Based on the typical positions of S&P 500 option market makers, we derive a funding illiquidity measure from quoted prices of S&P 500 derivatives. Our measure significantly affects the returns of leveraged managed portfolios; hedge funds with negative exposure to changes in funding illiquidity earn high returns in normal times and low returns in crisis periods when funding liquidity deteriorates. The results are not driven by existing measures of funding illiquidity, market illiquidity, and proxies for tail risk. Our funding illiquidity measure also affects leveraged closed-end mutual funds and, to an extent, asset classes where leveraged investors are marginal investors.
{"title":"Funding Illiquidity Implied by S&P 500 Derivatives","authors":"Benjamin Golez, Jens Jackwerth, Anna Slavutskaya","doi":"10.3390/risks12090149","DOIUrl":"https://doi.org/10.3390/risks12090149","url":null,"abstract":"Based on the typical positions of S&P 500 option market makers, we derive a funding illiquidity measure from quoted prices of S&P 500 derivatives. Our measure significantly affects the returns of leveraged managed portfolios; hedge funds with negative exposure to changes in funding illiquidity earn high returns in normal times and low returns in crisis periods when funding liquidity deteriorates. The results are not driven by existing measures of funding illiquidity, market illiquidity, and proxies for tail risk. Our funding illiquidity measure also affects leveraged closed-end mutual funds and, to an extent, asset classes where leveraged investors are marginal investors.","PeriodicalId":21282,"journal":{"name":"Risks","volume":"66 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142253959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Following the introduction of EUR/USD futures and USD/JPY futures on 31 October 2022, Thailand Futures Exchange first entered the top 11 list of derivatives exchanges based on foreign exchange derivative volumes in 2022. This paper investigates the dynamics of foreign exchange futures trading volumes in Thailand through the VAR(2) model. Trading volumes of EUR/USD futures, USD/JPY futures, and USD/THB futures are considered over the sample period from 31 October 2022 to 12 January 2024. The empirical results provide no evidence that the trading volume of EUR/USD futures is dependent on the past trading volumes of USD/JPY futures and USD/THB futures. The Granger causality test results show the existence of bidirectional causality between the trading volumes of USD/JPY futures and USD/THB futures. The results of the impulse response function are consistent with the sign results of the VAR(2) model, showing that the USD/JPY futures trading volume has a negative impact on the USD/THB futures trading volume, and vice versa. The analysis of variance decomposition shows that the variability of the USD/JPY futures trading volume and USD/THB futures trading volume, apart from its own shock, is explained by other FX futures trading volume shocks. Therefore, traders should pay more attention to new FX futures trading activity due to its negative impact on the USD/THB futures trading volume and its contribution to the variance in the USD/THB futures trading volume. Understanding the futures trading volume relationship also helps Thailand Futures Exchange develop new products and services that can foster market liquidity and stability.
{"title":"Dynamics of Foreign Exchange Futures Trading Volumes in Thailand","authors":"Woradee Jongadsayakul","doi":"10.3390/risks12090147","DOIUrl":"https://doi.org/10.3390/risks12090147","url":null,"abstract":"Following the introduction of EUR/USD futures and USD/JPY futures on 31 October 2022, Thailand Futures Exchange first entered the top 11 list of derivatives exchanges based on foreign exchange derivative volumes in 2022. This paper investigates the dynamics of foreign exchange futures trading volumes in Thailand through the VAR(2) model. Trading volumes of EUR/USD futures, USD/JPY futures, and USD/THB futures are considered over the sample period from 31 October 2022 to 12 January 2024. The empirical results provide no evidence that the trading volume of EUR/USD futures is dependent on the past trading volumes of USD/JPY futures and USD/THB futures. The Granger causality test results show the existence of bidirectional causality between the trading volumes of USD/JPY futures and USD/THB futures. The results of the impulse response function are consistent with the sign results of the VAR(2) model, showing that the USD/JPY futures trading volume has a negative impact on the USD/THB futures trading volume, and vice versa. The analysis of variance decomposition shows that the variability of the USD/JPY futures trading volume and USD/THB futures trading volume, apart from its own shock, is explained by other FX futures trading volume shocks. Therefore, traders should pay more attention to new FX futures trading activity due to its negative impact on the USD/THB futures trading volume and its contribution to the variance in the USD/THB futures trading volume. Understanding the futures trading volume relationship also helps Thailand Futures Exchange develop new products and services that can foster market liquidity and stability.","PeriodicalId":21282,"journal":{"name":"Risks","volume":"18 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2024-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142253961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We evaluate whether machine learning methods can better model excess portfolio returns compared to the standard regression-based strategies generally used in the finance and econometric literature. We examine 17 benchmark factor model specifications based on Expected Utility Theory and theory drawn from behavioural finance. We assess whether machine learning can identify features of the data-generating process undetected by standard methods and rank the best-performing algorithms. Our tests use 95 years of CRSP data, from 1926 to 2021, encompassing the price history of the broad US stock market. Our findings suggest that machine learning methods provide more accurate models of stock returns based on risk factors than standard regression-based methods of estimation. They also indicate that certain risk factors and combinations of risk factors may be more attractive when more appropriate account is taken of the non-linear properties of the underlying assets.
