The chapter presents machine learning approaches for business continuity and recovery optimization in agribusiness. Firstly, a mathematical method, entitled business continuity points (BCPTs) is tested with domain data for its potential to predict process recovery results, namely recovery time and criticality ranking of key operations. A 72.22% accuracy has been estimated. Then, decision tree prediction with 10-fold cross validation and random forest has been 92.31% accurate in classifying business functions as critical or not. Additionally, a new multi-approach and multi-class decision tree classifier with some of the BCPTs input variables is presented, with 55.36% accuracy, and 70.37% and 88.89% accuracy rates when boosted with the 10 folds and the random forest. Finally, regression analysis techniques are used to improve the initial recovery time BCPTs formula. Exponential regression has been more precise compared to the quadratic model (R2exp=0.954, R2quad=0.85). Despite current data limitations, the inferred prediction patterns are robust and highly accurate in the given field.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.