{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T23:23:02Z","timestamp":1773962582546,"version":"3.50.1"},"reference-count":58,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T00:00:00Z","timestamp":1758153600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec><jats:title>Purpose<\/jats:title><jats:p>Global fund managers, in their effort toward risk diversification and generating higher returns, design portfolios that consist of financial assets of various countries. In the process, they expose their investors not only to the fundamentals of the assets but also to transnational volatility, macroeconomic shocks of different countries, and exchange rate fluctuations. These factors make forecasting returns from such global funds quite difficult and, at the same time, challenging. To aid global fund managers and investors, this study presents a forecasting framework for predicting returns from Goldman Sachs BRICs Nifty 50 Developed Markets Index (BRICS NIFTY 50), which is a traded and listed financial asset. It is a global portfolio, which not only exposes investors to the fundamentals of different companies but also to country risk.<\/jats:p><\/jats:sec><jats:sec><jats:title>Design, methodology, and approach<\/jats:title><jats:p>Gradient boosting regression (GBR) and SHAP-based XAI are used to identify the top significant country-specific explanatory variables. Subsequently, with the selected variables, GBR, CatBoost, Light Gradient Boosting Machine (LGBM), Extreme Gradient Boosting (XGBoost), Random Forest (RF), and Extra Tree Regressor (ETR) are applied for forecasting returns from BRICS NIFTY 50. Along with standard evaluation tools, the S.A.F.E AI framework is used for measuring predictive accuracy, sustainability, and contribution of each predictor. To evaluate the relative efficacy of the six predictive models, the underlying research resorts to a multi-criteria decision-making (MCDM) framework.<\/jats:p><\/jats:sec><jats:sec><jats:title>Findings<\/jats:title><jats:p>We find that country-specific market volatility, industrial performance, financial sector development, and exchange rate fluctuations explain global returns significantly. Furthermore, the exercise also reveals that explanatory factors specific to India, China, and Brazil emerge to be relatively important.<\/jats:p><\/jats:sec><jats:sec><jats:title>Research limitations and implications<\/jats:title><jats:p>The study focuses on a single index. Future work will extend it to other indices and global funds.<\/jats:p><\/jats:sec><jats:sec><jats:title>Practical implications<\/jats:title><jats:p>The proposed methodology will be of practical use to global fund managers and investors. Policymakers may find it useful for identifying factors that make foreign direct investment and portfolio investment attractive.<\/jats:p><\/jats:sec><jats:sec><jats:title>Originality and value<\/jats:title><jats:p>Development of a two-step forecasting framework, identifying effects of country-specific explanatory variables, and applying different evaluation criteria to measure predictive efficiency underscore the novelty of the work.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2025.1668700","type":"journal-article","created":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T05:30:25Z","timestamp":1758173425000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Predicting BRICS NIFTY50 returns using XAI and S.A.F.E AI lens"],"prefix":"10.3389","volume":"8","author":[{"given":"Indranil","family":"Ghosh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tamal","family":"Datta Chaudhuri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Golnoosh","family":"Babaei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paolo","family":"Giudici","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emanuela","family":"Raffinetti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,9,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1504963","DOI":"10.3389\/frai.2024.1504963","article-title":"Segmenting female students' perceptions about Fintech using Explainable AI","volume":"7","author":"Adam","year":"2024","journal-title":"Front. Artif. Intell."