|
on Financial Markets |
| By: | Candelon, Bertrand (Université catholique de Louvain, LIDAM/LFIN, Belgium); Hasse, Jean-Baptiste (Aix-Marseille University) |
| Abstract: | In this paper, we investigate investor behavior related to the attributes of ESG mutual funds. Specifically, we examine whether financial and extrafinancial attributes enter the investor’s decision problem additively or interact multiplicatively. We derive the return elasticity of investor demand under both hypotheses, which yields distinct predictions for the flow-performance relationship. Using a dataset of 6, 965 European active equity mutual funds from August 2018 to June 2025, we empirically test these competing hypotheses. Our results indicate that the sensitivity of fund flows to lagged returns is greater for ESG funds than for conventional funds. Accordingly, we reject specifications in which financial and extrafinancial attributes enter the investor’s decision problem additively. Our findings provide new insights into investor demand for fund attributes and ESG-washing practices. |
| Keywords: | Sustainable investing ; Mutual funds ; Investor behavior ; Cash flows |
| Date: | 2026–03–05 |
| URL: | https://d.repec.org/n?u=RePEc:ajf:louvlf:2026001 |
| By: | Gu, Ming; Hirshleifer, David; Teoh, Siew Hong; Wu, Shijia |
| Abstract: | We study dynamic visual representations as a proxy for investor sentiment about the stock market. Our sentiment index, GIFsentiment, is constructed from millions of posts in the Graphics Interchange Format (GIF) on a leading investment social media platform. GIFsentiment correlates with seasonal mood variations and the severity of COVID lockdowns. It is positively associated with contemporaneous market returns and negatively predicts returns for up to four weeks, even after controlling for other sentiment and attention measures. These effects are stronger among portfolios that are more susceptible to mispricing. GIFsentiment positively predicts trading volume, market volatility, and flows toward equity funds and away from debt funds. Our evidence suggests that GIFsentiment is a proxy for misperceptions that are later corrected. |
| Keywords: | GIF; Dynamic Visuals; Investor Sentiment; Attention; Salience; Social Finance; Stock Mispricing and Trading; Return Predictability; Anomalies; Mental Models; Narratives |
| JEL: | C53 D84 D85 G12 G14 |
| Date: | 2025–12–21 |
| URL: | https://d.repec.org/n?u=RePEc:pra:mprapa:127438 |
| By: | Takanobu Mizuta; Isao Yagi |
| Abstract: | Some investors say increasing investors with the same strategy decreasing their profits per an investor. On the other hand, some investors using technical analysis used to use same strategy and parameters with other investors, and say that it is better. Those argues are conflicted each other because one argues using with same strategy decreases profits but another argues it increase profits. However, those arguments have not been investigated yet. In this study, the agent-based artificial financial market model(ABAFMM) was built by adding "additional agents"(AAs) that includes additional fundamental agents (AFAs) and additional technical agents (ATAs) to the prior model. The AFAs(ATAs) trade obeying simple fundamental(technical) strategy having only the one parameter. We investigated earnings of AAs when AAs increased. We found that in the case with increasing AFAs, market prices are made stable that leads to decrease their profits. In the case with increasing ATAs, market prices are made unstable that leads to gain their profits more. |
| Date: | 2026–03 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2603.03671 |
| By: | Pei-Jun Liao; Hung-Shin Lee; Yao-Fei Cheng; Li-Wei Chen; Hung-yi Lee; Hsin-Min Wang |
| Abstract: | Predicting stock prices presents challenges in financial forecasting. While traditional approaches such as ARIMA and RNNs are prevalent, recent developments in Large Language Models (LLMs) offer alternative methodologies. This paper introduces an approach that integrates LLMs with daily financial news for stock price prediction. To address the challenge of processing news data and identifying relevant content, we utilize stock name embeddings within attention mechanisms. Specifically, we encode news articles using a pre-trained LLM and implement three attention-based pooling techniques -- self-attentive, cross-attentive, and position-aware self-attentive pooling -- to filter news based on stock relevance. The filtered news embeddings, combined with historical stock prices, serve as inputs to the prediction model. Unlike prior studies that focus on individual stocks, our method trains a single generalized model applicable across multiple stocks. Experimental results demonstrate a 7.11% reduction in Mean Absolute Error (MAE) compared to the baseline, indicating the utility of stock name embeddings for news filtering and price forecasting within a generalized framework. |
| Date: | 2026–03 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2603.19286 |
| By: | Juan David Vega Baquero (Riskcenter, Department of Econometrics, Universitat de Barcelona, Spain.); Miguel Santolino (Riskcenter, Department of Econometrics, Universitat de Barcelona, Spain.) |
