<p>Lebanon’s industrial sector remains underdeveloped despite its potential for driving national economic recovery. This study examines 11 key manufacturing sectors and their presence across the country’s 26 administrative districts, using three performance metrics: automation rates, export activity, and industry frequency. These sectoral indicators are analyzed alongside seven socioeconomic indicators, including poverty, unemployment, illiteracy, population density, distance from Beirut, industrial firm count, and zone productivity. Employing statistical techniques and machine learning models such as Pearson and Spearman correlations, K-means clustering, and Ordinary Least Squares regression, the study identifies patterns of industrial concentration, disparities in regional competitiveness, and key determinants of successful industrialization. Key findings include a significant moderate positive Spearman correlation between automation and exports (<i>r</i>_<i>s</i> = 0.46; <i>p</i> = 1.197 × 10⁻¹⁶), a marginal inverse linear relationship between industrial concentration and poverty (<i>r</i> = −0.59 ; <i>p</i> = 0.081), and a marginal inverse linear relationship between industrial concentration and casa unemployment (<i>r</i> = −0.77; <i>p</i> = 0.061). Spatial analysis reveals marked heterogeneity: Matn dominates in firm presence in ten industrial sectors, while agri-food and non-metallic equipment fields exhibit the broadest geographic presence. High-performing cazas (zone productivity rank ≥ 4) sustain over 90 % of possible field-caza combinations, contrasting sharply with lower-rank districts. Cluster analysis further delineates 22 overperforming combinations (7.7 %) that contribute disproportionately to national exports and firm activity. This work directly supports Sustainable Development Goal 9 (SDG 9) by promoting inclusive, resilient, and sustainable industrial growth in Lebanon through informed infrastructure planning and industrial diversification.</p>