Display omitted •Data on chemical-enzymatic pretreatment of lignocellulosic biomass compiled.•Yield of reducing sugar is modelled with nine depnedendent variables.•Reduced interaction model offered the best-fit R2: 0.891, Adj. R2: 0.849.•Acid concentration and severity remain the least important predictors.•Genetic algorithm optimized artificial neural network offered excellent fit. Reducing sugar generation from lignocellulosic biomass (LCB) is closely linked with biomass characteristics, pretreatment and enzymatic hydrolysis conditions. In this study curated experimental data from literature was used to develop multivariate regression and artificial neural network (ANN) model considering nine predictors (i.e., cellulose, hemicellulose, lignin content, cellulose-lignin ratio, acid concentration, temperature, time, pretreatment severity, and enzyme concentration). Selected reduced polynomial model (R2: 0.891, Adj. R2: 0.849) suggests positive influence of acid and enzyme, while negative influence of treatment severity, temperature and time on reducing sugar generation. Genetic algorithm-optimized ANN model offered excellent fitness for LCB hydrolysis on training (R2: 0.997), validation (R2: 0.984), and test sets (R2: 0.967). Sensitivity analysis of the ANN predictors suggests lignin and to some extent hemicellulose contents can be inhibitory. Though polynomial models can have simple interpretation, use of optimized ANN offers better predictability in dataset with diverse biomass compositions.