Skip to content

hish-school-work/Math509-project

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

32 Commits
 
 
 
 

Repository files navigation

Stock Price Prediction Based on News Sentiment

Group Members

Name Student ID
Chetan Dhingra 1862481
Hish Salehi 1812352
Velda Iskandar 1882870

Research Question

How does news sentiment affect stock prices?

Project Description

This project aims to understand if the general feeling (sentiment) expressed in news articles about a company can help predict how its stock price will change. We will collect news articles, analyze their sentiment, and then see if this sentiment is related to actual stock price movements. We will use machine learning techniques to build a model that tries to predict these price changes based on news sentiment.

Goals

  • Get sentiment scores from news articles about a specific stock.
  • See if there's a connection between these sentiment scores and how the stock price changes.
  • Build computer models to predict stock price changes using news sentiment.
  • Check how well our models perform using standard statistical measures.
  • Use methods like MCMC sampling to better understand our model.

Data

We will use financial news articles and historical stock price data. The specific sources and how often we get the data will be decided later. We will choose data that allows us to see both quick reactions to news and longer-term trends.

Methodology

We will first process the news articles to determine their sentiment (positive, negative, or neutral). Then, we will use this sentiment data along with historical stock prices to build our prediction models. We plan to use Bayesian inference techniques for this.

Evaluation

We will measure how well our models work by looking at metrics like AUC-ROC. This will tell us how good our model is at correctly predicting whether a stock price will go up or down.

Assignments/Roles

Member Role
Chetan Dhingra Data Collection and Preprocessing
Hish Salehi Model Modeling and Implementation
Velda Iskandar Evaluation and Report Writing

Value

This project will help us understand the relationship between news and stock markets. It could provide insights for investors on how news sentiment might influence stock prices.

Links

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors