Automated retrosynthetic planning algorithms are a research area of increased importance. Automated reaction template extraction from large datasets in conjunction with neural network enhanced tree search algorithms can find plausible routes to target compounds in seconds. However, the current way of training the neural networks to predict suitable templates for a given target product, leads to many predictions which are not applicable in silico. Most templates in the top-50 suggested templates can’t be applied to the target molecule to perform the virtual reaction. Here we describe how to generate data and train a neural network policy that predicts if templates are applicable or not. First, we generate a massive training dataset by applying each retrosynthetic template to each product from our reaction database. Second, we train a neural network to near perfect prediction of the applicability labels on a held-out test set. The trained network is then joined with a policy model trained to predict and prioritize templates using the labels from the original dataset. The combined model was found to outperform the policy model in a route-finding task using 1700 compounds from our internal drug discovery projects.