Pub Date : 2026-01-01Epub Date: 2025-10-24DOI: 10.1016/j.najef.2025.102546
Xiaorui Xue , Shaofang Li , Xiaonan Wang , Tingting Ren
Predicting stock trends is vital in financial systems, providing insights for strategies aimed at generating excess returns. The market’s intrinsically chaotic, nonlinear, and multivariate characteristics hinder the efficacy of traditional deep learning models, especially in recognizing dynamic interdependencies and temporal non-stationarity. This study introduces an innovative hybrid framework (MVMD-NT-TiF) that integrates multivariate signal decomposition, non-stationary sequence modeling, and dual-attention-based feature selection into a cohesive architecture. By concurrently tackling noise, temporal adaptability, and feature redundancy, the approach facilitates precise and resilient forecasting in intricate financial contexts. Empirical findings regarding key stock indices illustrate its enhanced accuracy and universality relative to leading baselines, underscoring its use in real-world scenarios such as quantitative investing, risk management, and trend analysis.
{"title":"Enhancing stock market predictions with multivariate signal decomposition and dynamic feature optimization","authors":"Xiaorui Xue , Shaofang Li , Xiaonan Wang , Tingting Ren","doi":"10.1016/j.najef.2025.102546","DOIUrl":"10.1016/j.najef.2025.102546","url":null,"abstract":"<div><div>Predicting stock trends is vital in financial systems, providing insights for strategies aimed at generating excess returns. The market’s intrinsically chaotic, nonlinear, and multivariate characteristics hinder the efficacy of traditional deep learning models, especially in recognizing dynamic interdependencies and temporal non-stationarity. This study introduces an innovative hybrid framework (MVMD-NT-TiF) that integrates multivariate signal decomposition, non-stationary sequence modeling, and dual-attention-based feature selection into a cohesive architecture. By concurrently tackling noise, temporal adaptability, and feature redundancy, the approach facilitates precise and resilient forecasting in intricate financial contexts. Empirical findings regarding key stock indices illustrate its enhanced accuracy and universality relative to leading baselines, underscoring its use in real-world scenarios such as quantitative investing, risk management, and trend analysis.</div></div>","PeriodicalId":47831,"journal":{"name":"North American Journal of Economics and Finance","volume":"81 ","pages":"Article 102546"},"PeriodicalIF":3.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145415995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-01Epub Date: 2025-12-25DOI: 10.1016/j.najef.2025.102573
Abdulaziz A. Alshamrani , David Rakowski , Salil Sarkar
We examine whether credit ratings reflect the political ideology of the broader top management team rather than that of the CEO alone. Using political donation data for top executives from 1992 to 2017, we show that firms with more conservative executive teams receive higher credit ratings and are more likely to be investment grade. While CEO conservatism is positively associated with ratings, the ideology of non-CEO executives has comparable and often greater explanatory power. In firms where CEO and executive team ideologies diverge, ratings align more closely with the ideology of non-CEO managers. Additional analyses exploiting CEO turnover, firm fixed effects, and matched samples largely rule out alternative explanations based on firm culture or selection. Overall, the results suggest that credit rating agencies condition on the risk preferences of senior leadership teams rather than solely on CEOs.
{"title":"Credit ratings and top executives’ political ideology","authors":"Abdulaziz A. Alshamrani , David Rakowski , Salil Sarkar","doi":"10.1016/j.najef.2025.102573","DOIUrl":"10.1016/j.najef.2025.102573","url":null,"abstract":"<div><div>We examine whether credit ratings reflect the political ideology of the broader top management team rather than that of the CEO alone. Using political donation data for top executives from 1992 to 2017, we show that firms with more conservative executive teams receive higher credit ratings and are more likely to be investment grade. While CEO conservatism is positively associated with ratings, the ideology of non-CEO executives has comparable and often greater explanatory power. In firms where CEO and executive team ideologies diverge, ratings align more closely with the ideology of non-CEO managers. Additional analyses exploiting CEO turnover, firm fixed effects, and matched samples largely rule out alternative explanations based on firm culture or selection. Overall, the results suggest that credit rating agencies condition on the risk preferences of senior leadership teams rather than solely on CEOs.</div></div>","PeriodicalId":47831,"journal":{"name":"North American Journal of Economics and Finance","volume":"82 ","pages":"Article 102573"},"PeriodicalIF":3.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145884168","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study examines the impact of full-fledged inflation targeting (IT) regime adoption on stock market liquidity in emerging markets, addressing a critical yet underexplored dimension of monetary policy’s financial market effects. Understanding how IT influences financial market stability is crucial, particularly for emerging economies where liquidity constraints exacerbate financial fragility. Analyzing 35 emerging countries, of which 15 are inflation targeters, over the period 1990–2023, we employ Difference-in-Differences and Doubly Robust methods to assess the influence of IT on stock market liquidity, utilizing several proxies for liquidity. Our findings indicate that IT has a significant impact on liquidity, particularly during crises such as the Global Financial Crisis (GFC) and the COVID-19 pandemic. The positive impact of IT adoption on stock market liquidity emerges after a three-year delay and becomes statistically significant once key economic and financial variables are controlled for. Robust across multiple checks, our study extends prior literature by offering a broad multi-country perspective, isolating IT’s unique role, and using advanced methods to address selection bias. It highlights IT as a key policy tool for financial stability, equipping central bankers with strategies to prevent liquidity dry-ups and strengthen economic resilience in turbulent times.
