Modelling commodity value at risk with Psi Sigma neural networks using open–high–low–close data

Sermpinis, Georgios; Laws, Jason; Dunis, Christian L.

doi:10.1080/1351847x.2012.744763

Cited by 10 publications

(7 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the authors of [12] utilized Psi Sigma neural networks to predict one-dayahead VaR for Brent oil and gold bullion series. To benchmark their results, they used VaR forecasts from two different neural networks and genetic programming algorithms; some traditional techniques like the ARMA-Glosten, Jagannathan, and Runkle (1, 1) models; and the RiskMetrics volatility model.…”

Section: Deep Learning Approachesmentioning

confidence: 99%

Leveraging Return Prediction Approaches for Improved Value-at-Risk Estimation

Bagheri,

Reforgiato Recupero,

Sirnes

2023

Data

View full text Add to dashboard Cite

Value at risk is a statistic used to anticipate the largest possible losses over a specific time frame and within some level of confidence, usually 95% or 99%. For risk management and regulators, it offers a solution for trustworthy quantitative risk management tools. VaR has become the most widely used and accepted indicator of downside risk. Today, commercial banks and financial institutions utilize it as a tool to estimate the size and probability of upcoming losses in portfolios and, as a result, to estimate and manage the degree of risk exposure. The goal is to obtain the average number of VaR “failures” or “breaches” (losses that are more than the VaR) as near to the target rate as possible. It is also desired that the losses be evenly distributed as possible. VaR can be modeled in a variety of ways. The simplest method is to estimate volatility based on prior returns according to the assumption that volatility is constant. Otherwise, the volatility process can be modeled using the GARCH model. Machine learning techniques have been used in recent years to carry out stock market forecasts based on historical time series. A machine learning system is often trained on an in-sample dataset, where it can adjust and improve specific hyperparameters in accordance with the underlying metric. The trained model is tested on an out-of-sample dataset. We compared the baselines for the VaR estimation of a day (d) according to different metrics (i) to their respective variants that included stock return forecast information of d and stock return data of the days before d and (ii) to a GARCH model that included return prediction information of d and stock return data of the days before d. Various strategies such as ARIMA and a proposed ensemble of regressors have been employed to predict stock returns. We observed that the versions of the univariate techniques and GARCH integrated with return predictions outperformed the baselines in four different marketplaces.

show abstract

Section: Deep Learning Approachesmentioning

confidence: 99%

Leveraging Return Prediction Approaches for Improved Value-at-Risk Estimation

Bagheri,

Reforgiato Recupero,

Sirnes

2023

Data

View full text Add to dashboard Cite

show abstract

“…in credit scoring [49][50][51]. Furthermore, the neural networks trained by more sophisticated algorithms outperform those trained by ordinary gradient descent [22,52]. Besides, the hybrid of neural network and genetic algorithm proves as excellent classifier in credit scoring [53].…”

Section: Prevalent Classical Models For Credit Scoringmentioning

confidence: 99%

Optimizing hyper-parameters of neural networks with swarm intelligence: A novel framework for credit scoring

Zhang

Qiu

2020

PLoS ONE

View full text Add to dashboard Cite

Neural networks are widely used in automatic credit scoring systems with high accuracy and outstanding efficiency. However, in the absence of prior knowledge, it is difficult to determine the set of hyper-parameters, which makes its application limited in practice. This paper presents a novel framework of credit-scoring model based on neural networks trained by the optimal swarm intelligence (SI) algorithm. This framework incorporates three procedures. Step 1, pre-processing, including imputation, normalization, and reordering of the samples. Step 2, training, where SI algorithms optimize hyper-parameters of back-propagation artificial neural networks (BP-ANN) with the area under curve (AUC) as the evaluation function. Step 3, test, applying the optimized model in Step 2 to predict new samples. The results show that the framework proposed in this paper searches the hyper-parameter space efficiently and finds the optimal set of hyper parameters with appropriate time complexity, which enhances the fitting and generalization ability of BP-ANN. Compared with existing credit-scoring models, the model in this paper predicts with a higher accuracy. Additionally, the model enjoys a greater robustness, for the difference of performance between training and testing phases.

show abstract

“…Researchers and practitioners borrow algorithms from mathematics, physics, genetics and computer science in an attempt to model series that have a non-linear and non-stationary structure. Some apply simple technical rules (Gençay et al, 2003;Qi and Wu, 2006;Neely et al, 2009;Cialenco and Protopapadakis, 2011), while others explore complex non-linear models (Gehrig and Menkhoff, 2006;Gradojevic 2007;Sermpinis et al, 2015). There are also academics that believe FX series follow a random walk and any profitable trading rules are due to luck or not adjusting for appropriate risk factors (Meese and Rogoff, 1983; Kilian andTaylor, 2003, Ivanova et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

“…Other literature explores the latest developments in statistics and computer science and their application in FX trading. Gençay (1998), Jasic and Wood (2004), Gradojevic (2007), Sermpinis et al (2013) and Sermpinis et al (2015) apply Artificial Neural Networks (ANNs) -a form of non-linear regression algorithms -to the task of forecasting and trading financial series with some success. Alvarez-Diaz and Alvarez (2003), Pai et al (2006) and Huang et al (2010) develop models inspired by the evolution of species to financial forecasting with good results.…”

Section: Introductionmentioning

confidence: 99%