Introducing Quantile CNN VaR for after-work quants
Petneházi (2019) forecasts VaR with a dilated causal CNN + pinball/quantile loss, trained jointly across many stocks. Single-name QCNN overshoots; the joint net is the point. Not investment advice.
Academy notes
Articles and updates from SoloQuant Academy.
Tag: after-work
Petneházi (2019) forecasts VaR with a dilated causal CNN + pinball/quantile loss, trained jointly across many stocks. Single-name QCNN overshoots; the joint net is the point. Not investment advice.
Arimond, Borth, Hoepner, Klawunn & Weisheit (2020) train generative regime-switching nets for VaR: HMM init, a two-objective loss, and a data-size warning. Not investment advice.