Financial markets are globally interconnected, and trends in one market frequently influence others
\nthrough cross-country spillovers. Forecasting models that overlook these dependencies risk
\nsubstantial loss of predictive accuracy. This study proposes a novel hybrid framework that integrates
\nWavelet \u0394-band decomposition, Light Gradient Boosting Machine (LGBM), and Constricted Particle
\nSwarm Optimization (CPSO) to forecast Indian stock indices while explicitly modeling cross-country
\neffects. The target closing price series is decomposed into multi-resolution sub-bands using the
\nDiscrete Wavelet Transform (db4, level 3), and a first-order \u0394-transformation is applied to each
\nreconstructed band to stabilize non-stationarity. Each band is then modeled with CPSO-tuned LGBM
\nregressors, and predictions are aggregated via inverse DWT. Uniquely, the framework incorporates
\nU.S. market signals (Dow Jones Industrial Average) alongside 18 domestic technical indicators to
\ncapture global-to-local dependencies across three NSE indices: Nifty-50, Nifty Midcap, and Bank
\nNifty. Experimental evaluation on more than ten years of daily data (2013\u20132025) demonstrates strong
\npredictive performance, with the Nifty-50 achieving RMSE \u224882.46, MAE \u224857.31, and MAPE
\n<0.23%. SHAP-based interpretability analysis attributes approximately 47.68% of feature importance
\nto cross-country indicators, confirming significant global influence. A comprehensive ablation study
\nvalidates the incremental contribution of each component, and Diebold\u2013Mariano tests establish
\nstatistically significant improvements over baseline ML, deep learning, and econometric benchmarks,
\nhighlighting both methodological novelty and practical value for investors and policymakers.<\/p>\n","protected":false},"featured_media":5437,"template":"","meta":{"_acf_changed":false},"schedule":[7],"speaker-category":[6],"class_list":["post-5433","speaker","type-speaker","status-publish","has-post-thumbnail","hentry","schedule-day-2","speaker-category-speakers"],"acf":[],"yoast_head":"\n