|
on Financial Markets |
| By: | Tomasz R. Bielecki; Igor Cialenco |
| Abstract: | Robo-advisors (RAs) are automated portfolio management systems that complement traditional financial advisors by offering lower fees and smaller initial investment requirements. While most existing RAs rely on static, one-period allocation methods, we propose a dynamic, multi-period asset-allocation framework that leverages Model Predictive Control (MPC) to generate suboptimal but practically effective strategies. Our approach combines a Hidden Markov Model with Black-Litterman (BL) methodology to forecast asset returns and covariances, and incorporates practically important constraints, including turnover limits, transaction costs, and target portfolio allocations. We study two predominant optimality criteria in wealth management: dynamic mean-variance (MV) and dynamic risk-budgeting (MRB). Numerical experiments demonstrate that MPC-based strategies consistently outperform myopic approaches, with MV providing flexible and diversified portfolios, while MRB delivers smoother allocations less sensitive to key parameters. These findings highlight the trade-offs between adaptability and stability in practical robo-advising design. |
| Date: | 2026–01 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2601.09127 |
| By: | Chang Liu |
| Abstract: | The hedge fund industry presents significant challenges for investors due to its opacity and limited disclosure requirements. This pioneering study introduces two major innovations in financial text analysis. First, we apply topic modeling to hedge fund documents-an unexplored domain for automated text analysis-using a unique dataset of over 35, 000 documents from 1, 125 hedge fund managers. We compared three state-of-the-art methods: Latent Dirichlet Allocation (LDA), Top2Vec, and BERTopic. Our findings reveal that LDA with 20 topics produces the most interpretable results for human users and demonstrates higher robustness in topic assignments when the number of topics varies, while Top2Vec shows superior classification performance. Second, we establish a novel quantitative framework linking document sentiment to fund performance, transforming qualitative information traditionally requiring expert interpretation into systematic investment signals. In sentiment analysis, contrary to expectations, the general-purpose DistilBERT outperforms the finance-specific FinBERT in generating sentiment scores, demonstrating superior adaptability to diverse linguistic patterns found in hedge fund documents that extend beyond specialized financial news text. Furthermore, sentiment scores derived using DistilBERT in combination with Top2Vec show stronger correlations with subsequent fund performance compared to other model combinations. These results demonstrate that automated topic modeling and sentiment analysis can effectively process hedge fund documents, providing investors with new data-driven decision support tools. |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2512.06620 |
| By: | Mathis Mourey (The Hague University of Applied Sciences, CERAG - Centre d'études et de recherches appliquées à la gestion - UGA - Université Grenoble Alpes); Mohamad H Shahrour (HBKU - Hamad Bin Khalifa University [Doha, Qatar]); Florentina Şoiman (CERAG - Centre d'études et de recherches appliquées à la gestion - UGA - Université Grenoble Alpes) |
| Abstract: | This study examines the predictive power of weekend cryptocurrency performance on Monday stock returns. Using a Bayesian framework and Kalman filter, we analyze 20 of the largest cryptocurrencies, covering about 85% of market capitalization. Our results show a strong asymmetry: negative weekend returns significantly predict Monday equity declines, while positive returns have no effect. This pattern remains robust across benchmarks, including the Nasdaq, Russell 2000, S&P sector indices, and the S&P Crypto Index. The transmission mechanism strengthens markedly after the May 2022 LUNA collapse, signaling a structural break in crypto-equity dynamics. Our findings highlight the growing role of cryptocurrencies as transmitters of systemic risk and carry implications for forecasting, portfolio management, and financial stability monitoring. |
| Keywords: | Weekend effect, Information, Bayesian, Cryptocurrency, Stock indices |
| Date: | 2025–10–17 |
| URL: | https://d.repec.org/n?u=RePEc:hal:journl:hal-05415054 |
| By: | Sayed Akif Hussain; Chen Qiu-shi; Syed Amer Hussain; Syed Atif Hussain; Asma Komal; Muhammad Imran Khalid |
| Abstract: | This study proposes a novel hybrid deep learning framework that integrates a Large Language Model (LLM) with a Transformer architecture for stock price forecasting. The research addresses a critical theoretical gap in existing approaches that empirically combine textual and numerical data without a formal understanding of their interaction mechanisms. We conceptualise a prompt-based LLM as a mathematically defined signal generator, capable of extracting directional market sentiment and an associated confidence score from financial news. These signals are then dynamically fused with structured historical price features through a noise-robust gating mechanism, enabling the Transformer to adaptively weigh semantic and quantitative information. Empirical evaluations demonstrate that the proposed Hybrid LLM-Transformer model significantly outperforms a Vanilla Transformer baseline, reducing the Root Mean Squared Error (RMSE) by 5.28% (p = 0.003). Moreover, ablation and robustness analyses confirm the model's stability under noisy conditions and its capacity to maintain interpretability through confidence-weighted attention. The findings provide both theoretical and empirical support for a paradigm shift from empirical observation to formalised modelling of LLM-Transformer interactions, paving the way toward explainable, noise-resilient, and semantically enriched financial forecasting systems. |
| Date: | 2026–01 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2601.02878 |
| By: | Fornari, Fabio; Zaghini, Andrea; Pianeselli, Daniele |