},{"key":"B2","doi-asserted-by":"publisher","first-page":"2022","DOI":"10.1016\/j.physa.2022.127017","article-title":"NetVIX - a network volatility index of financial markets","volume":"194","author":"Ahelegbey","year":"2022","journal-title":"Phys. A: Stat. Mech. Applic."},{"key":"B3","doi-asserted-by":"publisher","first-page":"281","DOI":"10.35716\/IJED\/21242","article-title":"Measuring economic uncertainty in Syria: an approach to the Stochastic Volatility model","volume":"18","author":"Alakkari","year":"2022","journal-title":"Indian J. Econ. Dev."},{"key":"B4","doi-asserted-by":"publisher","first-page":"48","DOI":"10.58496\/MJBD\/2024\/005","article-title":"MLP and RBF algorithms in finance: predicting and classifying stock prices amidst economic policy uncertainty","volume":"2024","author":"Ali","year":"2024","journal-title":"Mesopot. J. Big Data"},{"key":"B5","doi-asserted-by":"publisher","first-page":"101103","DOI":"10.1016\/j.gfj.2025.101103","article-title":"Intraday impact of macroeconomic and COVID-19 news on Latin American stock indexes","volume":"65","author":"Ayadi","year":"2025","journal-title":"Glob. Fin. J."},{"key":"B6","unstructured":"Azevedo\n              D.\n            \n            \n              Bakliwal\n              S.\n            \n            \n              Chen\n              C.\n            \n            \n              Gilbert\n              M.\n            \n            \n              Koch-Weser\n              I.\n            \n            \n              Lang\n              N.\n            \n          \n          An Evolving BRICS and the Shifting World Order\n          \n          2024"},{"key":"B7","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1007\/s10260-025-00796-y","article-title":"A statistical package for safe artificial intelligence","volume":"34","author":"Babaei","year":"2025","journal-title":"Stat. Methods Applic"},{"key":"B8","doi-asserted-by":"publisher","first-page":"106126","DOI":"10.1016\/j.jeconbus.2023.106126","article-title":"Explainable FinTech lending","volume":"126","author":"Babaei","year":"2023","journal-title":"J. Econ. Business"},{"key":"B9","doi-asserted-by":"publisher","first-page":"125239","DOI":"10.1016\/j.eswa.2024.125239","article-title":"A rank graduation box for SAFE AI","volume":"259","author":"Babaei","year":"2025","journal-title":"Expert Syst. Applic."},{"key":"B10","doi-asserted-by":"publisher","first-page":"100058","DOI":"10.1016\/j.jclimf.2024.100058","article-title":"How important are climate change risks for predicting clean energy stock prices? Evidence from machine learning predictive modeling and interpretation","volume":"10","author":"Basher","year":"2025","journal-title":"J. Clim. Fin."},{"key":"B11","doi-asserted-by":"publisher","first-page":"100250","DOI":"10.1016\/j.sftr.2024.100250","article-title":"Morocco's green shield: ESG stock performance under global climate, economic, geopolitical and oil uncertainties","volume":"8","author":"Belcaid","year":"2024","journal-title":"Sust. Fut."},{"key":"B12","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"B13","doi-asserted-by":"publisher","first-page":"1578190","DOI":"10.3389\/frai.2025.1578190","article-title":"Explainable machine learning to predict the cost of capital","volume":"8","author":"Bussmann","year":"2025","journal-title":"Front. Artif. Intell."},{"key":"B14","doi-asserted-by":"publisher","first-page":"104218","DOI":"10.1016\/j.irfa.2025.104218","article-title":"Stock market volatility and oil shocks: a study of G7 economies","volume":"103","author":"Cadena-Silva","year":"2025","journal-title":"Int. Rev. Fin. Anal."},{"key":"B15","doi-asserted-by":"publisher","first-page":"103875","DOI":"10.1016\/j.resourpol.2023.103875","article-title":"Crude oil price shocks, volatility spillovers, and global systemic financial risk transmission mechanisms: evidence from the stock and foreign exchange markets","volume":"85","author":"Chen","year":"2023","journal-title":"Resour. Policy"},{"key":"B16","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1145\/2939672.2939785","article-title":"\u201cXgboost: a scalable tree boosting system,\u201d","volume-title":"Proceedings of the 22nd acm sigkdd International Conference on Knowledge Discovery and Data Mining","author":"Chen","year":"2016"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1519805","DOI":"10.3389\/frai.2025.1519805","article-title":"Predicting the Bitcoin's price using AI","volume":"8","author":"Cohen","year":"2025","journal-title":"Front. Artif. Intell."