{"title":"Automated Machine Learning and Asset Pricing","authors":"Jerome V. Healy, Andros Gregoriou, Robert Hudson","doi":"10.3390/risks12090148","DOIUrl":"https://doi.org/10.3390/risks12090148","url":null,"abstract":"We evaluate whether machine learning methods can better model excess portfolio returns compared to the standard regression-based strategies generally used in the finance and econometric literature. We examine 17 benchmark factor model specifications based on Expected Utility Theory and theory drawn from behavioural finance. We assess whether machine learning can identify features of the data-generating process undetected by standard methods and rank the best-performing algorithms. Our tests use 95 years of CRSP data, from 1926 to 2021, encompassing the price history of the broad US stock market. Our findings suggest that machine learning methods provide more accurate models of stock returns based on risk factors than standard regression-based methods of estimation. They also indicate that certain risk factors and combinations of risk factors may be more attractive when more appropriate account is taken of the non-linear properties of the underlying assets.","PeriodicalId":21282,"journal":{"name":"Risks","volume":"187 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2024-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142253962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study delves into the influence of banks’ governance and ownership structures on green lending. To examine this, we utilized the two-step system GMM and PCSE methods on the panel data of Vietnamese commercial banks spanning from 2010 to 2023. The findings suggest that board characteristics, precisely board size, board independence, and gender diversity, play a significant role in encouraging banks to provide green credit. The study highlights the importance of ownership structure in green lending. Banks with a high percentage of government ownership tend to fund more green projects, while foreign counterparts are reluctant to fund green finance. A mechanism test is also conducted to point out that banks’ disclosure of their green loan commitments is an influential channel whereby corporate governance and ownership structure impact green loans. Additionally, this research finds that the issuance of the Green Loan Principles in 2018 can facilitate banks’ governance of sustainable lending.
{"title":"What Drives Banks to Provide Green Loans? Corporate Governance and Ownership Structure Perspectives of Vietnamese Listed Banks","authors":"Ariful Hoque, Duong Thuy Le, Thi Le","doi":"10.3390/risks12090146","DOIUrl":"https://doi.org/10.3390/risks12090146","url":null,"abstract":"This study delves into the influence of banks’ governance and ownership structures on green lending. To examine this, we utilized the two-step system GMM and PCSE methods on the panel data of Vietnamese commercial banks spanning from 2010 to 2023. The findings suggest that board characteristics, precisely board size, board independence, and gender diversity, play a significant role in encouraging banks to provide green credit. The study highlights the importance of ownership structure in green lending. Banks with a high percentage of government ownership tend to fund more green projects, while foreign counterparts are reluctant to fund green finance. A mechanism test is also conducted to point out that banks’ disclosure of their green loan commitments is an influential channel whereby corporate governance and ownership structure impact green loans. Additionally, this research finds that the issuance of the Green Loan Principles in 2018 can facilitate banks’ governance of sustainable lending.","PeriodicalId":21282,"journal":{"name":"Risks","volume":"11 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142197329","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Manuel García-Nieto, Vicente Bueno-Rodríguez, Juan Manuel Ramón-Jerónimo, Raquel Flórez-López
This study examines risk factors in mergers and acquisitions (M&As) identified in the recent literature, addressing the following question: “What risk factors associated with M&A transactions are discussed in the recent academic literature?” A semi-systematic literature review was conducted using a comprehensive search strategy with targeted keywords related to M&A risks. Papers from 2020 to 2024 were selected based on quality and relevance, with detailed review of abstracts and titles. Co-occurrence analysis using VOSviewer software (version 1.6.20) was applied to categorize key themes. The review of 118 papers identified four main risk categories: information asymmetry; performance and corporate reputation; litigation and investor protection; and geopolitical factors. Findings reveal complex interdependencies among these risks, highlighting the need for a holistic approach to risk management. Corporate social responsibility (CSR) is crucial for mitigating risks, improving transparency, and enhancing reputation. This study offers recommendations for better financial disclosures, robust environmental, social and governance strategies, and the integration of digital finance technologies as blockchain in M&A activity. Future research should include longitudinal studies on M&A risk dynamics, case studies on corporate governance, advanced valuation methods, and comparative analyses across regions and industries, focusing on emerging technologies like AI and blockchain.
