Xylanases are an industrially important class of hydrolytic enzymes that degrade xylans. Production of xylanase from a fungal culture by submerged fermentation and optimization of the operating conditions for maximum activity are the two aims of the present study. Penicillium janthinellum NCIM 1169 with Mandels-Weber medium, sugarcane bagassse (40#) as a carbon source and beef extract as a nitrogen source were used in the experiments. We did 41 experiments to see the effect of variations in carbon, nitrogen source, pH, and inoculum on xylanase activity. This data was then used to build an input/output model using multiple linear regression, back propagation neural network and lazy learning algorithm. It was found that lazy learning model correlated well in mapping input/output data. This model was then utilized as an objective function in genetic algorithm to find the optimal combination of the operating conditions to get the maximum xylanase activity. It was observed that with carbon source, 1.63%, nitrogen source, 0.16%, pH, 4.1, and inoculum, 5.5%, maximum xylanase activity of 28.98 ± 1.73 U/ml was achieved. © 2008 Elsevier B.V. All rights reserved.