Deep learning for volatility forecasting in asset management

Predicting volatility is a critical activity for taking risk- adjusted decisions in asset trading and allocation. In order to provide effective decision-making support, in this paper we investigate the profitability of a deep Long Short-Term Memory (LSTM) Neural Network for forecasting daily stock market volatility using a panel of 28 assets representative of the Dow Jones Industrial Average index combined with the market factor proxied by the SPY and, separately, a panel of 92 assets belonging to the NASDAQ 100 index. The Dow Jones plus SPY data are from January 2002 to August 2008, while the NASDAQ 100 is from December 2012 to November 2017. If, on the one hand, we expect that this evolutionary behavior can be effectively captured adaptively through the use of Artificial Intelligence (AI) flexible methods, on the other, in this setting, standard parametric approaches could fail to provide optimal predictions. We compared the volatility forecasts generated by the LSTM approach to those obtained through use of widely recognized benchmarks models in this field, in particular, univariate parametric models such as the Realized Generalized Autoregressive Conditionally Heteroskedastic (R-GARCH) and the Glosten–Jagannathan–Runkle Multiplicative Error Models (GJR-MEM). The results demonstrate the superiority of the LSTM over the widely popular R-GARCH and GJR-MEM univariate parametric methods, when forecasting in condition of high volatility, while still producing comparable predictions for more tranquil periods.

A new dynamic masking technique for time resolved PIV analysis

Abstract

Time resolved PIV encompassing moving and/or deformable objects interfering with the light source requires the employment of dynamic masking (DM). A few DM techniques have been recently developed, mainly in microfluidics and multiphase flows fields. Most of them require ad-hoc design of the experimental setup, and may spoil the accuracy of the resulting PIV analysis. A new DM technique is here presented which envisages, along with a dedicated masking algorithm, the employment of fluorescent coating to allow for accurate tracking of the object. We show results from measurements obtained through a validated PIV setup demonstrating the need to include a DM step even for objects featuring limited displacements. We compare the proposed algorithm with both a no-masking and a static masking solution. In the framework of developing low cost, flexible and accurate PIV setups, the proposed algorithm is made available through a freeware application able to generate masks to be used by an existing, freeware PIV analysis package.

Graphic abstract

Possible Association of Periodontal Disease and Macular Degeneration: A Case-Control Study

Oral pathogens have been identified in bioptic specimens from Age-Related Macular Degeneration (ARMD) patients, and alveolar bone loss has been related to ARMD. Therefore, the possible association between ARMD and periodontal disease was investigated in the present case-control study, evaluating clinical and radiographic periodontal parameters, primarily, in cases vs. controls and, secondarily, in relation to ARMD risk factors, in cases, to highlight a possible pathogenic link between the disorders. Forty ARMD cases and 40 non-ARMD controls, matched for age (±3 years) and gender and homogeneous for ARMD risk factors, therefore comparable, underwent full-mouth periodontal charting, panoramic radiograph, and medical data, including ARMD risk factors, collection. Statistical analysis was conducted using the language R. Comparisons between groups were made using both traditional t-tests and Yuen’s test with bootstrap calibration. Enrolled subjects were ≥55 years old, and 50 females and 30 males were equally distributed among the two groups. No statistically significant difference was found in clinical and radiographic periodontal parameters in cases vs. controls. In the case group, no differences were found when relating the periodontal parameters to ARMD risk factors, except for Clinical Attachment Level values that were statistically significantly higher in hypertensive ARMD subjects. A possible association between periodontal disease and ARMD may be hypothesized in hypertensive ARMD subjects, with hypertension as a possible pathogenic link between the disorders.

Suitability of 2D modelling to evaluate flow properties in 3D porous media

The employment of 2D models to investigate the properties of 3D flows in porous media is ubiquitous in the literature. The limitations of such approaches are often overlooked. Here, we assess to which extent 2D flows in porous media are suitable representations of 3D flows. To this purpose, we compare representative elementary volume (REV) scales obtained by 2D and 3D numerical simulations of flow in porous media. The stationarity of several quantities, namely porosity, permeability, mean and variance of velocity, is evaluated in terms of both classical and innovative statistics. The variance of velocity, strictly connected to the hydrodynamic dispersion, is included in the analysis in order to extend conclusions to transport phenomena. Pore scale flow is simulated by means of a Lattice Boltzmann model. The results from pore scale simulations point out that the 2D approach often leads to inconsistent results, due to the profound difference between 2D and 3D flows through porous media. We employ the error in the evaluation of REV as a quantitative measure for the reliability of a 2D approach. Moreover, we show that the acceptance threshold for a 2D representation to be valid strongly depends on which flow/transport quantity is sought.

