Would like to work with some of the below tasks, initially pairing to outline and make progress on the work, and potentially handing off some of the work to be completed solo.
Many subprojects available in setting up financial data for training predictive models:
ingest from an api company fundamentals (from finnhub, first checking if licensing from quandl makes more sense)
ingest price data (from rar files) for a frontier market and stage on s3 (set up and run AWS Batch job to unrar/unzip many files; validate data quality)
port price data featurization code from pandas to pyspark
set up pyspark job on databricks to run the featurization code
build a streamlit app to display how stocks respond to significan stock-related news
and so on...