This paper analyzes the time-varying relationship between risk aversion and both conventional unconventional monetary policy in an international context at different frequencies using a wavelet coherency analysis. Our main results suggest existence of dynamic two variables depending on timescales periods. Thus, short-run negative leading from variable to measure is found for most period, sugges...

Traditional machine learning sequence models, such as RNN and LSTM, can solve sequential data problems with the use of internal memory states. However, neuron units weights are shared at each time step to reduce computational costs, limiting their ability learn time-varying relationships between model inputs outputs. In this context, paper proposes two methods characterize dynamic in real-world...