> ## Content Index
> Fetch the complete content index at: https://fsc.stevens.edu/llms.txt
> Use this file to discover other available public pages before exploring further.

# Modified Financial Latent Dirichlet Allocation: A Potential Feature Extraction Technique in Text Mining for Financial Time Series Prediction
- URL: https://fsc.stevens.edu/modified-financial-latent-dirichlet-allocation-a-potential-feature-extraction-technique-in-text-mining-for-financial-time-series-prediction-2/
- Published: 2026-02-16T18:57:01.000Z
- Updated: 2026-05-16T22:33:08.000Z
- Description: News articles can be a powerful source for many financial time series predictions. However, extracting useful information from a large amount of unstructured data and representing the features in a rather small dimensionality remain a big challenge for researchers.
- Author: hfsladmin
- Tags: masters-thesis

**Author:** Chun Chen 

**Advisor:** [Dr. Dragos Bozdog ](https://www.stevens.edu/profile/dbozdog?ref=fsc.stevens.edu)

**Date:** May 11, 2021 

**Department:** Financial Engineering 

**Degree:** Master of Science - Financial Engineering

  
**Advisory Committee:** 

[Dr. Dragos Bozdog](https://www.stevens.edu/profile/dbozdog?ref=fsc.stevens.edu), Chairman

[Dr. Ionut Florescu](https://www.stevens.edu/profile/ifloresc?ref=fsc.stevens.edu), Reader

**Abstract:** News articles can be a powerful source for many financial time series predictions. However, extracting useful information from a large amount of unstructured data and representing the features in a rather small dimensionality remain a big challenge for researchers. This paper introduces a modified topic model based on latent Dirichlet allocation (LDA) to extract features from news articles which combines sentiment analysis with text mining, denoted as Modified Financial LDA (M-FinLDA). With some assumptions, we provide the detailed mathematics behind the posterior distributions used in Gibbs Sampling and the log-likelihood used to fix the hyperparameters of the M-FinLDA model. We purpose a basic framework for applying the M-FinLDA in text mining and the features from M-FinLDA can be served as additional input features for any machine learning algorithm to improve the predictions. The experimental results show that the features from the M-FinLDA empirically give better results than the comparative features including topic distributions from the LDA and the FinLDA.

For full Dissertation, click [here](https://www.proquest.com/pqdtlocal1007352/docview/2562537355/B07FE4FC1CF0436BPQ/1?accountid=14052&sourcetype=Dissertations%20&%20Theses&ref=fsc.stevens.edu).