This study presents a unified machine learning (ML) framework designed to bridge four interconnected domains of modern finance: financial markets, banking stability, economic forecasting, and Islamic finance. Drawing on a multi-source empirical dataset—including U.S. equity and volatility indices (2000–2024), Shariah-compliant exchange-traded funds (ETFs) (2019–2024), major banking institution stocks, macroeconomic ETF proxies, and the World Bank Global Financial Development Database (GFDD) panel (2000–2023)—I develop a layered analytical architecture combining random forest and extreme gradient boosting (XGBoost) for feature selection and predictive modelling. A central contribution of this study is the treatment of Shariah-compliance screening as a quantifiable data feature, enabling systematic ethical filtering within a big data environment. The empirical results show that the random forest model reduces out-of-sample root mean square error (RMSE) by 78.3% relative to the ordinary least squares (OLS) benchmark in forecasting the Chicago Board Options Exchange Volatility Index (CBOE VIX), and achieves an R² of 0.224 in cross-country banking distress prediction. Shariah-compliant ETFs record a higher Sharpe ratio (0.819 vs. 0.702 for the S&P 500) and a marginally lower maximum drawdown (−33.57% vs. −33.92%) over the 2019–2024 period, though this period-specific differential should be interpreted with caution given the short five-year sample. Bank concentration (31.0%) and interest rate spreads (25.3%) emerge as the dominant structural predictors of non-performing loan ratios across global banking systems. These findings demonstrate that big data analytics can bring together traditionally separate financial domains—including Islamic finance—within a single, coherent predictive framework, with meaningful implications for financial regulation, portfolio construction, and Shariah-compliant asset management.
Citation: Umar Iqbal Butt. 2026: Harnessing big data analytics across financial markets, banking, economic forecasting, and islamic finance: A unified machine learning framework, Innovation Economics, 1(1): 52-67. doi: 10.3934/InnoEcon.2026003
This study presents a unified machine learning (ML) framework designed to bridge four interconnected domains of modern finance: financial markets, banking stability, economic forecasting, and Islamic finance. Drawing on a multi-source empirical dataset—including U.S. equity and volatility indices (2000–2024), Shariah-compliant exchange-traded funds (ETFs) (2019–2024), major banking institution stocks, macroeconomic ETF proxies, and the World Bank Global Financial Development Database (GFDD) panel (2000–2023)—I develop a layered analytical architecture combining random forest and extreme gradient boosting (XGBoost) for feature selection and predictive modelling. A central contribution of this study is the treatment of Shariah-compliance screening as a quantifiable data feature, enabling systematic ethical filtering within a big data environment. The empirical results show that the random forest model reduces out-of-sample root mean square error (RMSE) by 78.3% relative to the ordinary least squares (OLS) benchmark in forecasting the Chicago Board Options Exchange Volatility Index (CBOE VIX), and achieves an R² of 0.224 in cross-country banking distress prediction. Shariah-compliant ETFs record a higher Sharpe ratio (0.819 vs. 0.702 for the S&P 500) and a marginally lower maximum drawdown (−33.57% vs. −33.92%) over the 2019–2024 period, though this period-specific differential should be interpreted with caution given the short five-year sample. Bank concentration (31.0%) and interest rate spreads (25.3%) emerge as the dominant structural predictors of non-performing loan ratios across global banking systems. These findings demonstrate that big data analytics can bring together traditionally separate financial domains—including Islamic finance—within a single, coherent predictive framework, with meaningful implications for financial regulation, portfolio construction, and Shariah-compliant asset management.