{"title":"Inflation targeting and stock market liquidity: a difference-in-difference and doubly robust analysis of emerging markets","authors":"Ichrak Dridi , Mohamed Malek Belhoula , Adel Boughrara","doi":"10.1016/j.najef.2025.102580","DOIUrl":"10.1016/j.najef.2025.102580","url":null,"abstract":"<div><div>This study examines the impact of full-fledged inflation targeting (IT) regime adoption on stock market liquidity in emerging markets, addressing a critical yet underexplored dimension of monetary policy’s financial market effects. Understanding how IT influences financial market stability is crucial, particularly for emerging economies where liquidity constraints exacerbate financial fragility. Analyzing 35 emerging countries, of which 15 are inflation targeters, over the period 1990–2023, we employ Difference-in-Differences and Doubly Robust methods to assess the influence of IT on stock market liquidity, utilizing several proxies for liquidity. Our findings indicate that IT has a significant impact on liquidity, particularly during crises such as the Global Financial Crisis (GFC) and the COVID-19 pandemic. The positive impact of IT adoption on stock market liquidity emerges after a three-year delay and becomes statistically significant once key economic and financial variables are controlled for. Robust across multiple checks, our study extends prior literature by offering a broad multi-country perspective, isolating IT’s unique role, and using advanced methods to address selection bias. It highlights IT as a key policy tool for financial stability, equipping central bankers with strategies to prevent liquidity dry-ups and strengthen economic resilience in turbulent times.</div></div>","PeriodicalId":47831,"journal":{"name":"North American Journal of Economics and Finance","volume":"82 ","pages":"Article 102580"},"PeriodicalIF":3.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145884266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-01Epub Date: 2025-11-07DOI: 10.1016/j.najef.2025.102552
Halilibrahim Gökgöz , Aamir Aijaz Syed , Catalin Gheorghe , Ahmed Jeribi
This study explores the quantile–frequency linkages between U.S. sectoral stock indices and four macro-financial indicators: market volatility (VIX), geopolitical risk (GPR), inflation expectations (T5YIE), and the yield curve (T10Y3M), using the Quantile Coherence (QC) framework. The method captures nonlinear and asymmetric interactions across quantiles and horizons. The dataset covers daily observations from January 2016 to July 2025, encompassing episodes such as Brexit, the China–U.S. trade war, and recent geopolitical conflicts. Results reveal strong sectoral heterogeneity: dependence on VIX is predominantly negative in the short term during bullish phases, with reversals at longer horizons; the influence of GPR is asymmetric and forward-looking; inflation expectations, captured by T5YIE, show a stable long-run positive association with all sectors; while the yield curve (T10Y3M) generates systematic long-term co-movements, with leadership alternating between financial indicators and sector indices across regimes. These findings demonstrate uneven sectoral responses to macro-financial drivers and provide guidance for risk management and portfolio design in uncertain environments.
