© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.The developments in technology increase the amount of data produced in manufacturing and service systems. This leads to the preference for data-driven approaches instead of model-based approaches in the management of processes. As one of the most costly and labor-intensive parts of supply chain processes, warehouse operations are very critical for the effective management of supply chains. Picking time is an important parameter for warehouse problems. This study aims to develop a data-driven approach to predict picking time in an automobile spare parts warehouse by considering the characteristics of the pickers. We integrated fuzzy clustering and Artificial Neural Networks (ANN) for predicting picking times accurately. In our novel approach, pickers have been grouped to decrease the number of inputs by using a fuzzy clustering method. ANN model is trained to estimate the picking time of new orders by using fuzzy membership information and historical picking data. Picking time predictions can be used as the first step in solving many warehouse problems.