Interfacial areas (a(w)) and volumetric mass-transfer coefficients (k(L)a(w), K(L)a(w), k(G)a(w), and K(G)a(w)) required for randomly packed tower design were gathered from the literature to generate a working database including over 3780 measurements. A set of artificial neural network correlations for the gas-liquid interfacial area and the pure local mass-transfer coefficients was proposed. Thus, the gas-liquid interfacial area and the pure local mass transfer coefficients (k(y), where gamma = G or L) were extracted using a reconciliation procedure which combined actually measured interfacial areas with pseudo interfacial areas inferred from the actually measured volumetric mass-transfer coefficients. The neural network weights of the two a(w) and k(gamma) correlations were adjusted using a least-squares composite criterion simultaneously over the five mass-transfer parameters. The first correlation representing the gas-liquid interfacial area [a(w)/a(T) = f(Re-L, Fr-L, Eo(L), chi, K)] yielded an average absolute relative error (AARE) of 22.5% for the 325 measurements available. The second one, representing either k(G) or k(L), was also implemented using the following structure Sh(gamma) = f(Re-gamma, Fr-gamma, Sc-gamma, chi). The combination of both correlation predictions (i.e., k(gamma)a(w)) yielded an AARE of 24.4% for the local and global volumetric mass transfer coefficients (3455 data).