},{"key":"B18","unstructured":"\u201cCatBoost: gradient boosting with categorical features support,\u201d\n          \n          \n            \n              Dorogush\n              A. V.\n            \n            \n              Ershov\n              V.\n            \n            \n              Gulin\n              A.\n            \n          \n          Long Beach, CA\n          Workshop on ML Systems at NIPS 2017\n          \n          2017"},{"key":"B19","doi-asserted-by":"publisher","first-page":"101342","DOI":"10.1016\/j.jrras.2025.101342","article-title":"Determinants of bilateral trade between Egypt and BRICS: gravity model with traditional econometrics and machine learning algorithms","volume":"18","author":"El-Aal","year":"2025","journal-title":"J. Radiat. Res. Appl. Sci."},{"key":"B20","doi-asserted-by":"publisher","first-page":"112359","DOI":"10.1016\/j.asoc.2024.112359","article-title":"Machine learning techniques via ensemble approaches in stock exchange index prediction: systematic review and bibliometric analysis","volume":"167","author":"Ferro","year":"2024","journal-title":"Appl. Soft Comput."},{"key":"B21","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","article-title":"Extremely randomized trees","volume":"63","author":"Geurts","year":"2006","journal-title":"Mach. Learn."},{"key":"B22","doi-asserted-by":"publisher","first-page":"103889","DOI":"10.1016\/j.irfa.2024.103889","article-title":"ESG stock markets and clean energy prices prediction: insights from advanced machine learning","volume":"97","author":"Ghallabi","year":"2024","journal-title":"Int. Rev. Fin. Anal."},{"key":"B23","doi-asserted-by":"publisher","first-page":"118391","DOI":"10.1016\/j.eswa.2022.118391","article-title":"Integrating Navier-Stokes equation and neoteric iForest-BorutaShap-Facebook's prophet framework for stock market prediction: an application in Indian context","volume":"210","author":"Ghosh","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"B24","doi-asserted-by":"publisher","first-page":"121757","DOI":"10.1016\/j.techfore.2022.121757","article-title":"A hybrid approach to forecasting futures prices with simultaneous consideration of optimality in ensemble feature selection and advanced artificial intelligence","volume":"181","author":"Ghosh","year":"2022","journal-title":"Technol. Forecast. Soc. Change"},{"key":"B25","doi-asserted-by":"publisher","first-page":"103686","DOI":"10.1016\/j.tre.2024.103686","article-title":"Maritime Fuel Price Prediction of European Ports using Least Square Boosting and Facebook Prophet: Additional Insights from Explainable Artificial Intelligence","volume":"189","author":"Ghosh","year":"2024","journal-title":"Transportation Research Part E Logistics and Transportation Review"},{"key":"B26","doi-asserted-by":"publisher","first-page":"130176","DOI":"10.1016\/j.physa.2024.130176","article-title":"Explainable Artificial Intelligence methods for financial time series","volume":"655","author":"Giudici","year":"2024","journal-title":"Phys. A Stat. Mech. Applic."},{"key":"B27","doi-asserted-by":"publisher","first-page":"127287","DOI":"10.1016\/j.eswa.2025.127287","article-title":"A hybrid optimized deep learning model via the Golden jackal Optimizer for accurate stock price forecasting","volume":"78","author":"Gkonis","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"B28","doi-asserted-by":"publisher","first-page":"e42393","DOI":"10.1016\/j.heliyon.2025.e42393","article-title":"GA-Attention-Fuzzy-Stock-Net: an optimized neuro-fuzzy system for stock market price prediction with genetic algorithm and attention mechanism","volume":"11","author":"G\u00fclmez","year":"2025","journal-title":"Heliyon"},{"key":"B29","doi-asserted-by":"publisher","first-page":"104332","DOI":"10.1016\/j.resourpol.2023.104332","article-title":"A new answer to the old question of the environmental Kuznets Curve (EKC). Does it work for BRICS countries?","volume":"87","author":"Hasan","year":"2023","journal-title":"Resour. Policy"},{"key":"B30","doi-asserted-by":"publisher","first-page":"102885","DOI":"10.1016\/j.ribaf.2025.102885","article-title":"Higher-order moment and cross-moment spillovers among MENA stock markets: insights from geopolitical risks and global fear","volume":"77","author":"Helmi","year":"2025","journal-title":"Res. Int. Business Fin."