|
on Financial Markets |
| By: | Prashant Pilla; Raji Mekonen |
| Abstract: | With the volatile and complex nature of financial data influenced by external factors, forecasting the stock market is challenging. Traditional models such as ARIMA and GARCH perform well with linear data but struggle with non-linear dependencies. Machine learning and deep learning models, particularly Long Short-Term Memory (LSTM) networks, address these challenges by capturing intricate patterns and long-term dependencies. This report compares ARIMA and LSTM models in predicting the S&P 500 index, a major financial benchmark. Using historical price data and technical indicators, we evaluated these models using Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE). The ARIMA model showed reasonable performance with an MAE of 462.1, RMSE of 614, and 89.8 percent accuracy, effectively capturing short-term trends but limited by its linear assumptions. The LSTM model, leveraging sequential processing capabilities, outperformed ARIMA with an MAE of 369.32, RMSE of 412.84, and 92.46 percent accuracy, capturing both short- and long-term dependencies. Notably, the LSTM model without additional features performed best, achieving an MAE of 175.9, RMSE of 207.34, and 96.41 percent accuracy, showcasing its ability to handle market data efficiently. Accurately predicting stock movements is crucial for investment strategies, risk assessments, and market stability. Our findings confirm the potential of deep learning models in handling volatile financial data compared to traditional ones. The results highlight the effectiveness of LSTM and suggest avenues for further improvements. This study provides insights into financial forecasting, offering a comparative analysis of ARIMA and LSTM while outlining their strengths and limitations. |
| Date: | 2025–01 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2501.17366 |
| By: | Ayush Jha; Abootaleb Shirvani; Ali Jaffri; Svetlozar T. Rachev; Frank J. Fabozzi |
| Abstract: | This study presents the Adaptive Minimum-Variance Portfolio (AMVP) framework and the Adaptive Minimum-Risk Rate (AMRR) metric, innovative tools designed to optimize portfolios dynamically in volatile and nonstationary financial markets. Unlike traditional minimum-variance approaches, the AMVP framework incorporates real-time adaptability through advanced econometric models, including ARFIMA-FIGARCH processes and non-Gaussian innovations. Empirical applications on cryptocurrency and equity markets demonstrate the proposed framework's superior performance in risk reduction and portfolio stability, particularly during periods of structural market breaks and heightened volatility. The findings highlight the practical implications of using the AMVP and AMRR methodologies to address modern investment challenges, offering actionable insights for portfolio managers navigating uncertain and rapidly changing market conditions. |
| Date: | 2025–01 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2501.15793 |
| By: | Peter Albrecht; Evžen Kočenda; Evžen Kocenda |
| Abstract: | Our study presents an in-depth analysis of the interconnectedness in returns among five major cryptocurrencies from 2018 to 2023. Our work introduces novel findings by employing a novel bootstrap-after-bootstrap method of Greenwood-Nimmo et al. (2024) to establish a link between increases in connectedness and various systematic events. We found a clear rise in connectedness within a month following the event for ten endogenously selected events. Further, we identify Bitcoin and Ethereum as net return transmitters, mainly to Binance coin and Ripple. Moreover, we found that these transmissions increased by up to 20% for up to one month after the shocks occurred. We calculate optimal portfolio weights and hedging ratios for cryptocurrency risk management. Our findings reveal that Cardano and Ripple are the most effective choices in portfolio optimization. The implications of this study are significant for devising strategies in portfolio management and risk hedging, offering valuable guidance for policy formulation in the financial sector. |
| Keywords: | return connectedness, cryptocurrencies, bootstrap-after-bootstrap procedure, portfolio composition and hedging |
| JEL: | H56 G11 G15 Q40 |
| Date: | 2025 |
| URL: | https://d.repec.org/n?u=RePEc:ces:ceswps:_11658 |
| By: | Heming Chen |
| Abstract: | This study systematically examines how several alternative approaches considered affect three aspects that determine portfolio performance (the gross return, the transaction costs and the portfolio risk). We find that it is difficult to exploit the possible predictability of asset returns. However, the predictability of asset return volatility produces obvious economic value, although in a highly correlated cryptocurrencies market. |
| Date: | 2025–01 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2501.12841 |
| By: | Jinghai He; Cheng Hua; Chunyang Zhou; Zeyu Zheng |
| Abstract: | We develop a portfolio allocation framework that leverages deep learning techniques to address challenges arising from high-dimensional, non-stationary, and low-signal-to-noise market information. Our approach includes a dynamic embedding method that reduces the non-stationary, high-dimensional state space into a lower-dimensional representation. We design a reinforcement learning (RL) framework that integrates generative autoencoders and online meta-learning to dynamically embed market information, enabling the RL agent to focus on the most impactful parts of the state space for portfolio allocation decisions. Empirical analysis based on the top 500 U.S. stocks demonstrates that our framework outperforms common portfolio benchmarks and the predict-then-optimize (PTO) approach using machine learning, particularly during periods of market stress. Traditional factor models do not fully explain this superior performance. The framework's ability to time volatility reduces its market exposure during turbulent times. Ablation studies confirm the robustness of this performance across various reinforcement learning algorithms. Additionally, the embedding and meta-learning techniques effectively manage the complexities of high-dimensional, noisy, and non-stationary financial data, enhancing both portfolio performance and risk management. |
| Date: | 2025–01 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2501.17992 |
| By: | Michael Brolley; David Cimon |
| Abstract: | Non-bank financial institutions, such as principal-trading firms and hedge funds, increasingly compete with bank-owned dealers in fixed-income markets. Some market participants worry that if non-bank financial institutions push out established bank dealers, liquidity will become unreliable during times of stress. We model non-bank entry and state-dependent liquidity provision. Non-bank participants improve liquidity more during normal times than in stress, leading to a bifurcation of liquidity. In the cross-section, their entry improves liquidity for large and previously unserved small clients; however, banks may no longer provide reliable liquidity to marginal clients. Central bank lending may limit harmful bifurcation during times of stress if that lending is predictable and at sufficiently favourable terms. |
| Keywords: | Economic models; Financial institutions; Financial markets; Market structure and pricing |
| JEL: | G10 G20 G21 G23 L10 L13 L14 |
| Date: | 2025–01 |
| URL: | https://d.repec.org/n?u=RePEc:bca:bocawp:25-2 |