Daily Archives: August 19, 2026

Authors: Assistant Professor Vinay.M, Assistant Professor Raghuvarancheerla

Abstract: The blockchain technology has emerged as one such revolutionary solution to solving some major problems in the field of supply chain management that include information asymmetry, non-traceability, frauds and inefficiencies. In this paper, a novel methodology for managing the supply chain through the use of blockchain technology and improved consensus mechanism is proposed. The proposed methodology incorporates the use of permissioned blockchain along with an improved consensus algorithm known as the Delegated Proof of Stake (DPOS) which uses the concept of reputation-based voting and incentives. The performance improvements of the proposed system have been validated through the agent-based simulations of a four-tier supply chain model and are observed to be as high as 30.8% in service level improvement, 23.7% in cost saving and 30.8% in inventory reduction.

DOI: https://doi.org/10.5281/zenodo.22012991

Published by: vikaspatanker

Authors: Assistant Professor Subhadip Sarkar, Assistant Professor Ms. Preeta Rajiv Sivaraman

Abstract: Employee turnover is a challenging situation for any organization because of high associated costs related to recruitment and training of new employees as well as losing organizational knowledge. This research aims to examine how machine learning can be used in predictive analytics in managing employee turnover through the use of the IBM HR Analytics data set. Five models including Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, and Gradient Boosting were tested systematically. It was revealed that ensemble models such as Random Forest have the highest predictive accuracy and AUC equal to 87.3% and 0.9348, respectively. Overtime, job satisfaction, monthly income, and tenure are found to be important factors affecting employee turnover. These results show that machine learning may change HR practices from reactive to proactive retention strategies based on data analysis.

DOI: https://doi.org/10.5281/zenodo.22012826

Published by: vikaspatanker

Authors: Assistant Professor M Sravan Kumar Babu, Assistant Professor Devanshi Hemal Shah

Abstract: Robotic Process Automation (RPA) in combination with Artificial Intelligence (AI) has become a revolutionizing paradigm for enterprise automation that allows for surpassing the boundaries of traditional automation based on rules. In this paper, an advanced framework for Intelligent Process Automation (IPA) is proposed, combining deterministic nature of RPA with the cognitive capabilities of AI, which makes it possible to automate not only structured but unstructured business processes as well. Hybrid approach is designed to use natural language processing, optical character recognition, and machine learning models to deal with difficult decisions. Empirical study shows impressive increases in efficiency, as the time of task completion is reduced by 33%, and errors occur 65% less often. Comparative analysis with conventional RPA shows IPA to be a better solution in many aspects of performance. The results add to the literature on intelligent automation and have practical implications for organizations.

DOI: https://doi.org/10.5281/zenodo.22012612

Published by: vikaspatanker

Authors: Bilal Ibrahim Maijamaa, Salim Ahmad, Zaharaddeen Salele Iro, Aminu Aliyu Abdullahi

Abstract: Missing values are a common challenge in real-world datasets, often reducing the accuracy and reliability of machine learning models. Although numerous machine learning and ensemble-based imputation techniques have been proposed, many rely on single-level stacking architectures and do not explicitly model both linear and nonlinear relationships during prediction. This study proposes a Particle Swarm Optimization (PSO)-optimized two-level stacking ensemble for numerical data imputation. The framework employs PSO for base-learner selection and hyperparameter optimization; the selected base learners are Random Forest and XGBoost. A two-metalearner architecture is then used in which Linear Regression captures linear dependencies and Random Forest models nonlinear interactions to generate the final imputed values. The proposed framework was evaluated on the Breast Cancer Wisconsin and Wine Quality datasets under Missing Completely at Random (MCAR) mechanisms at 30%, 20%, and 10% missingness. Performance was assessed using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), coefficient of determination (R²), and processing time. Experimental results demonstrate that the proposed model consistently outperformed the standalone Random Forest and XGBoost models across all missingness levels. On the Breast Cancer dataset, the proposed model achieved RMSE values of 0.0747, 0.0627, and 0.0529 with corresponding R² values of 67.66%, 70.51%, and 74.63% at 30%, 20%, and 10% MCAR, respectively. Similarly, on the Wine Quality dataset, it recorded RMSE values of 0.1873, 0.1751, and 0.1681 with corresponding R² values of 49.54%, 52.15%, and 54.64%. Furthermore, the proposed approach outperformed a recently reported hybrid imputation method, achieving substantially lower prediction errors while maintaining acceptable computational cost. These findings demonstrate that integrating PSO optimization with a two-level stacking ensemble provides an accurate, robust, and scalable framework for numerical missing value imputation across datasets with varying degrees of missingness.

DOI: https://doi.org/10.5281/zenodo.22009422

Published by: vikaspatanker