Comparison of the Performances for CAPM and Fama-French models During COVID-19

Since the outbreak of COVID-19, it has caused a startling stun to both society and economy in numerous nations, where different industries suffered unequally. This paper reviews the various performance of the Capital Asset Pricing Model (CAPM), and the Fama-French three-factor model and the five-factor model in different regions and industries. To metric the performance, various statistics models and scaling are applied including Pearson correlation, linear regression, R2 scores, t-test, etc. Specifically, this paper demonstrates the different performances of the CAPM model on the US and Egyptian stock markets, whereas using generalized method of moments in a panel data analysis to evaluate the performance in the U.S. market and the paired sample t-test and Wilcoxon signed-rank to evaluate the performance in the Egyptian market. The Fama-French three-factor model and five-factor model are both based on the U.S. market and analyze the model's performance (measured by significant level) in the U.S. market in general and in individual sectors, respectively. Whereas, in terms of three-factors model, the OLS estimation and relapse expected excess return are used onto the variables and multiple linear regression method was used to study the significance of factors in three sub-industries. Regarding to five-factors model, a multivariate regression with covariates and OLS estimation are the method for evaluation. These results shed light for deeply understanding the model and recognizing the impact on the security market of the COVID-19. © 2023 SPIE.

A comparative study for COVID-19 cases forecasting with loss function as AIC and MSE in RNN family and ARIMA

Forecasting COVID-19 incidents is a trending research study in today's world. Since Machine learning models have been occupied in forecasting recently, this study focus on comparing statical and machine learning models such as ARIMA, RNN, LSTM, Seq2Seq, and Stacked LSTM. The performances were evaluated using two loss functions, namely, AIC and RMSE. The results showed that RNN performs with the lowest RMSE with-49.5% compared with the ARIMA. Seq2Seq scored the highest correlation of determination (R2) with 0.92. © 2022 IEEE.

D-Dimer Elevation Matters to Predict COVID-19 Severity: A Machine Learning Approach

Although previous studies using limited data have documented an association of D-dimer levels with COVID-19 severity, the role of D-dimer in the progression of COVID-19 remains unclear and requires further investigation using data from larger cohorts. We used traditional statistical modeling and machine learning methods to examine critical factors influencing the D-dimer elevation and to characterize associated risk factors of D-dimer elevation over the course of inpatient admission. We identified 20 important features to predict D-dimer levels, some of which could be used to predict and prevent the D-dimer elevation. Laboratory monitoring of D-dimer level and its risk factors at early stage can mitigate severe or death cases in COVID-19. © 2022 IEEE.

COVID-19 in Bangladesh: An Exploratory Data Analysis and Prediction of Neurological Syndrome Using Machine Learning Algorithms Based on Comorbidity

COVID-19 is caused by the SARS-CoV-2 virus, which has infected millions of people worldwide and claimed many lives. This highly contagious virus can infect people of all ages, but the symptoms and fatality are higher in elderly and comorbid patients. Many COVID-19 survivors have experienced a number of clinical consequences following their recovery. In order to have better knowledge about the long-COVID effects, we focused on the immediate and post-COVID-19 consequences in healthy and comorbid individuals and developed a statistical model based on comorbidity in Bangladesh. The dataset was gathered through a phone conversation with patients who had been infected with COVID-19 and had recovered. The results demonstrated that out of 705 patients, 66.3% were comorbid individuals prior to COVID-19 infection. Exploratory data analysis showed that the clinical complications are higher in the comorbid patients following COVID-19 recovery. Comorbidity-based analysis of long-COVID neurological consequences was investigated and risk of mental confusion was predicted using a variety of machine learning algorithms. On the basis of the accuracy evaluation metrics, decision trees provide the most accurate prediction. The findings of the study revealed that individuals with comorbidity have a greater likelihood of experiencing mental confusion after COVID-19 recovery. Furthermore, this study is likely to assist individuals dealing with immediate and post-COVID-19 complications and its management. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

A Relationship Between the SIR Model and the Generalized Logistic Distribution with Applications to SARS and COVID-19

This paper shows that the generalized logistic distribution model is derived from the well-known compartment model, consisting of susceptible, infected and recovered compartments, abbreviated as the SIR model, under certain conditions. In the SIR model, there are uncertainties in predicting the final values for the number of infected population and the infectious parameter. However, by utilizing the information obtained from the generalized logistic distribution model, we can perform the SIR numerical computation more stably and more accurately. Applications to severe acute respiratory syndrome (SARS) and Coronavirus disease 2019 (COVID-19) using this combined method are also introduced. © 2021 IEEE.

