# Stock-market signals in Twitter data

A team research project testing whether company and CEO tweets could help predict short-term stock direction.

Author: Joshua Palamuttam
Published: 2020-03-11
Type: Project
Status: Archived entry
Role: Team project contributor
Period: College project
Tags: machine-learning, natural-language-processing, python
Canonical page: https://www.joshuapalamuttam.com/built/stock-market-analysis/

## Links

- [Explore the repository](https://github.com/Joshua-Palamuttam/StockMarketAnalysis)
- [View the presentation](https://docs.google.com/presentation/d/1Tdd4hQHXKpW584hfNerBjT2z16ZnkSL97CS247rk0xo/edit?usp=sharing)

This project asked whether posts from a company and its CEO carried enough signal to
help predict whether the stock would move up or down.

Our team collected tweets, removed duplicate and noisy text, applied latent semantic
analysis, and compared classifiers including Naive Bayes with cross-validation. The
project was an early lesson in the gap between an interesting correlation and a useful
prediction—and in how much of data science is really careful data preparation.