Stock price prediction method based on TCN-BiGRU model

Deep learning technology is now applied in many fields. In the financial field, deep learning as an emerging technology is also widely used, such as high-frequency trading, investment portfolio, stock price prediction and risk management. Among them, the most valuable and popular for investors is stock price prediction. In this paper, we adopt a combination model of time convolution network and bidirectional gated recurrent unit for stock prediction. We choose the stock price of Amazon as the target price, use the NASDAQ Composite Index, the US Dollar Index and so on as features, and compare with the baseline model.