Journal of Business Management and Entrepreneurship

Machine Learning-Driven Reliability Engineering for E-Commerce Sites: A Study on Browsing, Cart, and Checkout Phases

Divya Soundarapandian — 2024-08-03

This study explores reliability engineering in e-commerce systems by analyzing critical user journey stages – browsing, cart, and checkout – using advanced machine learning models. The research uses random forest regression (RFR) and support vector regression (SVR) to assess and predict system performance, stability, and potential failure points. Data was obtained from simulated e-commerce transactions that included key parameters such as response time, server load, transaction success rate, and error frequency. The models were evaluated using statistical indicators including coefficient of determination (R²), mean square error (MSE), and mean absolute error (MAE) to measure predictive accuracy. The results indicated that both models achieved high reliability and accuracy, with SVR showing slightly higher generalization ability. The findings highlight that predictive modeling can effectively identify performance bottlenecks, reduce downtime, and improve the overall robustness of e-commerce operations. By integrating reliability engineering principles with machine learning techniques, this study contributes to improving user experience, enhancing system resilience, and ensuring scalable and stable online transaction environments. This hybrid analytics approach provides a foundation for developing proactive monitoring strategies in modern e-commerce infrastructures.

Artificial Intelligence for Accurate Service Level Assessment in Modern Inventory Management

Naidu Paila — 2024-08-03

Healthcare supply chains operate under conditions of high product variety, strict regulatory oversight, and time-critical demand, where supply disruptions may directly affect patient care. Planning and forecasting in these environments are often supported by rule-based systems and traditional statistical methods, which can struggle to accommodate demand variability and network complexity.

This study examines the application of data-driven optimization methods to healthcare supply chain planning using operational data collected over a 24-month period. The proposed framework integrates demand forecasting, service-level modeling, and multi-echelon inventory optimization within an enterprise planning environment. Statistical modeling and predictive analytics are used to support planning decisions across multiple echelons of the supply chain.

The analysis draws on data covering more than 10,000 product SKUs, over 150 hospital locations, and approximately 500,000 surgical procedures. Empirical results indicate sustained improvements in service levels and inventory efficiency, including a 14.78 percentage-point increase in True Service Level, the elimination of 1,857 documented kit shortages, a reduction of $144.2 million in global inventory, and a 55.3% improvement in forecast accuracy. These outcomes were achieved without compromising supply continuity.

Overall, the findings suggest that advanced analytics, when embedded within established planning processes, can materially improve healthcare supply chain performance. The study provides evidence from a large-scale implementation and may inform future applications of analytics-based optimization in regulated healthcare settings.

Executive Summary

Research represents a large-scale applied implementation of AI- and ML-driven optimization methods within a healthcare supply chain context, leveraging advanced Artificial Intelligence (AI) and Machine Learning (ML) algorithms to revolutionize inventory management, demand forecasting, and service level optimization. This research journal documents the comprehensive development, implementation, and measurable impact of three core algorithmic solutions:

True Service Level Algorithm - Ensuring surgical kit availability
Multi-Echelon Inventory Optimization (MEIO) - Reducing $300M in global inventory
PlanAI - Advanced demand forecasting with 55.3% accuracy improvement

Key empirical outcomes observed during the study period include $144.2M inventory reduction achieved (48.1% of $300M target) - 14.78% average improvement in True Service Level - 1,857 surgical kit shortages eliminated - 55.3% improvement in forecasting accuracy - $105M cumulative cost savings

Banking Service Evaluation in the Digital Age: A Comprehensive Analysis Using the VIKOR Method

Sushil Prabhu Prabhakaran — 2024-11-05

This study uses the VIKOR methodology to evaluate and rank various banking options, focusing on core banking features, digital capabilities, business-specific services, and value-added services. The research analyses five distinct banking types: digital-only banks, traditional credit unions, and online business banking platforms, specialty banks, and crypto banking solutions. Through a systematic evaluation using the VIKOR methodology, which is designed to address decision-making problems across multiple criteria, the study provides detailed rankings and this assessment highlights the varying strengths and weaknesses of each banking option. Specialty banks stand out, ranking first due to their strong overall performance. Traditional credit unions, in second place, perform well in business-oriented services but are weak in other areas. Despite their moderate scores, crypto banking solutions, with significant weaknesses in digital capabilities, are in third place. Online business banking platforms are in fourth place, benefiting from value-added services but lacking in other important aspects. Although strong in digital capabilities, digital-only banks are in fifth place, with significant weaknesses in business-oriented and value-added services, making them the least competitive option.

The results reveal that specialty banks rank highest with a Qj value of 1, showing superior performance across multiple criteria. Traditional credit unions come in second place (Qj = 0.716478), followed by crypto banking solutions (Qj = 0.673956), online business banking platforms (Qj = 0.551683), and digital-only banks (Qj = 0). In particular, while digital-only banks excel in digital capabilities, their overall rankings indicate limitations in other key areas, particularly value-added services. The findings highlight that success in the banking industry requires a balanced approach that combines traditional banking strengths with modern capabilities. The study provides valuable insights for businesses selecting banking partners and for banking institutions developing strategic plans.

Furthermore, the research demonstrates the effectiveness of the VIKOR methodology in evaluating complex banking options, providing a structured approach to decision-making in the financial sector. These results contribute to understanding the evolving banking landscape and the importance of comprehensive service offerings in meeting diverse business needs.