{"title":"Trends and Risks in Mergers and Acquisitions: A Review","authors":"Manuel García-Nieto, Vicente Bueno-Rodríguez, Juan Manuel Ramón-Jerónimo, Raquel Flórez-López","doi":"10.3390/risks12090143","DOIUrl":"https://doi.org/10.3390/risks12090143","url":null,"abstract":"This study examines risk factors in mergers and acquisitions (M&As) identified in the recent literature, addressing the following question: “What risk factors associated with M&A transactions are discussed in the recent academic literature?” A semi-systematic literature review was conducted using a comprehensive search strategy with targeted keywords related to M&A risks. Papers from 2020 to 2024 were selected based on quality and relevance, with detailed review of abstracts and titles. Co-occurrence analysis using VOSviewer software (version 1.6.20) was applied to categorize key themes. The review of 118 papers identified four main risk categories: information asymmetry; performance and corporate reputation; litigation and investor protection; and geopolitical factors. Findings reveal complex interdependencies among these risks, highlighting the need for a holistic approach to risk management. Corporate social responsibility (CSR) is crucial for mitigating risks, improving transparency, and enhancing reputation. This study offers recommendations for better financial disclosures, robust environmental, social and governance strategies, and the integration of digital finance technologies as blockchain in M&A activity. Future research should include longitudinal studies on M&A risk dynamics, case studies on corporate governance, advanced valuation methods, and comparative analyses across regions and industries, focusing on emerging technologies like AI and blockchain.","PeriodicalId":21282,"journal":{"name":"Risks","volume":"29 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142197492","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper aims to assess the return and downside risk of a decumulation portfolio established at the retirement age of a senior, with a determined lifetime horizon differentiated by the sex of the citizen. To measure the portfolio’s return and downside risk, two ratios conditioned by seniors’ risk attitude towards portfolio failure are employed: the downside Sortino ratio and the downside risk–return ratio. Unlike other research in the field, this manuscript provides three portfolio compositions catering to different senior investment profiles: aggressive, moderate, and conservative. Additionally, it offers a decumulation horizon conditioned by the sex-specific life expectancy of the individual, instead of offering different scenarios for conducting a sensitivity analysis. Lastly, this study was conducted across three socioeconomically distinct countries: the US, Spain, and Japan. The results clearly demonstrate that both sex and nationality significantly influence the selection of the optimal decumulation portfolio composition aimed at exhausting funds by the senior’s demise.
