Enhanced stock prediction using social network and statistical model

As a fundamental part of capital market, stock investment has great significance in optimizing capital allocation, funding as well as increasing the value of assets. To predict and evaluate the stock price also has important practical significance for investors due to the high income and high-risk characteristics of stock investments. However, the stock price is usually random fluctuation which affecting by speculative factors, thus make it is almost impossible to make accurate prediction. Considering conformist mentality is essential for accurately predict stock price. Recently, with expansive development of social networks (e.g. Facebook, Tweet or Sina weibo, etc.), huge users publish and exchange a variety of financial-related information with other users. Therefore, social network is an important approach to comprehend conformist mentality. In view of the above analysis, this paper proposed a new stock prediction method based on social networks and regression model, and we also used real dataset of NASDAQ market and Twitter to verify the proposed model. Experimental results show that the proposed method can accurately predict stock price.