Loading...

Stock Market Prediction Using Deep Learning based on Social Networks Data

Shafiei Masoleh, Mohammad | 2021

421 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 53832 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Sameti, Hossein
  7. Abstract:
  8. Stock market prediction has always been a challenging task. Due to its stochastic nature, naive models cannot help solve the problem. In the past, Statistical models were used, however nowa- days with the rise of deep learning and more complex models, aggregating data, in order to pre- dict the stock price, has become feasible. Moreover, the emergence of social networks enables researchers to design models for stock prediction.Researchers used recurrent networks and word vector representations to solve this problem. However, recently newer models such as generative models based on VAEs and attention have gained interest. Newer models also don’t rely on a single data source and use multiple data sources for stock prediction.In this research, we propose a model to make the prediction using twitter's data and stock's historical price. We also try to use corporations' relations to consider their effect on each other. By utilizing transformer-based models, we improve embedding textual data, and by adding a graph neural network to our model, we consider the relation and effects of companies on each other. We test our proposed method on a standard dataset and by comparing with the baseline model, we show that our model has improved the Matthews correlation coefficient (MCC) from 0.080 to 0.115
  9. Keywords:
  10. Natural Language Processing ; Deep Learning ; Graph Neural Network ; Social Networks ; Price Forecasting ; Stock Price ; Stock Price Prediction

 Digital Object List

 Bookmark

...see more