Abstract: Systems and methods are provided for interpreting a correlation model that predicts a correlation between a pair of data corresponding to a pair of incident tickets using an interpreter model. The correlation model includes a Siamese Network including a plurality of neural networks. The interpreter model, trained by using training data, represents a student model (a glass-box model) while the correlation model, trained using the training data, represents a more complex teacher model (a black-box mode) of a teacher-student model. The present disclosure generates global feature importance scores based on the trained interpreter model, which indicates a degree of influence of a feature compared to other features in incident data in determining correlations, to generate additional training data emphasizing influential features and to retrain the correlation model.

Abstract: A method for training a neural network for linking incident management tickets is provided. A first training set of linked pairs of incident management tickets is generated. Each pair is labeled as being linked and comprises first and second tickets having first text features and second features. A Siamese neural network model is trained using the first text features as inputs to an input layer of the model. The input layer is configured to generate first and second input embeddings for the first and second tickets, respectively. The model is trained using the first and second input embeddings and the second features as inputs to an output layer of the model. The output layer is configured to generate first and second output embeddings for the first and second tickets, respectively. The model is trained using a contrastive loss function between the first and second output embeddings.