We develop a methodology for detecting asset bubbles using a neural network. We rely on the theory of local martingales in continuous-time and use a deep network to estimate the diffusion coefficient of the price process more accurately than the current estimator, obtaining an improved detection...

We develop a new method that detects jumps nonparametrically in financial time series and significantly outperforms the current benchmark on simulated data. We use a long short- term memory (LSTM) neural network that is trained on labelled data generated by a process that experiences both jumps...

The size of the economic shocks triggered by the COVID-19 pandemic and the effects of the associated non-pharmaceutical interventions have not been fully assessed, because the official economic indicators have not been published. This paper provides estimates of the economic impacts of the...

How much an economy should invest in its physical infrastructure is a crucial question being asked by policy makers from developing countries where financial resources for economic development are limited. This paper aims to address this question by bringing insights from the literature that...