Over the past few decades, business analytics has been widely used in various business sectors and has been effective in increasing enterprise value. With the advancement of science and technology in the Big Data era, business analytics techniques have been changing and evolving rapidly. Therefore, this paper reviews the latest techniques and applications of business analytics based on the existing literature. Meanwhile, many problems and challenges are inevitable in the progress of business analytics. Therefore, this review also presents the current challenges faced by business analytics and open research directions that need further consideration. All the research papers were obtained from the Web of Science and Google Scholar databases and were filtered with several selection rules. This paper will help to provide important insights for researchers in the field of business analytics, as it presents the latest techniques, various applications and several directions for future research.
The joint replenishment problem has been extensively studied and the joint replenishment strategy has been adopted by a large variety of retailers in recent years. However, the joint replenishment problem under minimum order quantity and other constraints does not receive sufficient attention. This paper analyzes a retailing supply chain involving a supplier that provides quantity discount schedules and limits the order quantity. The order quantity constraints include minimum order requirements for each item and as to the total quantity; additionally, the latter cannot exceed the transport capacity constraint. These are common constraints in the retail industry today and create greater complexity and difficulty in the retailer’s decision-making. To analyze the problem, an integer nonlinear programming model is set up to maximize retailers’ profit with all practical constraints. A two-layer efficient algorithm named the Marginal and Cumulative Profit-Based Algorithm (MCPB) is then proposed to find whether to order and the optimal order quantity for each item. The results of computational experiments show that the proposed algorithm can find near-optimal solutions to the problem efficiently and is a reference for retailers to solve practical joint replenishment problems.
Healthcare expenditures in Australia have grown steadily in recent years, intensifying fiscal pressures and exposing challenges related to unequal resource distribution. While traditional statistical methods struggle to capture complex data relationships, machine learning offers a more robust approach to handling intricate and non-linear data. This study employs machine learning techniques to investigate the key determinants of healthcare expenditures in Australia from 2011 to 2021. Using advanced models, including Random Forest, XGBoost, and Multi-Layer Perceptron (MLP), along with SHAP (SHapley Additive exPlanations) analysis, we identify the most influential factors driving healthcare spending. The results reveal that funding sources, public hospital services, and geographic disparities are the primary predictors of expenditure trends. Notably, funding allocation mechanisms and regional inequities emerge as critical influences on spending patterns. By integrating feature importance metrics with SHAP analysis, this study enhances model interpretability and offers actionable insights for policymakers. The findings underscore the urgent need to optimize resource allocation and address regional disparities to promote the sustainability and equity of Australia’s healthcare system.