| Abstract: | Asset allocation refers to deciding the optimal participation of each asset within a portfolio. Therefore, these participations are a composition, and compositional methods should be used to treat the data and perform analysis over it. When trying to find relationships between parts of a composition, proportions have shown to be more suitable than correlations. In this paper, using a previous proportionality index as starting point, two new indexes are proposed and all of them are used to analyze the asset allocation in a portfolio composed of five stocks from the IBEX 35 (the Spanish stock market index). Results shed light on the connection between volatility, allocations and their proportionality. |
| Keywords: | Aitchison Geometry; Capital Allocation; Portfolio Theory; Proportionality. JEL classification: C01; E22; G11. |
| Date: | 2026–01 |
| URL: | https://d.repec.org/n?u=RePEc:ira:wpaper:202601 |
| By: | Wajcman, Judy; Kampmann, David; Young, Erin |
| Abstract: | Venture capital (VC) is fuelling the boom in artificial intelligence (AI). Yet analysis of a UK dataset reveals that VC is dominated by men, both as investors and the AI start-ups they fund. Gender disparities are identified in VC decision-makers, the composition of founders and the average capital raised by predominantly male, compared to female, teams. This is particularly pronounced in AI software start-ups, the sector that attracts most investment. Whether and how this gender gap shapes the innovation process itself is a further question explored here. Drawing on feminist science and technology studies, we argue that the homogeneity of the VC ecosystem is key to perpetuating the gender gap in innovation. On this basis, we conceptualise venture capital as effectively a form of ‘male-lens investing’, illustrating the limitations of the male-dominated and profit-driven VC investment model. We believe this theoretical framing contributes to contextualising debates about the need for inclusive innovation systems. |
| Keywords: | venture capital; gender; AI |
| JEL: | A14 B54 G24 |
| Date: | 2026–03–12 |
| URL: | https://d.repec.org/n?u=RePEc:ehl:lserod:137323 |
| By: | Olkhov, Victor |
| Abstract: | We show that Markowitz’s (1952) portfolio variance describes only a limited case when all volumes of successive trades at exchange with shares of all securities of the portfolio are assumed constant during the averaging interval. We overcome this limitation and derive market-based portfolio variance that depends upon the means, variances, and covariance of random values and volumes of consecutive trades. To derive that, we convert the time series of trades made at the exchange with shares of portfolio securities and obtain the time series that model the trades with the portfolio like trades with one security. That establishes an equal description of market-based variance of any security and portfolio. The time series that model the trades with the portfolio, like trades with one security, reveal that the market-based equation that describes random portfolio return depends on random returns of its securities and on random volumes of market trades. Markowitz hasn't accounted for the impact of random trade volumes on random portfolio returns. If all trade volumes are assumed constant, the market-based equation on random portfolio returns coincides with the corresponding Markowitz equation. We use market-based portfolio variance that accounts for random trade volumes and describe the dependence of the Sharpe Ratio of the portfolio on random trade volumes. We prove that correlations between random prices and trade volumes always equal zero. To study market-based statistical dependence between random trade volumes and prices, one should empirically calculate correlations between prices and squares of trade volumes. |
| Keywords: | portfolio variance, portfolio theory, random trade volumes |
| JEL: | G00 G11 G12 G17 G24 |
| Date: | 2026–01–20 |
| URL: | https://d.repec.org/n?u=RePEc:pra:mprapa:127810 |
| By: | Matteo Bonato (Department of Economics and Econometrics, University of Johannesburg, Auckland Park, South Africa; IPAG Business School, 184 Boulevard Saint-Germain, 75006 Paris, France); Oguzhan Cepni (Ostim Technical University, Ankara, Turkiye; University of Edinburgh Business School, Centre for Business, Climate Change, and Sustainability; Department of Economics, Copenhagen Business School, Denmark); Rangan Gupta (Department of Economics, University of Pretoria, Private Bag X20, Hatfield 0028, South Africa); Christian Pierdzioch (Department of Economics, Helmut Schmidt University, Holstenhofweg 85, P.O.B. 700822, 22008 Hamburg, Germany) |
| Abstract: | We introduce credit standards from the Federal Reserve's Senior Loan Officer Opinion Survey (SLOOS) as a novel predictor of U.S. stock market realized volatility over 1990:04-2024:12. We show that tighter credit standards significantly predict higher realized volatility both in- and out-of-sample at one-, three-, and six-month-ahead horizons. A parsimonious model with only the credit standards factor outperforms more complex specifications incorporating macroeconomic factors, uncertainty indexes, and realized moments, estimated via elastic-net and random forest methods, with forecasting gains increasing at longer horizons. These findings establish credit standards as a powerful and distinct predictor of stock market volatility with practical implications for portfolio allocation and risk management. |
