits, suggesting that entry costs dominate participation costs. Our finding of slow responses supports the asset-pricing literature that uses adjustment frictions to explain important asset-pricing puzzles, and has implications for optimal capital taxation when tax rates differ across assets. |
| JEL: | G11 G5 G51 H20 H31 |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:35262 |
| By: | Nag, Arindam |
| Abstract: | This paper investigates whether artificial intelligence amplifies systemic risk in equity markets using daily data spanning February 2023 to December 2025, comprising 721 observations across the CBOE Volatility Index, S&P 500 and NASDAQ Composite returns, abnormal trading volume, and the Amihud illiquidity ratio. Employing descriptive statistical analysis, an event study framework, OLS regression with Newey-West HAC-corrected standard errors, and a six-lag Vector Autoregression, the results provide evidence broadly consistent with systemic risk amplification through the liquidity withdrawal channel. The regression results indicate that market illiquidity, as measured by the Amihud ratio, is a statistically significant predictor of volatility (coefficient = 1, 144, 957; p |
| Keywords: | Artificial Intelligence, Algorithmic Trading, Systemic Risk, Market Volatility, Financial Stability, Liquidity Risk |
| JEL: | G0 G10 G14 G18 G3 G33 O33 |
| Date: | 2026 |
| URL: | https://d.repec.org/n?u=RePEc:pra:mprapa:128853 |
| By: | Cruz, Lizelle Ann |
| Abstract: | Systemic risk remains a key concern for financial authorities, especially in emerging economies where traditional, low‑frequency balance sheet indicators often lag changing conditions. This study develops a high‑frequency Systemic Risk Sentiment Index (SRSI) for the Philippines using news headlines from 2011–2025 and an ensemble of domain‑specific financial sentiment models. Results show that negative sentiment is mainly driven by external‑sector developments, market volatility, and equity‑related news, with surges aligning with global and domestic stress episodes. Empirical tests indicate only modest predictive power for domestic equity returns, and misclassifications highlight challenges in capturing nuances of Philippine financial reporting. Overall, the SRSI is best viewed as a responsive, real‑time barometer that complements conventional systemic risk measures. |
| Keywords: | Systemic Risk, Early Warning Indicators, Sentiment Analysis, Machine Learning, Large Language Model |
| JEL: | C43 C55 E44 G14 |
| Date: | 2026–03–02 |
| URL: | https://d.repec.org/n?u=RePEc:pra:mprapa:128944 |