Abstract
Financial time series data are often used to construct financial complex networks for studying price volatility transmission, risk diffusion and asset portfolio and so on. High frequency Network can provide more effective information for exploring network structure and more accurate research on network evolution rules. The motivation of this paper is to construct high frequency networks using low frequency data when high frequency data is unavailable, with improvement of compressed sensing method. Results show that the network reconstructed by compressed sensing is closer to the high frequency network. In conclusion, compressed sensing can be applied to solve financial practice problem.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