{"title":"The Role of Sex in the Assessment of Return and Downside Risk in Decumulation Financial Planning","authors":"Amaia Jone Betzuen Álvarez, Amancio Betzuen Zalbidegoitia","doi":"10.3390/risks12090142","DOIUrl":"https://doi.org/10.3390/risks12090142","url":null,"abstract":"This paper aims to assess the return and downside risk of a decumulation portfolio established at the retirement age of a senior, with a determined lifetime horizon differentiated by the sex of the citizen. To measure the portfolio’s return and downside risk, two ratios conditioned by seniors’ risk attitude towards portfolio failure are employed: the downside Sortino ratio and the downside risk–return ratio. Unlike other research in the field, this manuscript provides three portfolio compositions catering to different senior investment profiles: aggressive, moderate, and conservative. Additionally, it offers a decumulation horizon conditioned by the sex-specific life expectancy of the individual, instead of offering different scenarios for conducting a sensitivity analysis. Lastly, this study was conducted across three socioeconomically distinct countries: the US, Spain, and Japan. The results clearly demonstrate that both sex and nationality significantly influence the selection of the optimal decumulation portfolio composition aimed at exhausting funds by the senior’s demise.","PeriodicalId":21282,"journal":{"name":"Risks","volume":"1 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2024-09-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142197494","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Charlotte Jamotton, Donatien Hainaut, Thomas Hames
The K-means algorithm and its variants are well-known clustering techniques. In actuarial applications, these partitioning methods can identify clusters of policies with similar attributes. The resulting partitions provide an actuarial framework for creating maps of dominant risks and unsupervised pricing grids. This research article aims to adapt well-established clustering methods to complex insurance datasets containing both categorical and numerical variables. To achieve this, we propose a novel approach based on Burt distance. We begin by reviewing the K-means algorithm to establish the foundation for our Burt distance-based framework. Next, we extend the scope of application of the mini-batch and fuzzy K-means variants to heterogeneous insurance data. Additionally, we adapt spectral clustering, a technique based on graph theory that accommodates non-convex cluster shapes. To mitigate the computational complexity associated with spectral clustering’s O(n3) runtime, we introduce a data reduction method for large-scale datasets using our Burt distance-based approach.
{"title":"Insurance Analytics with Clustering Techniques","authors":"Charlotte Jamotton, Donatien Hainaut, Thomas Hames","doi":"10.3390/risks12090141","DOIUrl":"https://doi.org/10.3390/risks12090141","url":null,"abstract":"The K-means algorithm and its variants are well-known clustering techniques. In actuarial applications, these partitioning methods can identify clusters of policies with similar attributes. The resulting partitions provide an actuarial framework for creating maps of dominant risks and unsupervised pricing grids. This research article aims to adapt well-established clustering methods to complex insurance datasets containing both categorical and numerical variables. To achieve this, we propose a novel approach based on Burt distance. We begin by reviewing the K-means algorithm to establish the foundation for our Burt distance-based framework. Next, we extend the scope of application of the mini-batch and fuzzy K-means variants to heterogeneous insurance data. Additionally, we adapt spectral clustering, a technique based on graph theory that accommodates non-convex cluster shapes. To mitigate the computational complexity associated with spectral clustering’s O(n3) runtime, we introduce a data reduction method for large-scale datasets using our Burt distance-based approach.","PeriodicalId":21282,"journal":{"name":"Risks","volume":"42 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142225149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The current study aims to develop a financial stability model in Iraq; after reviewing the relevant literature and sources related to financial stability and considering Iraq’s social, economic, political, and cultural conditions, a conceptual model and a research questionnaire have been developed. Based on the developed conceptual model, macro variables at the level of the economy, micro variables at the level of companies, the environmental variables of companies, and corporate governance have been selected as model dimensions. Each dimension has several components, including several indicators; 39 indicators were measured through questions in 2024. The research questionnaire was subjected to the opinion of 21 experts with sufficient experimental and academic records on this subject, and by using the Analytic Hierarchy Process (AHP) and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) methods, the results were analyzed, and the final model was extracted. In this model, the scientific method used to analyze the results determines the weight of each dimension, component, and indicator. The results of this research show that the dimensions of corporate governance, the variables of the company environment, micro variables at the company level, and macro variables at the economic level with coefficients of 0.345, 0.251, 0.236, and 0.168, respectively, have the most significant impact on the ranking of the company’s financial stability. So far, research has yet to be conducted to present the financial stability model of Iraqi companies. Therefore, the present research is one of the first studies in this respect, which presents a model both qualitatively (by designing a questionnaire and conceptual model) and quantitatively (through a mathematical model) to measure financial stability that can help the development of science and knowledge in this field.