| Keywords: | Credit conditions, Realized stock market volatility, Forecasting |
| JEL: | C22 C53 E23 G10 G17 |
| Date: | 2026–03 |
| URL: | https://d.repec.org/n?u=RePEc:pre:wpaper:202607 |
| By: | Schöller, Vanessa |
| Abstract: | The smooth functioning of the repo market is essential to financial stability. However, the market has faced repeated episodes of stress in recent years. This paper examines the resilience of the euro-denominated repo market during recent episodes of elevated financial stress, drawing on transaction-level data and applying network analysis. The institutional repo network displays a core–periphery structure, with connectivity intensifying during stress periods. At the sectoral level, trading volumes and repo spreads remain broadly stable. For the euro repo market as a whole, financial stress is associated with lower spreads, consistent with the interpretation that the market functions as a shock absorber. JEL Classification: G01, G21, G23, E44 |
| Keywords: | haircuts, network analysis, non-banks, repo spreads |
| Date: | 2026–03 |
| URL: | https://d.repec.org/n?u=RePEc:ecb:ecbwps:20263205 |
| By: | Ursina Sanderink |
| Abstract: | Cross-sectional ranking models are often deployed as if point predictions were sufficient: the model outputs scores and the portfolio follows the induced ordering. Under non-stationarity, rankers can fail during regime shifts. In the AI Stock Forecaster, a LightGBM ranker performs well overall at a 20-day horizon, yet the 2024 holdout coincides with an AI thematic rally and sector rotation that breaks the signal at longer horizons and weakens 20d. This motivates treating deployment as two decisions: (i) whether the strategy should trade at all, and (ii) how to control risk within active trades. We adapt Direct Epistemic Uncertainty Prediction (DEUP) to ranking by predicting rank displacement and defining an epistemic uncertainty signal ehat relative to a point-in-time (PIT-safe) baseline. Empirically, ehat is structurally coupled with signal strength (median correlation between ehat and absolute score is about 0.6 across 1, 865 dates), so inverse-uncertainty sizing de-levers the strongest signals and degrades performance. To address this, we propose a two-level deployment policy: a strategy-level regime-trust gate G(t) that decides whether to trade (AUROC around 0.72 overall and 0.75 in FINAL) and a position-level epistemic tail-risk cap that reduces exposure only for the most uncertain predictions. The operational policy, trade only when G(t) is at least 0.2, apply volatility sizing on active dates, and cap the top epistemic tail, improves risk-adjusted performance in the 20d policy comparison and indicates DEUP adds value mainly as a tail-risk guard rather than a continuous sizing denominator. |
| Date: | 2026–02 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2603.13252 |
| By: | Mohammad Al Ridhawi; Mahtab Haj Ali; Hussein Al Osman |
| Abstract: | Stock markets exhibit regime-dependent behavior where prediction models optimized for stable conditions often fail during volatile periods. Existing approaches typically treat all market states uniformly or require manual regime labeling, which is expensive and quickly becomes stale as market dynamics evolve. This paper introduces an adaptive prediction framework that adaptively identifies deviations from normal market conditions and routes data through specialized prediction pathways. The architecture consists of three components: (1) an autoencoder trained on normal market conditions that identifies anomalous regimes through reconstruction error, (2) dual node transformer networks specialized for stable and event-driven market conditions respectively, and (3) a Soft Actor-Critic reinforcement learning controller that adaptively tunes the regime detection threshold and pathway blending weights based on prediction performance feedback. The reinforcement learning component enables the system to learn adaptive regime boundaries, defining anomalies as market states where standard prediction approaches fail. Experiments on 20 S&P 500 stocks spanning 1982 to 2025 demonstrate that the proposed framework achieves 0.68% MAPE for one-day predictions without the reinforcement controller and 0.59% MAPE with the full adaptive system, compared to 0.80% for the baseline integrated node transformer. Directional accuracy reaches 72% with the complete framework. The system maintains robust performance during high-volatility periods, with MAPE below 0.85% when baseline models exceed 1.5%. Ablation studies confirm that each component contributes meaningfully: autoencoder routing accounts for 36% relative MAPE degradation upon removal, followed by the SAC controller at 15% and the dual-path architecture at 7%. |
| Date: | 2026–03 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2603.19136 |