Resumen
This article describes the deep neural network model for books classification by genre on the base of text description. Such problems are usually solved with the use of models consisting of recurrent layers, however, in this work it is proposed to use the model with the hybrid architecture: the neural network consisting of LSTMs and convolutional layers. The paper provides the structure of the network and also discusses methods for improving the quality of its work. Deep neural network training and testing is carried out on its own dataset containing information on thousands of books. We can judge the possibility of using the trained model in solving practical problems on the basis of the results obtained. Moreover, this model can be used for the classification of text data in other topics.