project_suggestions.md

Project Suggestions

Create a Bayesian data pipeline

1. Fetches data from a public API.
2. Submits the data as an input to a probabilistic model.
3. Generates samples from a posterior.
4. Takes posterior samples and stores them in an S3 bucket.

The storage in the S3 bucket should be serialized such that you can query the samples using Amazon Athena.

Implement a barebones probabilistic programming language