Stock Price Prediction Using Sentiment Analysis
Author(s):
Nir Nandu, Taibaz Pathan, Rahul Shukla, Kanhaiya Singh, Payal Varangaonkar
Keywords:
Abstract
Machine learning is THE future. As our hardware systems inch ever so forward so does our capability in deploying ever increasingly more complex machine learning algorithms. With the failure of the efficient market hypothesis and more advent of more powerful processors stock market prediction has become a viable solution. By taking current news sentiments and combining them with technical analysis of price factors, this research aims to predict trends in future prices on an intraday basis. It is human nature to be more focused on the negative parts of a dialogue. So, the sentiment analyzer was made to be more sensitive towards negative news. The predicted values showed a certain trend in which they were averse to rising too quickly. We think this is because the model was made to be more prone to negative things. This coupled with the more negative focused sentiment analyzer made it such that the model took a rather conservative or even pessimistic approach in its prediction. It was found that considering the news polarity drastically reduces the MSE values to below 1. This just shows us how much the general public relies on the news headlines to navigate the stock market and that just technical or fundamental analysis isn’t enough for accurate predictions.
Article Details
Unique Paper ID: 154755

Publication Volume & Issue: Volume 8, Issue 12

Page(s): 229 - 233
Article Preview & Download


Share This Article

Join our RMS

Conference Alert

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024

Last Date: 15th March 2024

Call For Paper

Volume 11 Issue 1

Last Date for paper submitting for Latest Issue is 25 June 2024

About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Social Media

Google Verified Reviews