{"title":"Quantile-frequency dependence between U.S. sector stock indices and macro-financial indicators: A quantile coherence approach","authors":"Halilibrahim Gökgöz , Aamir Aijaz Syed , Catalin Gheorghe , Ahmed Jeribi","doi":"10.1016/j.najef.2025.102552","DOIUrl":"10.1016/j.najef.2025.102552","url":null,"abstract":"<div><div>This study explores the quantile–frequency linkages between U.S. sectoral stock indices and four macro-financial indicators: market volatility (VIX), geopolitical risk (GPR), inflation expectations (T5YIE), and the yield curve (T10Y3M), using the Quantile Coherence (QC) framework. The method captures nonlinear and asymmetric interactions across quantiles and horizons. The dataset covers daily observations from January 2016 to July 2025, encompassing episodes such as Brexit, the China–U.S. trade war, and recent geopolitical conflicts. Results reveal strong sectoral heterogeneity: dependence on VIX is predominantly negative in the short term during bullish phases, with reversals at longer horizons; the influence of GPR is asymmetric and forward-looking; inflation expectations, captured by T5YIE, show a stable long-run positive association with all sectors; while the yield curve (T10Y3M) generates systematic long-term co-movements, with leadership alternating between financial indicators and sector indices across regimes. These findings demonstrate uneven sectoral responses to macro-financial drivers and provide guidance for risk management and portfolio design in uncertain environments.</div></div>","PeriodicalId":47831,"journal":{"name":"North American Journal of Economics and Finance","volume":"81 ","pages":"Article 102552"},"PeriodicalIF":3.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145519582","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper investigates the complex, nonlinear forces behind price movements in Nigeria by applying quantile econometric techniques. Using monthly data from December 2012 to August 2024, the analysis applies Elastic Net Regression for variable selection and employs Quantile-on-Quantile Kernel Regularized Least Squares (QQKRLS) alongside Quantile-on-Quantile Granger Causality (QQGC) tests. The results show that while money supply consistently drives inflation, the effects of other variables are regime-dependent; for instance, private sector credit fuels inflation in moderate-to-high periods, while bank reserves can dampen it in moderate ones. Furthermore, the analysis confirms a directional causality from these variables of interest to inflation, with the strength of the relationship varying significantly across quantiles. The results reveal that uniform policies are inadequate. Policymakers should, therefore, adopt quantile-specific and context-sensitive fiscal and monetary strategies to ensure durable price stability in Nigeria.
{"title":"Asymmetric drivers of inflation: new evidence from machine learning and quantile method","authors":"Kingsley Imandojemu , Adetutu Omotola Habib , Omozele Lynda Showunmi , Loveth Oribhabor Agboola","doi":"10.1016/j.najef.2025.102551","DOIUrl":"10.1016/j.najef.2025.102551","url":null,"abstract":"<div><div>This paper investigates the complex, nonlinear forces behind price movements in Nigeria by applying quantile econometric techniques. Using monthly data from December 2012 to August 2024, the analysis applies Elastic Net Regression for variable selection and employs Quantile-on-Quantile Kernel Regularized Least Squares (QQKRLS) alongside Quantile-on-Quantile Granger Causality (QQGC) tests. The results show that while money supply consistently drives inflation, the effects of other variables are regime-dependent; for instance, private sector credit fuels inflation in moderate-to-high periods, while bank reserves can dampen it in moderate ones. Furthermore, the analysis confirms a directional causality from these variables of interest to inflation, with the strength of the relationship varying significantly across quantiles. The results reveal that uniform policies are inadequate. Policymakers should, therefore, adopt quantile-specific and context-sensitive fiscal and monetary strategies to ensure durable price stability in Nigeria.</div></div>","PeriodicalId":47831,"journal":{"name":"North American Journal of Economics and Finance","volume":"81 ","pages":"Article 102551"},"PeriodicalIF":3.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145519584","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-01Epub Date: 2025-09-02DOI: 10.1016/j.najef.2025.102535
Turker Acikgoz
This study develops a novel methodological framework, the dynamic -dependent cross-correlation (DQCC) test, to evaluate the diversification, hedging, and safe-haven properties of financial assets under conditions of fractality and nonlinear dependence. Traditional econometric approaches often fail to capture three critical aspects of financial markets: time-varying structures, heterogeneous investment horizons, and fluctuation-dependent dynamics. To address these limitations, the proposed framework integrates fractal theory and econophysics-based cross-correlation measures, enabling a simultaneous analysis of time, scale, and moment dimensions. Empirically, the model is applied to the nexus between green bonds and equity markets. Methodologically, both quantile-based and event-based specifications are employed to assess asset behavior under normal conditions and during systemic crises, including the COVID-19 pandemic, the Russia–Ukraine war, and the Hamas–Israel conflict. The results reveal strong evidence of multifractality and nonlinear dynamics across all return series, rejecting market efficiency. Green bonds are found to provide persistent diversification benefits against both advanced and emerging market equities under ordinary conditions, while their safe-haven properties emerge during extreme downturns, particularly at lower quantiles and longer horizons. Event-based results confirm the safe-haven role of green bonds during COVID-19, with more mixed evidence during geopolitical crises. No robust hedging capacity is observed. The study contributes to the literature by introducing a comprehensive testing framework for investment classification under fractal dynamics and by extending the understanding of the green bond–equity nexus across advanced and emerging markets. The findings carry significant implications for portfolio construction, risk management, and sustainable finance, and the model can be applied to other asset classes to evaluate their potential roles as diversifiers, hedges, or safe-haven.