},{"key":"B31","article-title":"\u201cMultiple attribute decision making,\u201d","volume-title":"Lecture Notes in Economics and Mathematical Systems","author":"Hwang","year":"1981"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1608365","DOI":"10.3389\/frai.2025.1608365","article-title":"Large Language models in equity markets: applications, techniques, and insight","volume":"8","author":"Jadhav","year":"2025","journal-title":"Front. Artif. Intell."},{"key":"B33","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1007\/s10479-021-04000-8","article-title":"A differential evolution-based regression framework for forecasting Bitcoin price","volume":"306","author":"Jana","year":"2021","journal-title":"Ann. Oper. Res."},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1007\/s10614-025-11016-w","article-title":"Enhanced bankruptcy prediction model based on network analysis and explainable machine learning","author":"Kadkhoda","year":"2025","journal-title":"Comput. Econ"},{"key":"B35","first-page":"10061","article-title":"\u201cThe unholy trinity of financial contagion,\u201d","volume-title":"NBER Working Paper Series, Working Paper","author":"Kaminsky","year":"2003"},{"key":"B36","doi-asserted-by":"publisher","first-page":"3149","DOI":"10.5555\/3294996.3295074","article-title":"LightGBM: a highly efficient gradient boosting decision tree","volume":"30","author":"Ke","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B37","doi-asserted-by":"publisher","first-page":"525","DOI":"10.3390\/sym13040525","article-title":"Determination of objective weights using a new method based on the removal effects of criteria (MEREC)","volume":"13","author":"Keshavarz-Ghorabaee","year":"2021","journal-title":"Symmetry"},{"key":"B38","doi-asserted-by":"publisher","first-page":"101002","DOI":"10.1016\/j.ememar.2023.101002","article-title":"Spillovers and connectedness among BRICS stock markets, cryptocurrencies, and uncertainty: evidence from the quantile vector autoregression network","volume":"54","author":"Khalfaoui","year":"2023","journal-title":"Emerg. Markets Rev."},{"key":"B39","doi-asserted-by":"publisher","first-page":"100250","DOI":"10.1016\/j.prime.2023.100250","article-title":"Perspective of renewable energy in the BRICS country","volume":"5","author":"Khare","year":"2023","journal-title":"e-Prime Adv. Electr. Eng. Electr. Energy"},{"key":"B40","doi-asserted-by":"publisher","first-page":"1559900","DOI":"10.3389\/frai.2025.1559900","article-title":"Does business news sentiment matter in the energy stock market? Adopting sentiment analysis for short-term stock market prediction in the energy industry","volume":"8","author":"Lee","year":"2025","journal-title":"Front. Artif. Intell."},{"key":"B41","doi-asserted-by":"publisher","first-page":"1283741","DOI":"10.3389\/frai.2023.1283741","article-title":"Application of hybrid fuzzy interval-based machine learning models on financial time series \u2014 a case study of Taiwan biotech index during the epidemic period","volume":"6","author":"Lin","year":"2024","journal-title":"Front. Artif. Intell."},{"key":"B42","article-title":"\u201cStatistical analysis with missing data,\u201d","volume-title":"Wiley Series in Probability and Statistics, 3rd Edn","author":"Little","year":"2019"},{"key":"B43","doi-asserted-by":"publisher","first-page":"113985","DOI":"10.1016\/j.knosys.2025.113985","article-title":"Purely sentiment-driven stock index trend forecast: a probability model based on social media sentiment space","volume":"325","author":"Liu","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"B44","doi-asserted-by":"publisher","first-page":"103577","DOI":"10.1016\/j.irfa.2024.103577","article-title":"The determinants of voluntary disclosure: integration of eXtreme gradient boost (XGBoost) and explainable artificial intelligence (XAI) techniques","volume":"96","author":"Lu","year":"2024","journal-title":"Int. Rev. Fin. Anal."