How does node centrality in a financial network affect asset price prediction?

In complex financial networks, systemically important nodes usually play crucial roles. Asset price forecasting is important for describing the evolution of a financial network. Naturally, the question arises as to whether node centrality impacts the effectiveness of price forecasting. To explore this, we examine networks composed of major global assets and investigate how node centrality affects price forecasting using a hybrid random forest algorithm. Our findings reveal two counterintuitive phenomena: (i) factors with low centrality usually have better forecasting ability, and (ii) nodes with low centrality can be predicted more accurately in direction. These unexpected observations can be explained from the perspective of information theory. Moreover, our research suggests a criterion for factor selection: when predicting an asset price in a complex system, factors with low centrality should be selected rather than only factors with high centrality. Finally, we verify the robustness of our results using an alternative deep learning method.