Forecasting the Pakistan’s Leading Stock Exchange During Covid-19 Using Machine learning (ML) Algorithms: Model Development and Validation (preprint)

During COVID-19, marketing shows sharp fluctuation in upward and downward trends. Forecasting price actions is one of the most challenging problems in this situation. It is challenging to build an accurate model, which integrates economic and Covid-19 variables as input for KSE index prediction. To tackle this problem, our proposal comprises applying machine learning (ML) techniques to predict the KSE during Covid-19. The principal aim of this study is to examine accuracy of combined models with individual models to forecast the Karachi Stock Exchange during COVID-19. This study has analyzed the indices of KSE from March 1st, 2020, to November 26th, 2021. Therefore, this study is keen to find the best-fitted model that forecasts more accurately during the pandemic. To select the most suitable machine learning technique, the six inferred models (i.e., Linear regression (LR), Artificial Neural Network (ANN), Regression Tree (RT), Random Forests (RF), (KNN), and Support Vector Regression (SVR)) are selected to forecast the Karachi Stock Exchange During Covid-19. Performance metrics (i.e., MAE, MSE, MAPE, and R2) are applied to measure and compare accuracy. The modeling outputs presented the RF model provided the best performance of 0.98 versus the other models in predicting the KSE100 index. Thus, the addition of ML methods improves the exchange indications and the competitiveness of future trading guidelines. These projections helped the government to make strategies for the stock exchange KSE-100 and fight against a pandemic disease. The results suggest that the performance of the KSE-100 index can be predicted with machine-learning techniques.

Disparities in critical care resources across Pakistan – findings from a national survey (preprint)

Background: In response to the COVID-19 pandemic, concerted efforts were made by provincial and federal governments to invest in critical care infrastructure and medical equipment to bridge the gap of resource-limitation in Intensive Care Units (ICUs) across Pakistan. An initial step in creating a plan towards strengthening Pakistan’s baseline critical care capacity was to carry out a needs-assessment within the country to assess gaps and devise strategies for improving the quality of critical care facilities.  Methods: To assess the baseline critical care capacity of Pakistan, we conducted a series of cross-sectional surveys of hospitals providing COVID-19 care across the country. These hospitals were pre-identified by the Health Services Academy (HSA), Pakistan. Surveys were administered via telephonic and on-site interviews and based on a unique checklist for assessing critical care units which was adapted from the Partners in Health 4S Framework, which is: Space, Staff, Stuff, and Systems. These components were scored, weighted equally, and then ranked into quartiles.  Results: A total of 106 hospitals were surveyed, with the majority being in the public sector (71.7%) and in the metropolitan setting (56.6%).  We found infrastructure, staffing, and systems lacking as only 19.8% of hospitals had negative pressure rooms and 44.4% had quarantine facilities for staff. Merely 36.8% of hospitals employed accredited intensivists and 54.8% of hospitals maintained an ideal nurse-to-patient ratio. 31.1% of hospitals did not have a staffing model while 37.7% of hospitals did not have surge policies. On chi-square analysis, statistically significant differences (p<0.05) were noted between public and private sectors along with metropolitan versus rural settings in various elements. Almost all ranks showed significant disparity between public-private and metropolitan-rural settings, with private and metropolitan hospitals having a greater proportion in the 1st rank, while public and rural hospitals had a greater proportion in the lower ranks. Conclusion: Pakistan has an underdeveloped critical care network with significant inequity between   public-private and metropolitan-rural strata. We hope for future resource allocation and capacity development projects for critical care in order to reduce these disparities.