},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1705.07874","author":"Lundberg","year":"2017","journal-title":"A unified approach to interpreting model predictions. arXiv:1705.07874"},{"key":"B46","doi-asserted-by":"publisher","first-page":"107472","DOI":"10.1016\/j.frl.2025.107472","article-title":"Decoding risk sentiment in 10-K filings: predictability for U.S. stock indices","volume":"81","author":"Magner","year":"2025","journal-title":"Fin. Res. Lett."},{"key":"B47","doi-asserted-by":"publisher","first-page":"e02575","DOI":"10.1016\/j.sciaf.2025.e02575","article-title":"Nexus between stock market and agricultural sector development in nigeria and south africa: accounting for three-regime marginal-threshold effects","volume":"27","author":"Manasseh","year":"2025","journal-title":"Sci. Afr."},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1007\/s10614-025-10962-9","article-title":"Machine Learning XAI for early loan default prediction","author":"Monje","year":"2025","journal-title":"Comput. Econ"},{"key":"B49","doi-asserted-by":"publisher","first-page":"e40095","DOI":"10.1016\/j.heliyon.2024.e40095","article-title":"An explainable deep learning approach for stock market trend prediction","volume":"10","author":"Muhammad","year":"2024","journal-title":"Heliyon"},{"key":"B50","doi-asserted-by":"publisher","first-page":"29616","DOI":"10.1016\/j.ijhydene.2020.10.172","article-title":"A new hybrid fuzzy multi-criteria decision methodology model for prioritizing the alternatives of the hydrogen bus development: a case study from Romania","volume":"46","author":"Pamucar","year":"2020","journal-title":"Int. J. Hydrogen Energy"},{"key":"B51","doi-asserted-by":"publisher","first-page":"127240","DOI":"10.1016\/j.eswa.2025.127240","article-title":"Economic implications of enhanced stock market analysis using improved forecasting methods","volume":"277","author":"Peng","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"B52","doi-asserted-by":"publisher","first-page":"1599799","DOI":"10.3389\/frai.2025.1599799","article-title":"CMDMamba: dual-layer Mamba architecture with dual convolutional feed-forward networks for efficient financial time series forecasting","volume":"8","author":"Qin","year":"2025","journal-title":"Front. Artif. Intell."},{"key":"B53","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1257\/aer.99.2.466","article-title":"The aftermath of financial crises","volume":"99","author":"Reinhart","year":"2009","journal-title":"Am. Econ. Rev."},{"key":"B54","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1023\/A:1007614523901","article-title":"Improved boosting algorithms using confidence-rated predictions","volume":"37","author":"Schapire","year":"1999","journal-title":"Mach. Learn."},{"key":"B55","doi-asserted-by":"publisher","first-page":"122701","DOI":"10.1016\/j.renene.2025.122701","article-title":"Sustainable future orientation for BRICS+ nations: green growth, political stability, renewable energy and technology for ecological footprint mitigation","volume":"244","author":"Sethi","year":"2025","journal-title":"Renew. Energy"},{"key":"B56","doi-asserted-by":"publisher","first-page":"104253","DOI":"10.1016\/j.resourpol.2023.104253","article-title":"Revealing stock liquidity determinants by means of explainable AI: the role of ESG before and during the COVID-19 pandemic","volume":"86","author":"Teplova","year":"2023","journal-title":"Resour. Policy"},{"key":"B57","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1016\/j.iref.2023.10.038","article-title":"Return and volatility connectedness across global ESG stock indexes: evidence from the time-frequency domain analysis","volume":"89","author":"Wan","year":"2024","journal-title":"Int. Rev. Econ. Fin."},{"key":"B58","doi-asserted-by":"publisher","first-page":"2501","DOI":"10.1108\/MD-05-2017-0458","article-title":"A combined compromise solution (CoCoSo) method for multi-criteria decision-making problems","volume":"57","author":"Yazdani","year":"2019","journal-title":"Manag. Decis."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1668700\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T05:30:29Z","timestamp":1758173429000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1668700\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,18]]},"references-count":58,"alternative-id":["10.3389\/frai.2025.1668700"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1668700","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,18]]},"article-number":"1668700"}}