{"title":"A Financial Stability Model for Iraqi Companies","authors":"Narjis Abdlkareem Ibrahim, Mahdi Salehi, Hussen Amran Naji Al-Refiay, Mahmoud Lari Dashtbayaz","doi":"10.3390/risks12090140","DOIUrl":"https://doi.org/10.3390/risks12090140","url":null,"abstract":"The current study aims to develop a financial stability model in Iraq; after reviewing the relevant literature and sources related to financial stability and considering Iraq’s social, economic, political, and cultural conditions, a conceptual model and a research questionnaire have been developed. Based on the developed conceptual model, macro variables at the level of the economy, micro variables at the level of companies, the environmental variables of companies, and corporate governance have been selected as model dimensions. Each dimension has several components, including several indicators; 39 indicators were measured through questions in 2024. The research questionnaire was subjected to the opinion of 21 experts with sufficient experimental and academic records on this subject, and by using the Analytic Hierarchy Process (AHP) and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) methods, the results were analyzed, and the final model was extracted. In this model, the scientific method used to analyze the results determines the weight of each dimension, component, and indicator. The results of this research show that the dimensions of corporate governance, the variables of the company environment, micro variables at the company level, and macro variables at the economic level with coefficients of 0.345, 0.251, 0.236, and 0.168, respectively, have the most significant impact on the ranking of the company’s financial stability. So far, research has yet to be conducted to present the financial stability model of Iraqi companies. Therefore, the present research is one of the first studies in this respect, which presents a model both qualitatively (by designing a questionnaire and conceptual model) and quantitatively (through a mathematical model) to measure financial stability that can help the development of science and knowledge in this field.","PeriodicalId":21282,"journal":{"name":"Risks","volume":"389 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142197504","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Farhat Iqbal, Dimitrios Koutmos, Eman A. Ahmed, Lulwah M. Al-Essa
The global foreign exchange (FX) market represents a critical and sizeable component of our financial system. It is a market where firms and investors engage in both speculative trading and hedging. Over the years, there has been a growing interest in FX modeling and prediction. Recently, machine learning (ML) and deep learning (DL) techniques have shown promising results in enhancing predictive accuracy. Motivated by the growing size of the FX market, as well as advancements in ML, we propose a novel forecasting framework, the MVO-BiGRU model, which integrates variational mode decomposition (VMD), data augmentation, Optuna-optimized hyperparameters, and bidirectional GRU algorithms for monthly FX rate forecasting. The data augmentation in the Prevention module significantly increases the variety of data combinations, effectively reducing overfitting issues, while the Optuna optimization ensures optimal model configuration for enhanced performance. Our study’s contributions include the development of the MVO-BiGRU model, as well as the insights gained from its application in FX markets. Our findings demonstrate that the MVO-BiGRU model can successfully avoid overfitting and achieve the highest accuracy in out-of-sample forecasting, while outperforming benchmark models across multiple assessment criteria. These findings offer valuable insights for implementing ML and DL models on low-frequency time series data, where artificial data augmentation can be challenging.
全球外汇（FX）市场是我们金融体系中一个重要而庞大的组成部分。在这个市场上，企业和投资者既进行投机交易，也进行套期保值。多年来，人们对外汇建模和预测的兴趣与日俱增。最近，机器学习（ML）和深度学习（DL）技术在提高预测准确性方面取得了可喜的成果。在外汇市场规模不断扩大以及 ML 技术不断进步的推动下，我们提出了一个新颖的预测框架，即 MVO-BiGRU 模型，该模型集成了变模分解（VMD）、数据增强、Optuna 优化超参数和双向 GRU 算法，用于月度外汇汇率预测。预防模块中的数据扩增大大增加了数据组合的多样性，有效地减少了过拟合问题，而 Optuna 优化则确保了模型配置的最优化，从而提高了性能。我们的研究成果包括 MVO-BiGRU 模型的开发，以及将其应用于外汇市场所获得的启示。我们的研究结果表明，MVO-BiGRU 模型可以成功避免过度拟合，并在样本外预测方面达到最高准确度，同时在多个评估标准方面优于基准模型。这些发现为在低频时间序列数据上实施 ML 和 DL 模型提供了有价值的见解，因为在低频时间序列数据上，人工数据增强可能具有挑战性。
