4 research outputs found
Analysis of subjectivity on sovereign credit ratings through machine learning
No full textSovereign credit rating provided by credit rating agencies like S&P, Moody’s and Fitch has always been of great importance, but these agencies have been facing criticism on their rating methodology which create subjectivity and potential biases. This harms the image of developing economies in international markets. This research is responsible to study subjectivity, its extent and evaluate the ML methodologies for better assessment of credit ratings through objective and transparent framework. The balanced panel data consisting of ten diverse countries from 2000 to 2023 is used. The study uses factors responsible for explaining credit worthiness of a country. These factors are divided into 5 WDI (World Development Indicators) and 5 WGI (World Governance Indicators) as independent variables. The dependent variable is considered as historical credit ratings of country. Nine distinct ML algorithms were tested starting from Linear Regression (baseline), KNN, SVR, Decision Tree, Random Forest, ANN, CatBoost, XGBoost and Light GBM. Results of these algorithms were evaluated by performance metrics such as R2, Adjusted R2, RAE, RMSE, MSE, Precision, Recall and F1 score. Results of these algorithms showed that nonlinear algorithm models outperformed the traditional models. Among all models tested, Light GBM emerged as the most robust model achieving highest adjusted R2 (0.7675) and lowest prediction errors such as (RMSE 0.4263), that shows model ability to capture largest proportion of variance explained by predictors with less predictive risk. Feature importance analysis provides insights with the best paramount indicators. Those indicators are labeled as Feature “CG” (Core economic strength) and I (Institutional Quality). This study explores the potential of ML algorithms to create objective rating framework that mitigate subjectivity in rating and to assess sovereign risk in the global financial landscape
Open Licenses and Radical Shift in Digital Content Distribution.
No full textWorld Wide Web is becoming the most preferred location for academic community, librarians and other
professionals for communication, content generation and transfer. They are extensively making use of web
services such as blogs, podcast, wiki’s, digital libraries and institutional repositories for the transfer and
access of information content in digital format. Text, images, audio and video in digitized format facilitate
easy creation, transfer and duplication of information throughout networks. Reckless use and transfer of digital
content through Internet invokes threats to copyright claims of commercial content creators. This situation
force commercial publishers to make use of technology and law to ensure security and prevent unauthorized
access of digital content
Incidents on land and water, or, Four years on the Pacific coast Being a narrative of the burning of the ships Nonantum, Humayoon and Fanchon, together with many, adventures on sea and land.
No full textMicroform master no.: 10096.Master microform held by: MH.Mode of access: Internet
Comparison of Conventional Cyclophosphamide versus Fludarabine-Based Conditioning in High-Risk Aplastic Anemia Patients Undergoing Matched-Related Donor Transplantation
No full textAllogeneic stem cell transplant for high-risk aplastic anemia (AA) yields inferior results using conventional cyclophosphamide (CY)-based conditioning. The use of fludarabine (Flu)-based regimens has resulted in improved outcomes in high-risk patients. Limited data are available comparing these two conditioning regimens in such patients. We retrospectively analyzed 192 high-risk patients undergoing matched-related donor transplantation from July 2001 to December 2018. The median age was 19.5 (2–52) years. Patients were divided into 2 groups, Cy200 anti-thymocyte globulin (ATG)20 (Gp1 n = 79) or Flu120–150 Cy120–160 ATG20 (Gp2 n = 113). The risk of graft failure was significantly higher in Gp1, and the majority occurred in patients with >2 risk factors (p = 0.02). The incidence of grade II-IV acute graft versus host disease (GVHD) and chronic GVHD was not significantly different between the two groups. The overall survival (OS) of the study cohort was 81.3 %, disease-free survival (DFS) 76.6 % and GVHD-free relapse-free survival (GRFS) was 64.1%. DFS and GRFS were significantly higher in Gp2 as compared to Gp1: DFS 84.1% versus 68.4 % (p = 0.02), GRFS 77.9% versus 54.4% (p = 0.01), respectively. We conclude that Flu-based conditioning is associated with superior OS, DFS and GRFS as compared to the conventional Cy-based regimen in high-risk AA
