The key novelty of our work is the proposal of a new component in neural network modeling, named Temporal Graph Convolution, which jointly models the temporal evolution and relation network of stocks. To validate our method, we perform back-testing on the historical data of two stock markets, NYSE and NASDAQ.What is temporal convolutional networks (TCN)?
Temporal Convolutional Networks, or simply TCN, is a variation of Convolutional Neural Networks for sequence modelling tasks, by combining aspects of RNN and CNN architectures.What is financial time series (FTS)?
Financial Time Series (FTS) modelling is a practice with a long history which fir s t revolutionised algorithmic trading in the early 1970s. The analysis of FTS was divided into two categories: fundamental analysis and technical analysis. Both these practices were put into question by the Efficient Market Hypothesis (EMH).