Relugolix for the treatment of uterine fibroids

INTRODUCTION

Uterine fibroids (UF) are benign tumors common in premenopausal women, with strong impact on the health-care systems. For many years, surgery represented the only therapy for symptomatic fibroids. However, clinicians are observing a switch from surgery to noninvasive methods; in particular, medical treatment has been shown to be efficacious in obtaining a bleeding reduction and in ameliorating patient conditions.

AREAS COVERED

The authors review the current options available for the treatment of women with UF, with a special focus on the newest one, relugolix. It is an orally active non-peptide Gonadotropin-releasing hormone (GnRH)-receptor antagonist recently licensed for women with symptomatic fibroids. Relugolix is a well-tolerated safe drug; it is effective in inducing a dose-dependent decrease in menstrual blood loss, with faster reduction of heavy menstrual bleeding (HMB) and a greater shrinkage in fibroid volume compared to the current standard of GnRH agonist treatment.

EXPERT OPINION

Relugolix is a promising drug for the non-surgical treatment of women with UF. To date, the only published data come from a well-selected Japanese female population study while results from worldwide ongoing studies are ongoing in order to confirm the efficacy of this GnRH agonist receptor.

Nonlinear autoregressive sieve bootstrap based on extreme learning machines

The aim of the paper is to propose and discuss a sieve bootstrap scheme based on Extreme Learning Machines for non linear time series. The procedure is fully nonparametric in its spirit and retains the conceptual simplicity of the residual bootstrap. Using Extreme Learning Machines in the resampling scheme can dramatically reduce the computational burden of the bootstrap procedure, with performances comparable to the NN-Sieve bootstrap and computing time similar to the ARSieve bootstrap. A Monte Carlo simulation experiment has been implemented, in order to evaluate the performance of the proposed procedure and to compare it with the NN-Sieve bootstrap. The distributions of the bootstrap variance estimators appear to be consistent, delivering good results both in terms of accuracy and bias, for either linear and nonlinear statistics (such as the mean and the median) and smooth functions of means (such as the variance and the covariance).

A 5-year longitudinal cohort study on crown to implant ratio effect on marginal bone level in single implants

BACKGROUND

A 5-year longitudinal cohort study was carried out to evaluate the influence of anatomical crown to implant ratio (CIR) on peri-implant marginal bone level (MBL) in single implants.

MATERIALS AND METHODS

The longest possible implants, according to the availability of pristine bone, were inserted, one per patient, among periodontally healthy teeth in consecutively recruited subjects. CIR and MBL changes were measured on standardized radiographs. The relationship between MBL and multiple predictors was investigated. A statistical analysis suitable for mixed type distributions was conducted: for the discrete component a logistic regression model was used and for the continuous component the impact of the variables on MBL was examined by using robust nonparametric comparison tests.

RESULTS

Seventy-eight dental implants were inserted in 34 mandibles and 44 maxillae, with one stage procedure in 40 cases and two stage in 38 cases. Thirty-five implants were <10 mm, while 43 were ≥ 10 mm long; 28 implants had a CIR ≤1 and 50 had a CIR >1. No drop-outs or implant loss were observed. Bone loss occurred only in a few cases, measuring less than 0.5 mm and being significantly more pronounced for implant length ≥10 mm, for lower CIR values and for the two stage procedure.

CONCLUSION

Higher CIR values were not related to increased peri-implant bone loss; a <10 mm long implant insertion may be safely considered for reduced bone heights.

Designing neural networks for modeling biological data: a statistical perspective

In this paper, we propose a strategy for the selection of the hidden layer size in feedforward neural network models. The procedure herein presented is based on comparison of different models in terms of their out of sample predictive ability, for a specified loss function. To overcome the problem of data snooping, we extend the scheme based on the use of the reality check with modifications apt to compare nested models. Some applications of the proposed procedure to simulated and real data sets show that it allows to select parsimonious neural network models with the highest predictive accuracy.

Neural Networks and Bootstrap Methods for Regression Models with Dependent Errors

This chapter introduces the use of the bootstrap in a nonlinear, nonparametric regression framework with dependent errors. The aim is to construct approximate confidence intervals for the regression function which is estimated by using a single hidden layer feedforward neural network. In this framework, the use of a standard residual bootstrap scheme is not appropriate and it may lead to results that are not consistent. As an alternative solution, we investigate the AR-Sieve bootstrap and the Moving Block bootstrap, which are used to generate bootstrap replicates with a proper dependence structure. Both approaches are nonparametric bootstrap schemes, a consistent choice when dealing with neural network models which are often used as an accurate nonparametric estimation and prediction tool. In this context, both procedures may lead to satisfactory results but the AR sieve bootstrap seems to outperform the moving block bootstrap delivering confidence intervals with coverages closer to the nominal levels.