{"title":"Dynamic q-dependent cross-correlation test for investment classification and its application on green finance","authors":"Turker Acikgoz","doi":"10.1016/j.najef.2025.102535","DOIUrl":"10.1016/j.najef.2025.102535","url":null,"abstract":"<div><div>This study develops a novel methodological framework, the dynamic <span><math><mi>q</mi></math></span>-dependent cross-correlation (DQCC) test, to evaluate the diversification, hedging, and safe-haven properties of financial assets under conditions of fractality and nonlinear dependence. Traditional econometric approaches often fail to capture three critical aspects of financial markets: time-varying structures, heterogeneous investment horizons, and fluctuation-dependent dynamics. To address these limitations, the proposed framework integrates fractal theory and econophysics-based cross-correlation measures, enabling a simultaneous analysis of time, scale, and moment dimensions. Empirically, the model is applied to the nexus between green bonds and equity markets. Methodologically, both quantile-based and event-based specifications are employed to assess asset behavior under normal conditions and during systemic crises, including the COVID-19 pandemic, the Russia–Ukraine war, and the Hamas–Israel conflict. The results reveal strong evidence of multifractality and nonlinear dynamics across all return series, rejecting market efficiency. Green bonds are found to provide persistent diversification benefits against both advanced and emerging market equities under ordinary conditions, while their safe-haven properties emerge during extreme downturns, particularly at lower quantiles and longer horizons. Event-based results confirm the safe-haven role of green bonds during COVID-19, with more mixed evidence during geopolitical crises. No robust hedging capacity is observed. The study contributes to the literature by introducing a comprehensive testing framework for investment classification under fractal dynamics and by extending the understanding of the green bond–equity nexus across advanced and emerging markets. The findings carry significant implications for portfolio construction, risk management, and sustainable finance, and the model can be applied to other asset classes to evaluate their potential roles as diversifiers, hedges, or safe-haven.</div></div>","PeriodicalId":47831,"journal":{"name":"North American Journal of Economics and Finance","volume":"81 ","pages":"Article 102535"},"PeriodicalIF":3.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145004430","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-01Epub Date: 2025-09-13DOI: 10.1016/j.najef.2025.102538
Rana Muhammad Nasir , Feng He , Mehrad Asadi , David Roubaud
This study investigates the extreme connectedness and spillover transmission between cryptocurrencies, digital assets, green bonds, traditional and green energy markets against different uncertainties from July 2, 2018, to February 3, 2023. First, we employ Quantile VAR to unveil extreme connectedness among markets. Further, Baruník and Křehlík (BK) framework is used to understand time frequency spillover transmission across our chosen markets. Our results indicate that spillover magnitude under bullish market conditions is higher than normal and bearish market conditions. In addition, the equity market volatility, geopolitical risk, Twitter-based economic risk, and oil markets are the major receiver of spillover across all market conditions. In contrast, NFTs and Defis are the significant transmitters of spillover across all quantiles. Similarly, natural gas and green bonds act as spillover transmitters under extreme quantiles. While, green energy and cryptocurrencies are net transmitters in only bearish market conditions. Based on these findings, this study proposed several important implications for investors, financial markets participants, portfolio managers and market regulators in terms of diversifying their risk and design effective market regulation policies.
