Modeling of Machine Learning-Based Extreme Value Theory in Stock Investment Risk Prediction: A Systematic Literature Review

The stock market is heavily influenced by global sentiment, which is full of uncertainty and is characterized by extreme values and linear and nonlinear variables. High-frequency data generally refer to data that are collected at a very fast rate based on days, hours, minutes, and even seconds. Stock prices fluctuate rapidly and even at extremes along with changes in the variables that affect stock fluctuations. Research on investment risk estimation in the stock market that can identify extreme values is nonlinear, reliable in multivariate cases, and uses high-frequency data that are very important. The extreme value theory (EVT) approach can detect extreme values. This method is reliable in univariate cases and very complicated in multivariate cases. The purpose of this research was to collect, characterize, and analyze the investment risk estimation literature to identify research gaps. The literature used was selected by applying the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) and sourced from Sciencedirect.com and Scopus databases. A total of 1107 articles were produced from the search at the identification stage, reduced to 236 in the eligibility stage, and 90 articles in the included studies set. The bibliometric networks were visualized using the VOSviewer software, and the main keyword used as the search criteria is "VaR." The visualization showed that EVT, the Generalized Autoregressive Conditional Heteroskedasticity (GARCH) models, and historical simulation are models often used to estimate the investment risk; the application of the machine learning (ML)-based investment risk estimation model is low. There has been no research using a combination of EVT and ML to estimate the investment risk. The results showed that the hybrid model produced better Value-at-Risk (VaR) accuracy under uncertainty and nonlinear conditions. Generally, models only use daily return data as model input. Based on research gaps, a hybrid model framework for estimating risk measures is proposed using a combination of EVT and ML, using multivariable and high-frequency data to identify extreme values in the distribution of data. The goal is to produce an accurate and flexible estimated risk value against extreme changes and shocks in the stock market. Mathematics Subject Classification: 60G25; 62M20; 6245; 62P05; 91G70.

The effect of artificial diet made of soybeans (Glycine max L.) on the rearing of Spodoptera frugiperda (Lepidoptera:Noctuidae)

Spodoptera frugiperda is a novel invasive pest of maize crops. Therefore, studies on this pest are limited. Research on the use of artificial diets in S. frugiperda larvae rearing is essential to facilitate the provision of test larva stocks for lab-scale study purposes. The aim of this research was to figure out the effect of an artificial diet from soybeans as a protein source on S. frugiperda rearing. The parameters observed in this research were larval-stage longevity, larval survival rate, pupa size, sex ratio, pupal-stage longevity, pupal survival rate, fecundity, and nutritional index. The results showed that an artificial diet with soybeans had a significant effect on sex ratio, pupal survival rate, relative consumption rate (RCR) 4.89 g/g/day (4th instar); 1.99 g/g/day (5th instar), approximate digestibility (AD) 98.39% (4th instar); 95.45% (5th instar), and fecundity, but it did not have any significant effect on larval-stage longevity, larval survival rate, pupa size, pupal-stage longevity, the efficiency of conversion of ingested food (ECI) 3.68% (4th instar); 7.84% (5th instar), and efficiency of conversion of digested food (ECD) 3.76% (4th instar); 8.27% (5th instar). Artificial diet-based soybean was highly potential to be used in S. frugiperda rearing.

P418 CARDIOMETABOLIC ALTERATIONS IN OBESE PATIENTS WITH OBSTRUCTIVE SLEEP APNEA SYNDROME

Background

Obesity and Obstructive Sleep Apnea Syndrome (OSAS) has been recognized as two of the major cardiac risk factors and they often coexist in one patient. OSAS increase the risk of as myocardial infarction, heart failure and arrhythmias. On the other hand, obesity is and independent predictor of cardiovascular mortality since it causes insulin resistance, dyslipidemia, sympathetic hyperactivation, chronic inflammation and endothelial dysfunction.

Aim

To evaluate cardiometabolic profile, echocardiographic alterations and the presence of arrhythmias in obese patients with Obstructive Sleep Apnea Syndrome and non obese patients.

