In Chapter 3, Alternative Data for Finance, we learned how to scrape earnings call data from the SeekingAlpha site. In this section, we will illustrate topic modeling using this source. I'm using a sample of some 500 earnings call transcripts from the second half of 2018. For a practical application, a larger dataset would be highly desirable. The earnings_calls directory contains several files, with examples mentioned later.

See the lda_earnings_calls notebook for details on loading, exploring, and preprocessing the data, as well as training and evaluating individual models, and the run_experiments.py file for the experiments described here.