{"title":"Spillover and return connectedness between uncertainties, digital assets, green bond, green and traditional energy markets: Evidence from quantile VAR","authors":"Rana Muhammad Nasir , Feng He , Mehrad Asadi , David Roubaud","doi":"10.1016/j.najef.2025.102538","DOIUrl":"10.1016/j.najef.2025.102538","url":null,"abstract":"<div><div>This study investigates the extreme connectedness and spillover transmission between cryptocurrencies, digital assets, green bonds, traditional and green energy markets against different uncertainties from July 2, 2018, to February 3, 2023. First, we employ Quantile VAR to unveil extreme connectedness among markets. Further, Baruník and Křehlík (BK) framework is used to understand time frequency spillover transmission across our chosen markets. Our results indicate that spillover magnitude under bullish market conditions is higher than normal and bearish market conditions. In addition, the equity market volatility, geopolitical risk, Twitter-based economic risk, and oil markets are the major receiver of spillover across all market conditions. In contrast, NFTs and Defis are the significant transmitters of spillover across all quantiles. Similarly, natural gas and green bonds act as spillover transmitters under extreme quantiles. While, green energy and cryptocurrencies are net transmitters in only bearish market conditions. Based on these findings, this study proposed several important implications for investors, financial markets participants, portfolio managers and market regulators in terms of diversifying their risk and design effective market regulation policies.</div></div>","PeriodicalId":47831,"journal":{"name":"North American Journal of Economics and Finance","volume":"81 ","pages":"Article 102538"},"PeriodicalIF":3.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145095580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-01Epub Date: 2025-12-17DOI: 10.1016/j.najef.2025.102570
László Kamocsai , Mihály Ormos
We propose a new variant of the heterogeneous autoregressive model, the pseudo leverage HAR model, which exploits the well-known leverage effect to improve forecasting performance. Built on the fact there is an interconnectedness among commodities we employ a common leverage factor in forecasting exercises which is derived by principal component regression. Including this common leverage variable in HAR framework leads to significant improvements in both in-sample estimates and out-of-sample forecasts, suggesting that the factor structure is a valid assumption not just for return and volatility, but for volatility asymmetry too. The robustness tests confirm the usefulness of the common leverage factor, since the model incorporating this variable consistently remains in the model confidence set, implying that the model’s performance independent of the choice of the leverage structure or volatility proxy. Moreover, the portfolio evaluation exercise and the cumulative sum of forecast errors revealed the incremental gain of using the common leverage variable at all forecasting horizons, especially in turbulent periods.
{"title":"Modeling and forecasting commodity price volatility using a common leverage factor","authors":"László Kamocsai , Mihály Ormos","doi":"10.1016/j.najef.2025.102570","DOIUrl":"10.1016/j.najef.2025.102570","url":null,"abstract":"<div><div>We propose a new variant of the heterogeneous autoregressive model, the pseudo leverage HAR model, which exploits the well-known leverage effect to improve forecasting performance. Built on the fact there is an interconnectedness among commodities we employ a common leverage factor in forecasting exercises which is derived by principal component regression. Including this common leverage variable in HAR framework leads to significant improvements in both in-sample estimates and out-of-sample forecasts, suggesting that the factor structure is a valid assumption not just for return and volatility, but for volatility asymmetry too. The robustness tests confirm the usefulness of the common leverage factor, since the model incorporating this variable consistently remains in the model confidence set, implying that the model’s performance independent of the choice of the leverage structure or volatility proxy. Moreover, the portfolio evaluation exercise and the cumulative sum of forecast errors revealed the incremental gain of using the common leverage variable at all forecasting horizons, especially in turbulent periods.</div></div>","PeriodicalId":47831,"journal":{"name":"North American Journal of Economics and Finance","volume":"82 ","pages":"Article 102570"},"PeriodicalIF":3.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145840950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-01Epub Date: 2025-09-26DOI: 10.1016/j.najef.2025.102543
Barbara Będowska-Sójka , Piotr Wójcik , Daniel Traian Pele
The cryptocurrency market harbours a hidden risk: assets that silently disappear from trading, leaving investors stranded. These ‘zombie’ cryptocurrencies technically exist but become temporarily untradable on exchanges, ranging from weeks to permanent delisting. This study predicts which cryptocurrencies are at risk of becoming zombies using predictors derived from return statistics, trading volume, market capitalisation, and asset-specific features. Our sample includes cryptocurrencies listed for at least 210 days between January 2015 and December 2022. We employ various machine learning algorithms and novel explainable AI (XAI) tools, including permutation-based feature importance and partial dependence plots (PDPs), to identify and analyse key factors influencing zombification risk. Our machine learning models achieve 84% out-of-time balanced accuracy in predicting whether a cryptocurrency will become a zombie within the next 28 days. Tree-based approaches, particularly random forests, significantly outperform traditional econometric methods. Trading volumes and past returns emerge as the most influential predictors.