Patients and Methods

67 obese patients (37 male/30 female) and 52 non obese patients (40 male/12 female) were enrolled. All subjects underwent anthropometrical evaluation and a venous blood sample for biochemical and hormonal determinations including fasting plasma glucose, fasting plasma insulin, Hba1c and OGTT to 5 hours. The insulin resistance was evaluated by HOMA–IR. All the patients underwent echocardiographic examination, polysomnographic evaluation, in order to diagnose the OSAS, and a simultaneous 12–lead Holter ECG to evaluate the presence of nocturnal arrhythmias.

Results

As expected, we found a better antropometrics profile in non obese patients. Obese patients display a severe OSAS compared to non–obese patient as shown by higher values of AHI (26.37 ±24.95 vs 16.58 ±14.07; P < 0.05), TC90 (19.61 ±24.45 vs 8.63 ±17.80; P < 0.05) and ODI (40.55 ±27.41 vs 21.06 ±22.78; P < 0,05). In obese patients we also found a significant reduction of both ejection fraction (55.54 ±7.97 vs 66.52 ±8.95; P < 0.05) and A–wave (0.75 ±0.17 vs 0.83 ±0.19; P < 0.05). In 20% of obese patients, 12–lead Holter ECG showed the presence of cardiac pause > 3 sec during apnea. In obese population alone we demonstrated a significant negative correlation between AHI and E–wave (r= –0.3; P = 0.04) and a positive correlation with interventricular septum (r = 0.38; P = 0.01) and left ventricular mass (r = 0.32; P = 0.02). Post–hoc analysis shown how these findings maintained statistical significance even when the obese patients were stratified in subgroups according to the severity of OSAS.

Conclusions

Our data, even if preliminary, seem to indicate that OSAS is not only linked to obesity but it also acts as a negative factor on the cardiometabolic risk.

C72 THE EFFECTS OF BATRIATIC SURGERY ON CARDIO–METABOLIC PROFILE AND CARDIAC REMODELING

Background

Obesity is associated with cardiac remodeling resulting in hypertrophy of the left ventricle (LV) with a predominantly concentric pattern. LV remodeling and fibrosis induce mechanical and electrical dysfunction of the myocardial tissue, an increase in cardiac output, an increase of myocardial workload and mean arterial pressure.

Objective

To evaluate the impact of bariatric surgery, and therefore of anthropometric and cardio–metabolic variations, on cardiac structure and function.

Methods

Twenty–six obese patients treated with bariatric surgery were enrolled. All the patients at baseline and at 6 and 12 months underwent a complete anthropometrical evaluation, laboratory determinations and echocardiogram evaluation. The IR has been assessed by HOMA–IR. The patients were divided into two groups: the first group (8 patients) carried out a follow–up at 6 months post–surgery; the second group (18 patients) at 12 months post–surgery.

Results

As expected, an improvement in the anthropometric and metabolic profile in patients treated with bariatric surgery was observed. Echocardiographic data showed a significant increase in the Ejection Fraction (P < 0.001) and the E/A Ratio (P < 0.001) 6 months after bariatric surgery, a significant reduction in the Interventricular Septum thickness at 6 months (P < 0.001) and at 12 months (P < 0.002) post–surgery and a significant reduction in the Left Ventricular Mass at 6 months (P = 0.02) and at 12 months (P = 0.05) after bariatric surgery. A reduction no significant in the Left Ventricular posterior wall thickness has been observed.

Conclusions

Our data showed an increase of the systolic function, an increase of the left ventricular diastolic compliance and a reduction in subclinical cardiac organ damage. Therefore, significant weight loss obtained with bariatric surgery may lead to reverse cardiac remodeling, associated with beneficial effects on myocardial structure and systo-diastolic function.

A Cytotoxic Flavanone from The Pod Peels of Theprosia vogelii Hook.f

Tephrosia vogelii Hook.f. is a species of the family Fabaceae (Leguminoceae). These plants are termed ″Polong-polongan″ in Indonesia, and are known to contain active flavonoid groups. Previous studies have shown the isolation of one known flavanone: isolonchocarpin from methanol extract, and the structure obtained was established based on chemical evidence as well as spectroscopic methods, including NMR, and also by a comparison with published data. This research is aimed at evaluating the cytotoxic property of methanol extract against larvae of Arthemia salina Leach, using the Brine Shrimp Lethality Test (BSLT) method. The results show potent cytotoxicity at LC50 of 41.40 ppm.