| Abstract: | We provide empirical evidence that the pricing of green bonds tends to be highly sophisticated and based on a two-tiered approach. When buying a green bond, investors do not look only at the presence of a green label, but also consider additional characteristics of the bond that involve the environmental score of the issuer and the soundness of the underlying project. By comparing the yields at issuance of green bonds to those of a matched control sample of conventional bonds, our baseline specification identifies a premium of 16 basis points for the green label alone. Furthermore, when the environmental score of the issuer is in the top tercile of the cross-sectional distribution of such an indicator across the analyzed issuers, the greenium nearly doubles. Green certification and periods of heightened climate uncertainty also significantly affect the size of the greenium. JEL Classification: G12, G15, C21, C58, Q56 |
| Keywords: | corporate bonds, ESG scores, green bonds, greenium, sustainable finance |
| Date: | 2026–01 |
| URL: | https://d.repec.org/n?u=RePEc:ecb:ecbwps:20263176 |
| By: | Sahaj Raj Malla; Shreeyash Kayastha; Rumi Suwal; Harish Chandra Bhandari; Rajendra Adhikari |
| Abstract: | This study develops a robust machine learning framework for one-step-ahead forecasting of daily log-returns in the Nepal Stock Exchange (NEPSE) Index using the XGBoost regressor. A comprehensive feature set is engineered, including lagged log-returns (up to 30 days) and established technical indicators such as short- and medium-term rolling volatility measures and the 14-period Relative Strength Index. Hyperparameter optimization is performed using Optuna with time-series cross-validation on the initial training segment. Out-of-sample performance is rigorously assessed via walk-forward validation under both expanding and fixed-length rolling window schemes across multiple lag configurations, simulating real-world deployment and avoiding lookahead bias. Predictive accuracy is evaluated using root mean squared error, mean absolute error, coefficient of determination (R-squared), and directional accuracy on both log-returns and reconstructed closing prices. Empirical results show that the optimal configuration, an expanding window with 20 lags, outperforms tuned ARIMA and Ridge regression benchmarks, achieving the lowest log-return RMSE (0.013450) and MAE (0.009814) alongside a directional accuracy of 65.15%. While the R-squared remains modest, consistent with the noisy nature of financial returns, primary emphasis is placed on relative error reduction and directional prediction. Feature importance analysis and visual inspection further enhance interpretability. These findings demonstrate the effectiveness of gradient boosting ensembles in modeling nonlinear dynamics in volatile emerging market time series and establish a reproducible benchmark for NEPSE Index forecasting. |
| Date: | 2026–01 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2601.08896 |
| By: | Kim Christensen; Allan Timmermann; Bezirgen Veliyev |
| Abstract: | Corporate earnings announcements unpack large bundles of public information that should, in efficient markets, trigger jumps in stock prices. Testing this implication is difficult in practice, as it requires noisy high-frequency data from after-hours markets, where most earnings announcements are released. Using a unique dataset and a new microstructure noise-robust jump test, we show that earnings announcements almost always induce jumps in the stock price of announcing firms. They also significantly raise the probability of price co-jumps in non-announcing firms and the market. We find that returns from a post-announcement trading strategy are consistent with efficient price formation after 2016. |
| Date: | 2026–01 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2601.08962 |
| By: | Haibo Wang; Takeshi Tsuyuguchi |
| Abstract: | Major bank mergers and acquisitions (M&A) transform the financial market structure, but their valuation and spillover effects remain open to question. This study examines the market reaction to two M&A events: the 2005 creation of Mitsubishi UFJ Financial Group following the Financial Big Bang in Japan, and the 2018 merger involving Resona Holdings after the global financial crisis. The multi-method analysis in this research combines several distinct methods to explore these M&A events. An event study using the market model, the capital asset pricing model (CAPM), and the Fama-French three-factor model is implemented to estimate cumulative abnormal returns (CAR) for valuation purposes. Vector autoregression (VAR) models are used to test for Granger causality and map dynamic effects using impulse response functions (IRFs) to investigate spillovers. Propensity score matching (PSM) helps provide a causal estimate of the average treatment effect on the treated (ATT). The analysis detected a significant positive market reaction to the mergers. The findings also suggest the presence of prolonged positive spillovers to other banks, which may indicate a synergistic effect among Japanese banks. Combining these methods provides a unique perspective on M&A events in the Japanese banking sector, offering valuable insights for investors, managers, and regulators concerned with market efficiency and systemic stability |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2512.06550 |
| By: | Ali Hosseinzadeh |
| Abstract: | Speculative bubbles exhibit common statistical signatures across many financial markets, suggesting the presence of universal underlying mechanisms. We test this hypothesis in the Iranian stock market, an economy that is highly isolated, subject to capital controls, and largely inaccessible to foreign investors. Using the Log-Periodic Power Law Singularity (LPPLS) model, we analyze two major bubble episodes in 2020 and 2023. The estimated critical exponents beta around 0.46 and 0.20 fall within the empirical ranges documented for canonical historical bubbles such as the 1929 DJIA crash and the 2000 Nasdaq episode. The Tehran Stock Exchange displays clear LPPLS hallmarks, including faster-than-exponential price acceleration, log-periodic corrections, and stable estimates of the critical time horizon. These results indicate that endogenous herding, imitation, and positive-feedback dynamics, rather than exogenous shocks, play a dominant role even in politically and economically isolated markets. By showing that an emerging and semi-closed financial system conforms to the same dynamical patterns observed in global markets, this paper provides new empirical support for the universality of bubble dynamics. To the best of our knowledge, it also presents the first systematic LPPLS analysis of bubbles in the Tehran Stock Exchange. The findings highlight the usefulness of LPPLS-based diagnostic tools for monitoring systemic risk in emerging or restricted economies. |
| Date: | 2025–12 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2512.12054 |