Automated industry classification with deep learning
Sam Wood, Rohit Muthyala, Yi Jin, Yixing Qin, Nilaj Rukadikar, Amit Rai, Hua Gao · 2017
In this paper, we present a novel technique for industry classification. Leveraging EverString's API to construct a database of companies labeled with the industries to which they belong, we train a deep neural network to predict the industries of novel companies. We examine the capacity of our model to predict six-digit NAICS codes, as well as the ability of our model architecture to adapt to other industry segmentation schemas. Additionally, we investigate the ability of our model to generalize despite the presence of noise in the labels in our training set. Finally, we explore the possibility of increasing predictive precision by thresholding based on the confidence scores that our model outputs along with its predictions. We find that our approach yields six-digit NAICS code predictions that surpass the precision of gold-standard databases.