{"title":"Early warning systems for cryptocurrency markets: Predicting ‘zombie’ assets using machine learning","authors":"Barbara Będowska-Sójka , Piotr Wójcik , Daniel Traian Pele","doi":"10.1016/j.najef.2025.102543","DOIUrl":"10.1016/j.najef.2025.102543","url":null,"abstract":"<div><div>The cryptocurrency market harbours a hidden risk: assets that silently disappear from trading, leaving investors stranded. These ‘zombie’ cryptocurrencies technically exist but become temporarily untradable on exchanges, ranging from weeks to permanent delisting. This study predicts which cryptocurrencies are at risk of becoming zombies using predictors derived from return statistics, trading volume, market capitalisation, and asset-specific features. Our sample includes cryptocurrencies listed for at least 210 days between January 2015 and December 2022. We employ various machine learning algorithms and novel explainable AI (XAI) tools, including permutation-based feature importance and partial dependence plots (PDPs), to identify and analyse key factors influencing zombification risk. Our machine learning models achieve 84% out-of-time balanced accuracy in predicting whether a cryptocurrency will become a zombie within the next 28 days. Tree-based approaches, particularly random forests, significantly outperform traditional econometric methods. Trading volumes and past returns emerge as the most influential predictors.</div></div>","PeriodicalId":47831,"journal":{"name":"North American Journal of Economics and Finance","volume":"81 ","pages":"Article 102543"},"PeriodicalIF":3.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145266567","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-01Epub Date: 2025-08-21DOI: 10.1016/j.najef.2025.102527
Wan-Lin Yan , Adrian (Wai Kong) Cheung , Jiawei Yuan
Cryptocurrency market has a significant impact on energy markets due to the intensive usage of energy in the mining process. This study analyzes the impact of green and nongreen cryptocurrency markets on traditional and clean energy markets by using a TVP-VAR connectedness approach. Moreover, the higher-order moment connectedness is investigated. The empirical results show that there is a time varying connectedness between cryptocurrency and energy markets and extreme events can intensify the connectedness. The transmission of volatility spillover and return asymmetry is more obvious between nongreen cryptocurrency and energy markets, while the probability of occurring extreme events is higher between green cryptocurrency and energy markets. Energy markets act as the net shock receiver, while cryptocurrencies are mainly the net shock transmitters in each order moment connectedness. The impact of geopolitical acts is mostly negative and the moderating impact of geopolitical threats on skewness is different between green and nongreen cryptocurrencies. This study significantly contributes to a deeper understanding of the impacts of green and non-green cryptocurrencies on energy markets, which has significant implications for investors and policymakers.
{"title":"The impact of green cryptocurrency and nongreen cryptocurrency on energy markets: Evidence from geopolitical risk and higher-order moment connectedness","authors":"Wan-Lin Yan , Adrian (Wai Kong) Cheung , Jiawei Yuan","doi":"10.1016/j.najef.2025.102527","DOIUrl":"10.1016/j.najef.2025.102527","url":null,"abstract":"<div><div>Cryptocurrency market has a significant impact on energy markets due to the intensive usage of energy in the mining process. This study analyzes the impact of green and nongreen cryptocurrency markets on traditional and clean energy markets by using a TVP-VAR connectedness approach. Moreover, the higher-order moment connectedness is investigated. The empirical results show that there is a time varying connectedness between cryptocurrency and energy markets and extreme events can intensify the connectedness. The transmission of volatility spillover and return asymmetry is more obvious between nongreen cryptocurrency and energy markets, while the probability of occurring extreme events is higher between green cryptocurrency and energy markets. Energy markets act as the net shock receiver, while cryptocurrencies are mainly the net shock transmitters in each order moment connectedness. The impact of geopolitical acts is mostly negative and the moderating impact of geopolitical threats on skewness is different between green and nongreen cryptocurrencies. This study significantly contributes to a deeper understanding of the impacts of green and non-green cryptocurrencies on energy markets, which has significant implications for investors and policymakers.</div></div>","PeriodicalId":47831,"journal":{"name":"North American Journal of Economics and Finance","volume":"81 ","pages":"Article 102527"},"PeriodicalIF":3.9,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144893666","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号