Exploring a knowledge-based approach to predicting NACE codes of enterprises based on web page texts

Abstract

Classification of enterprises by main economic activity according to NACE codes is a challenging but important task for national statistical institutes. Since manual editing is time-consuming, we investigated the automatic prediction from dedicated website texts using a knowledge-based approach. To that end, concept features were derived from a set of domain-specific keywords. Furthermore, we compared flat classification to a specific two-level hierarchy which was based on an approach used by manual editors. We limited ourselves to Naïve Bayes and Support Vector Machines models and only used texts from the main web pages. As a first step, we trained a filter model that classifies whether websites contain information about economic activity. The resulting filtered data set was subsequently used to predict 111 NACE classes. We found that using concept features did not improve the model performance compared to a model with character n-grams, i.e. non-informative features. Neither did the two-level hierarchy improve the performance relative to a flat classification. Nonetheless, prediction of the best three NACE classes clearly improved the overall prediction performance compared to a top-one prediction. We conclude that more effort is needed in order to achieve good results with a knowledge-based approach and discuss ideas for improvement.