| [1] |
Andersen TG, Bollerslev T, Diebold FX, et al. (2003) Modeling and forecasting realized volatility. Econometrica 71: 579–625. https://doi.org/10.1111/1468-0262.00418 doi: 10.1111/1468-0262.00418
|
| [2] |
Athey S (2017) Beyond prediction: Using big data for policy problems. Science 355: 483–485. https://doi.org/10.1126/science.aal4321 doi: 10.1126/science.aal4321
|
| [3] | Athey S, Imbens GW (2019) Machine learning methods that economists should know about. Annu Rev Econ 11: 685–725. |
| [4] |
Berge TJ, Jordà Ò (2011) Evaluating the classification of economic activity into recessions and expansions. Am Econ J-Macroecon 3: 246–277. https://doi.org/10.1257/mac.3.2.246 doi: 10.1257/mac.3.2.246
|
| [5] |
Berger AN, Klapper LF, Turk-Ariss R (2009) Bank competition and financial stability. J Financ Serv Res 35: 99–118. https://doi.org/10.1007/s10693-008-0050-7 doi: 10.1007/s10693-008-0050-7
|
| [6] |
Bernanke B, Gertler M (1995) Inside the black box: The credit channel of monetary policy transmission. J Econ Perspect 9: 27–48. https://doi.org/10.1257/jep.9.4.27 doi: 10.1257/jep.9.4.27
|
| [7] |
Breiman L (2001) Random forests. Mach Learn 45: 5–32. https://doi.org/10.1023/A:1010933404324 doi: 10.1023/A:1010933404324
|
| [8] |
Brunnermeier MK, Pedersen LH (2009) Market liquidity and funding liquidity. Rev Financ Stud 22: 2201–2238. https://doi.org/10.1093/rfs/hhn098 doi: 10.1093/rfs/hhn098
|
| [9] |
Bussière M, Fratzscher M (2006) Towards a new early warning system of financial crises. J Int Money Financ 25: 953–973. https://doi.org/10.1016/j.jimonfin.2006.07.007 doi: 10.1016/j.jimonfin.2006.07.007
|
| [10] | Chen T, Guestrin C (2016) XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794. https://doi.org/10.1145/2939672.2939785 |
| [11] |
Cont R (2011) Statistical modeling of high-frequency financial data. Ieee Signal Proc Mag 28: 16–25. https://doi.org/10.1109/MSP.2011.941548 doi: 10.1109/MSP.2011.941548
|
| [12] |
Coulombe PG, Leroux M, Stevanovic D, et al. (2022) How is machine learning useful for macroeconomic forecasting? J Appl Economet 37: 920–964. https://doi.org/10.1002/jae.2910 doi: 10.1002/jae.2910
|
| [13] |
Estrella A, Mishkin FS (1998) Predicting U. S. recessions: Financial variables as leading indicators. Rev Econ Stat 80: 45–61. https://doi.org/10.1162/003465398557320 doi: 10.1162/003465398557320
|
| [14] | Fathurahman H, Fitriati R (2013) Comparative analysis of return on sukuk and conventional bonds. Am J Agr Econ 3: 159–163. |
| [15] |
Fischer T, Krauss C (2018) Deep learning with long short-term memory networks for financial market predictions. Eur J Oper Res 270: 654–669. https://doi.org/10.1016/j.ejor.2017.11.054 doi: 10.1016/j.ejor.2017.11.054
|
| [16] |
Goodell JW, Kumar S, Lim WM, et al. (2021) Artificial intelligence and machine learning in finance: Identifying foundations, themes, and future research directions. Financ Res Lett 42: 101786. https://doi.org/10.1016/j.jbef.2021.100577 doi: 10.1016/j.jbef.2021.100577
|
| [17] |
Gu S, Kelly B, Xiu D (2020) Empirical asset pricing via machine learning. Rev Financ Stud 33: 2223-2273. https://doi.org/10.1093/rfs/hhaa009 doi: 10.1093/rfs/hhaa009
|
| [18] | Hassan MK (2002) Risk, return and volatility of faith-based investing: The case of the Dow Jones Islamic Index. Proceedings of the 5th Harvard University Forum on Islamic Finance, 43–67. |
| [19] |