Comparative analysis of Covid- 19 Data: A statistical approach for unraveling the relation between the awareness and healthcare system from Indian perspective

The Novel Corona virus disease caused by SARS-Cov-2 has been declared pandemic by WHO as it unanimously effected almost all the provinces over the globe. It has incapacitated poorer nations as well as paralyzed the healthcare system of world's major economies like Europe and America. Several regulations and measures were put into place to control the spread of the virus and Statistical models been deduced for evaluating the infections in real time. In the present research, Python 3 and kaggle has been applied for data analysis of the dataset retrieved from the various Indian states. An attempt has been made to draw a conclusive relation between the healthcare systems and the awareness as regard to covid infections. There was positive and high co-relation (>0.95) values for total confirmed cases -discharged and first - second dose of vaccinations. A positive and high co relation value of 0.78 was obtained when plotted for total covid tests performed against vaccination while a negative co relation of value -0.117 obtained when percentage covid positive amongst the sample tested was plotted against the total covid test performed. This statistical analysis aid in understanding overall healthcare system of a state and immunity amongst Indian population © 2022 IEEE.

Forecasting Diurnal Covid-19 Cases for Top-5 Countries Using Various Time-series Forecasting Algorithms

On January 30, 2020, the World Health Organisation classified the Covid-19 outbreak a Public Health Emergency of International Concern, and a pandemic was proclaimed on March 11, 2020. Two years after the Covid-19 outbreak, the virus has new transmutations plus is turning out to be more difficult for forecasting in terms of both its behaviour and severity. Various techniques for time series analysis of coronavirus (Covid-19) cases were examined in this study. The Deep Learning model chosen, Long Short-Term Memory (LSTM) is compared against Statistical approaches, such as Linear Regression, Auto-Regressive Integrated Moving Average (ARIMA), and Seasonal Auto-Regressive Integrated Moving Average (SARIMA), based on a variety of performance metrics. Following the estimates of the superior algorithm, medical care professionals can act at the appropriate moment to supply Equipment to health care institutions and further help the public. According to our data, as the number of projected days grows, so does the model's error rate. Forecasted trends also suggest that statistical approaches are relatively better overall for predictions of fewer days, but Deep Learning methods are relatively better for forecasts of more days. © 2022 IEEE.

Modelling New Cases of Covid-19 in the Philippines using Polynomial and MLP Regression

Covid-19 has been a serious issue in the Philippines for the past two years. Its spread has taken a toll on the country's economy and society. Furthermore, the populous has been suffering throughout the pandemic as new cases and deaths are increasing. These massive problems warrant research on modelling and predicting this pandemic. Although there are numerous research with regards to using statistical modelling, Machine learning, deep learning, and artificial intelligence to model and understand the pandemic throughout the world, few pieces of researches focus on the Philippines alone. In addition to that, simple models are seen to fit the Covid-19 data more than complex ones. With these in mind, the authors fit and modelled Philippine new cases of Covid-19 using Sklearn Polynomial and MLP regressors. It was found out that Polynomial models fit the entire dataset from January 2020 to September 2021, but MLP model fits the recent September 2021 data better. Further research using different countries as case studies or different models is recommended. © 2021 IEEE.

Statistical Modelling with Machine Learning for COVID-19 Prediction

As of December 2019, the world's view fashionable contact past events give birth been replaced because unending COVID-19 entire. This demand the use of a great deal methodical study of part of material world to help label corona-virus human being existence medicate for healing question and control the spread of this mild sickness. This paper is related to the computer network;looking into survive developed as a finish at hand together facts imperceptible form. This news imperceptible form exist secondhand as an approval for diversified official proclamation fashioned earlier models establish mathematical model (Logistic Regression, LR) and well-run political organization ability to perceive model (Support Vector Machine, SVM, and Multi-Layer Perception, MLP). These models come to pass use to express an outcome earlier potential person being treated for medical problem of COVID-19 demonstrate their signs and sign of disease or question. The MLP bear stage a performance display highest in rank accuracy or propriety (91.62%) outstanding to the added models. Meanwhile, the SVM give birth proved topmost fashionable rank precision or correctness 91.67%. © 2021 IEEE.

