The use of machine learning techniques for assessing the potential of organizational resilience

Abstract

Abstract Organizational resilience (OR) increases when the company has the ability to anticipate, plan, make decisions, and react quickly to changes and disruptions. Thus the company should focus on the creation and implementation of proactive and innovative solutions. Proactive processing of information requires modern technological solutions and new techniques used. The main focus of this study is to propose the best technique of Machine Learning (ML) in the context of accuracy for predicting the attributes of the organizational resilience potential. Based on the calculations, the research includes estimating them through the applications of regression and machine learning methods. The dataset is obtained from the results of the our survey based on the questionnaire consisting of 48 items mainly established on OR attributes formed on ISO 22316:2017 standard. Based on the outcomes of the study, it can be stated that the optimal technique in the context of accuracy for predicting the attributes of the organizational resilience potential is ensemble methods. The k-nearest neighbor (KNN) filtering-based data pre-processing technique for stacked ensemble classifier is used. The stacking is achieved with three base classifiers namely Random Forest (RF), Naive Bayes (NB), and Support Vector Machine (SVM). The chosen ensemble method should be implemented in an organization systemically according to the circle of innovation, and should support the quality of managerial decision-making process by increasing the accuracy of organizational resilience potential prediction, and indication of the importance of attributes and factors affecting the potential for organizational resilience.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 29 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.