Machine Learning for Economics and Finance in TensorFlow 2: Deep Learning Models for Research and Industry

© Isaiah Hull 2021

I. HullMachine Learning for Economics and Finance in TensorFlow 2https://doi.org/10.1007/978-1-4842-6373-0_6

6. Text Data

Isaiah Hull¹  

(1)

Nacka, Sweden

 

The economics and finance disciplines have been generally reluctant to integrate forms of unstructured data. One exception to this is text, which has been applied to a wide variety of empirical problems. This may have arisen, in part, as a consequence of early successful applications in economics, such as Romer and Romer (2004), which demonstrated the empirical value of measuring internal central bank narratives.

The more widespread adoption of text may also be attributable to its many natural applications within economics and finance. It can, for instance, be used to extract latent ...