Hassan MK, Girard E (2011) Faith-based ethical investing: The case of Dow Jones Islamic indexes. Islamic Econ Stud 17: 1–31. https://doi.org/10.2139/ssrn.1808853 doi: 10.2139/ssrn.1808853
|
| [20] |
Ho CSF, Abd Rahman NA, Yusuf NHM, et al. (2014) Performance of global Islamic versus conventional share indices: International evidence. Pac-Basin Financ J 28: 110–121. https://doi.org/10.1016/j.pacfin.2013.09.002 doi: 10.1016/j.pacfin.2013.09.002
|
| [21] |
Holopainen M, Sarlin P (2017) Toward robust early-warning models: A horse race, ensembles and model uncertainty. Quant Financ 17: 1933–1963. https://doi.org/10.1080/14697688.2017.1357972 doi: 10.1080/14697688.2017.1357972
|
| [22] | Houlsby N, Giurgiu A, Jastrzebski S, et al. (2019) Parameter-efficient transfer learning for NLP. Proceedings of the International Conference on Machine Learning (ICML), 2790–2799. |
| [23] |
Huang W, Nakamori Y, Wang SY (2020) Forecasting stock market movement direction with support vector machine. Comput Oper Res 32: 2513–2522. https://doi.org/10.1016/j.cor.2004.03.016 doi: 10.1016/j.cor.2004.03.016
|
| [24] | Islamic Finance Development Report (2023) Resilience and continuity. Islamic Corporation for the Development of the Private Sector (ICD) / LSEG. |
| [25] |
Johnes J, Izzeldin M, Pappas V (2014) A comparison of performance of Islamic and conventional banks 2004–2009. J Econ Behav Organ 103: S93–S107. https://doi.org/10.1016/j.jebo.2013.07.016 doi: 10.1016/j.jebo.2013.07.016
|
| [26] |
Khandani AE, Kim AJ, Lo AW (2010) Consumer credit-risk models via machine-learning algorithms. J Bank Financ 34: 2767–2787. https://doi.org/10.1016/j.jbankfin.2010.06.001 doi: 10.1016/j.jbankfin.2010.06.001
|
| [27] |
Kjosevski J, Petkovski M (2017) Non-performing loans in Baltic States: Determinants and macroeconomic effects. Baltic J Econ 17: 25–44. https://doi.org/10.1080/1406099X.2016.1246234 doi: 10.1080/1406099X.2016.1246234
|
| [28] | López de Prado M (2018) Advances in financial machine learning. John Wiley & Sons. https://doi.org/10.2139/ssrn.3365271 |
| [29] |
Mention AL, Bontis N (2013) Intellectual capital and performance within the banking sector of Luxembourg and Belgium. J Intellect Cap 14: 286–309. https://doi.org/10.1108/14691931311323896 doi: 10.1108/14691931311323896
|
| [30] |
Ozili PK (2019) Non-performing loans and financial development: New evidence. J Risk Financ 20: 59–81. https://doi.org/10.1108/JRF-07-2017-0112 doi: 10.1108/JRF-07-2017-0112
|
| [31] |
Sherrill DE, Upton K (2018) Actively replacing passive benchmarks: A review of the U. S. market for Shariah-compliant ETFs. Manag Financ 44: 351–369. https://doi.org/10.1108/MF-03-2017-0067 doi: 10.1108/MF-03-2017-0067
|
| [32] | Stock JH, Watson MW (2012) Disentangling the channels of the 2007–2009 recession. Brookings Papers on Economic Activity, Spring, 81–135. |
| [33] |
Walkshäusl C, Lobe S (2012) Islamic investing. Rev Financ Econ 21: 53–62. https://doi.org/10.1353/eca.2012.0005 doi: 10.1353/eca.2012.0005
|
| [34] | World Bank (2024) Global Financial Development Database (GFDD). Retrieved from https://www.worldbank.org/en/publication/gfdr/data. |
 InnoEcon-01-01-003-s001.pdf |
 |
Umar Iqbal Butt. 2026: Harnessing big data analytics across financial markets, banking, economic forecasting, and islamic finance: A unified machine learning framework, Innovation Economics, 1(1): 52-67. doi: 10.3934/InnoEcon.2026003
DownLoad: