This study investigates the interplay between exchange rate fluctuations, inflation, and India’s trade dynamics over a decade, leveraging machine learning to model these relationships. While prior research has predominantly focused on either exports or imports in isolation, this work addresses a critical gap by analyzing both trade components simultaneously, incorporating their interdependencies with macroeconomic variables. Using monthly data from the Reserve Bank of India, the study employs Lasso regression to build predictive models for export and import volumes, while correlation analysis tests hypotheses on the significance of exchange rates and inflation. Key findings reveal strong positive correlations between exchange rate depreciation and both exports and imports, challenging conventional expectations for imports, where structural inelasticity and essential goods dependency override price sensitivity. Inflation exhibits a moderate positive association with exports and imports, reflecting sectoral adaptations and imported inflation dynamics. The Lasso models demonstrate robust predictive performance, explaining 78.5% of variation in exports and 73.7% of variance in imports, with exchange rates emerging as the dominant predictor. The results underscore the nuanced role of currency depreciation in driving export competitiveness while inadvertently inflating import costs due to India’s reliance on critical foreign goods. Policy implications emphasize stabilizing exchange rates, curbing imported inflation, and fostering sectoral resilience through targeted interventions. This study contributes to trade policy discourse by integrating machine learning with macroeconomic analysis, offering actionable insights for balancing India’s trade ecosystem amid global volatility.