Home
Add
Get on Google Play
Home
> Edit
Add/Update Thesis
Title*
Author's Name*
Supervisor's Name
Abstract
Stock market prediction has been an area of interest for a few decades now and much recently, there has been a lot of new research in the field of neural networks and natural language processing (NLP), that has resulted in satisfactory results. Sentiment analysis is one such sub-field of NLP that has made possible the extraction of emotions expressed in a body of text. These sentiments have been shown to co-relate with the change in stock prices. Previously twitter has been used to show a positive co-relation between the positive and negative sentiments gathered from a collection of tweets, and directional stock movements. In this paper, I expand upon these findings as I develop multiple predictive models that incorporates these technologies to predict not only the directional changes in the stock market but also the stock prices. For this purpose I use New York Times article headlines for the top 5 IT corporations listed on the S&P 500 index (Google, Microsoft, Amazon, Facebook and Apple), and use word2vec for encoding these headlines into vectors. These vectors are fed into LSTM NN, along with momentum-based economic indicators to supplement the predictive model. This has resulted in a MAPE (Mean Absolute Percentage Error) score of 1.15% for the regression based model and 65% direction accuracy, hence, indicating a positive co-relation between stock prices and public sentiment
Subject/Specialization
Language
Program
Faculty/Department's Name
Institute Name
Univeristy Type
Public
Private
Campus (if any)
Institute Affiliation Inforamtion (if any)
City where institute is located
Province
Country
Degree Starting Year
Degree Completion Year
Year of Viva Voce Exam
Thesis Completion Year
Thesis Status
Completed
Incomplete
Number of Pages
Urdu Keywords
English Keywords
Link
Select Category
Religious Studies
Social Sciences & Humanities
Science
Technology
Any other inforamtion you want to share such as Table of Contents, Conclusion.
Your email address*