{"title":"A Novel Hybrid Deep Learning Method for Accurate Exchange Rate Prediction","authors":"Farhat Iqbal, Dimitrios Koutmos, Eman A. Ahmed, Lulwah M. Al-Essa","doi":"10.3390/risks12090139","DOIUrl":"https://doi.org/10.3390/risks12090139","url":null,"abstract":"The global foreign exchange (FX) market represents a critical and sizeable component of our financial system. It is a market where firms and investors engage in both speculative trading and hedging. Over the years, there has been a growing interest in FX modeling and prediction. Recently, machine learning (ML) and deep learning (DL) techniques have shown promising results in enhancing predictive accuracy. Motivated by the growing size of the FX market, as well as advancements in ML, we propose a novel forecasting framework, the MVO-BiGRU model, which integrates variational mode decomposition (VMD), data augmentation, Optuna-optimized hyperparameters, and bidirectional GRU algorithms for monthly FX rate forecasting. The data augmentation in the Prevention module significantly increases the variety of data combinations, effectively reducing overfitting issues, while the Optuna optimization ensures optimal model configuration for enhanced performance. Our study’s contributions include the development of the MVO-BiGRU model, as well as the insights gained from its application in FX markets. Our findings demonstrate that the MVO-BiGRU model can successfully avoid overfitting and achieve the highest accuracy in out-of-sample forecasting, while outperforming benchmark models across multiple assessment criteria. These findings offer valuable insights for implementing ML and DL models on low-frequency time series data, where artificial data augmentation can be challenging.","PeriodicalId":21282,"journal":{"name":"Risks","volume":"171 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142197493","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Farha Usman, Jennifer S. K. Chan, Udi E. Makov, Yang Wang, Alice X. D. Dong
We leverage telematics data on driving behavior variables to assess driver risk and predict future insurance claims in a case study utilising a representative telematics sample. In the study, we aim to categorise drivers according to their driving habits and establish premiums that accurately reflect their driving risk. To accomplish our goal, we employ the two-stage Poisson model, the Poisson mixture model, and the Zero-Inflated Poisson model to analyse the telematics data. These models are further enhanced by incorporating regularisation techniques such as lasso, adaptive lasso, elastic net, and adaptive elastic net. Our empirical findings demonstrate that the Poisson mixture model with the adaptive lasso regularisation outperforms other models. Based on predicted claim frequencies and drivers’ risk groups, we introduce a novel usage-based experience rating premium pricing method. This method enables more frequent premium updates based on recent driving behaviour, providing instant rewards and incentivising responsible driving practices. Consequently, it helps to alleviate cross-subsidization among risky drivers and improves the accuracy of loss reserving for auto insurance companies.
{"title":"Claim Prediction and Premium Pricing for Telematics Auto Insurance Data Using Poisson Regression with Lasso Regularisation","authors":"Farha Usman, Jennifer S. K. Chan, Udi E. Makov, Yang Wang, Alice X. D. Dong","doi":"10.3390/risks12090137","DOIUrl":"https://doi.org/10.3390/risks12090137","url":null,"abstract":"We leverage telematics data on driving behavior variables to assess driver risk and predict future insurance claims in a case study utilising a representative telematics sample. In the study, we aim to categorise drivers according to their driving habits and establish premiums that accurately reflect their driving risk. To accomplish our goal, we employ the two-stage Poisson model, the Poisson mixture model, and the Zero-Inflated Poisson model to analyse the telematics data. These models are further enhanced by incorporating regularisation techniques such as lasso, adaptive lasso, elastic net, and adaptive elastic net. Our empirical findings demonstrate that the Poisson mixture model with the adaptive lasso regularisation outperforms other models. Based on predicted claim frequencies and drivers’ risk groups, we introduce a novel usage-based experience rating premium pricing method. This method enables more frequent premium updates based on recent driving behaviour, providing instant rewards and incentivising responsible driving practices. Consequently, it helps to alleviate cross-subsidization among risky drivers and improves the accuracy of loss reserving for auto insurance companies.","PeriodicalId":21282,"journal":{"name":"Risks","volume":"29 1","pages":""},"PeriodicalIF":2.2,"publicationDate":"2024-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142197500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：