Improving Neural Networks for Time-Series Forecasting using Data Augmentation and AutoML

Statistical methods such as the Box-Jenkins method for time-series forecasting have been prominent since their development in 1970. Many researchers rely on such models as they can be efficiently estimated and also provide interpretability. However, advances in machine learning research indicate that neural networks can be powerful data modeling techniques, as they can provide higher accuracy for a plethora of learning problems and datasets. In the past, they have been tried on time-series forecasting as well, but their overall results have not been significantly better than the statistical models especially for intermediate length times-series data. Their modeling capacities are limited in cases where enough data may not be available to estimate the large number of parameters that these non-linear models require. This paper presents an easy to implement data augmentation method to significantly improve the performance of such networks. Our method, Augmented-Neural-Network, which involves using forecasts from statistical models, can help unlock the power of neural networks on intermediate length time-series and produces competitive results. It shows that data augmentation, when paired with Automated Machine Learning techniques such as Neural Architecture Search, can help to find the best neural architecture for a given time-series. Using the combination of these, demonstrates significant enhancement in the forecasting accuracy of three neural network-based models for a COVID-19 dataset, with a maximum improvement in forecasting accuracy by 21.41%, 24.29%, and 16.42%, respectively, over the neural networks that do not use augmented data. © 2021 IEEE.

Feature Based Statistical Model of Employee Productivity with Real Time Checked Data

The COVID-19 pandemic has led to a decentralization of the workforce in many industries. Due to the stay-at-home orders to control the spread of the virus, many are working from home. Even though modern technological advancements have helped some companies adapt to this new norm, many others are still scrambling to find the best way to remotely manage employees and accommodate their needs. Our research shows that the current challenges organizations face in managing their human capital are like the ones they face due to workplace demographic changes. This study focuses on analyzing those challenges and how human competency can be unlocked and developed to encourage sustainable autonomous working in an office, at home, or during frequent traveling. This study investigates the challenges faced by both organizations and employees, and presents a new business model that helps with the sustainable use of human resources and improves employee efficiency. © 2021 IEEE.

Empirical Quantitative Analysis of COVID-19 Forecasting Models

COVID-19 has been a public health emergency of international concern since early 2020. Reliable forecasting is critical to diminish the impact of this disease. To date, a large number of different forecasting models have been proposed, mainly including statistical models, compartmental models, and deep learning models. However, due to various uncertain factors across different regions such as economics and government policy, no forecasting model appears to be the best for all scenarios. In this paper, we perform quantitative analysis of COVID-19 forecasting of confirmed cases and deaths across different regions in the United States with different forecasting horizons, and evaluate the relative impacts of the following three dimensions on the predictive performance (improvement and variation) through different evaluation metrics: model selection, hyperparameter tuning, and the length of time series required for training. We find that if a dimension brings about higher performance gains, if not well-tuned, it may also lead to harsher performance penalties. Furthermore, model selection is the dominant factor in determining the predictive performance. It is responsible for both the largest improvement and the largest variation in performance in all prediction tasks across different regions. While practitioners may perform more complicated time series analysis in practice, they should be able to achieve reasonable results if they have adequate insight into key decisions like model selection. © 2021 IEEE.

Interactive Visualization for Statistical Modelling through a Shiny App in R

The importance of analytics and visualization tools has been growing over the last decades to handle big data which steamed from all aspects of life. The focus of this paper was on visualization as a crucial tool in presenting complex raw data and modelling results to provide easy-to-understand actionable information that facilitate decision-making. However, limited research distinguished between 'data visualization' and 'model visualization', which has been clearly made in this paper. Furthermore, this paper aimed to shed light on the importance of interactive visualizations to compliment statistical data modelling using R and Shiny for its advanced capabilities. Specifically, a methodology has been proposed based on a hybrid development lifecycle that adopts the Agile Software Development Lifecycle and the Data Analytics Lifecycle. Finally, by presenting a case study to model the dynamics of COVID-19, it was found that R and Shiny alongside the proposed hybrid development lifecycle significantly reduced the amount of time required to build visually interactive applications. The reported results highlighted the effectiveness of the adopted approach in assisting and guiding researchers and developers in building interactive applications that leverage Big Data Analytics. © 2021 IEEE.

Intelligent Forecasting Strategy for COVID-19 Pandemic Trend in India: A Statistical Approach

In recent times, an infectious disease namely COVID-19 has affected a large number of individuals. Forecasting models have been helpful in predicting the possible number of confirmed cases, deaths, and recovery counts in the future. In this paper, the prediction of COVID-19 cumulative confirmed cases and deaths for India is analyzed based on various statistical models such as (a) time series, (b) machine learning, and (c) ensemble learning. Autoregressive integrated moving average (ARIMA) and Holt-Winters exponential smoothing in time series;support vector regression (SVR) and linear regression (LR) in machine learning (ML) and random forest regression in ensemble learning (EL) have been implemented for predictions. The accuracies of the trained models are evaluated using metrics such as R-squared value, root mean squared error (RMSE), mean squared error (MSE), mean absolute errors (MAE), and mean absolute percentage error (MAPE). The proposed forecasting models can be used to monitor the rise in COVID-19 cases which can thereby be helpful for government officials to make required changes to their system. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.