Search

This paper enters the ongoing volatility forecasting debate by examining the ability of a wide range of Machine Learning methods (ML), and specifically Artificial Neural Network (ANN) models. The ANN models are compared against traditional econometric models for ten Asian markets using daily data for the time period from 12 September 1994 to 05 March 2018. The empirical results indicate that ML algorithms, across the range of countries, can better approximate dependencies compared to traditional benchmark models. Notably, the predictive performance of such deep learning models is superior perhaps due to its ability in capturing long-range dependencies. For example, the Neuro Fuzzy models of ANFIS and CANFIS, which outperform the EGARCH model, are more flexible in modelling both asymmetry and long memory properties. This offers new insights for Asian markets. In addition to standard statistics forecast metrics, we also consider risk management measures including the value-at-risk (VaR) average failure rate, the Kupiec LR test, the Christoffersen independence test, the expected shortfall (ES) and the dynamic quantile test. The study concludes that ML algorithms provide improving volatility forecasts in the stock markets of Asia and suggest that this may be a fruitful approach for risk management. [ABSTRACT FROM AUTHOR]

Background: Chronic spinal cord injury (SCI) increases morbidity and mortality associated with cardiometabolic diseases, secondary to increases in central adiposity, hyperlipidaemia and impaired glucose tolerance. While upper-body Moderate Intensity Continuous Training (MICT) improves cardiorespiratory fitness, its effects on cardiometabolic component risks in adults with SCI appear relatively modest. The aim of this study is to assess the acute effects of Continuous Resistance Training (CRT), High Intensity Interval Training (HIIT), MICT and rest (CON) on fasting and postprandial systemic biomarkers and substrate utilisation.Methods: Eleven healthy, chronic SCI (> 1 year, ASIA A-C) men will be recruited. Following preliminary testing, each will complete four experimental conditions, where they will report to the laboratory following an ~ 10-h overnight fast. A venous blood sample will be drawn and expired gases collected to estimate resting metabolic rate (RMR). In order to ensure an isocaloric exercise challenge, each will complete CRT first, with the remaining three conditions presented in randomised order: (1) CRT, ~ 45 min of resistance manoeuvres (weight lifting) interspersed with low-resistance, high-speed arm-crank exercise; (2) CON, seated rest; (3) MICT, ~ 45 min constant arm-crank exercise at a resistance equivalent to 30-40% peak power output (PPO) and; (4) HIIT, ~ 35 min arm-crank exercise with the resistance alternating every 2 min between 10% PPO and 70% PPO. After each ~ 45-min condition, participants will ingest a 2510-kJ liquid test meal (35% fat, 50% carbohydrate, 15% protein). Venous blood and expired gas samples will be collected at the end of exercise and at regular intervals for 120 min post meal.Discussion: This study should establish the acute effects of different forms of exercise on fasting and postprandial responses in chronic SCI male patients. Measures of glucose clearance, insulin sensitivity, lipid and inflammatory biomarker concentrations will be assessed and changes in whole-body substrate oxidation estimated from expired gases.Trial Registration: ClinicalTrials.gov, ID: NCT03545867 . Retrospectively registered on 1 June 2018. [ABSTRACT FROM AUTHOR]