An Advanced Learned Type-3 Fuzzy Logic-Based Hybrid System to Optimize Inventory Cost for a New Business Policy

In this paper, a type-3 fuzzy logic-based system has been created by accumulating the demand as the input variable to design the ideal inventory level that would minimize the overall inventory cost for the economic order quantity model. The new adaptation law based on the extended Kalman filter, and the unscented Kalman filter is carried out to tune the rule parameters and antecedent parameters of the suggested IT3-FLS. A real-life data set is collected to feed and test the IT3-FLS model. Some statistical measures like root-mean-square error, variance, correlation coefficient (R), and Theil's coefficient are calculated to examine the prediction accuracy. The lowest RMSE observed is 0.02138, and the highest R is 0.99975 for IT3-FLS. Furthermore, the optimal total variable cost is calculated by collecting the estimated inventory. Additionally, to demonstrate the applicability of the suggested methodology, one real-life issue and its managerial resolution have been highlighted.

Automated summary

In this paper, a type-3 fuzzy logic-based system is created to design the ideal inventory level that minimizes the overall inventory cost. New adaptation laws based on extended Kalman filter and unscented Kalman filter are used to tune the parameters of the system. Real-life data is collected to test the model, and statistical measures are calculated to evaluate the prediction accuracy. The applicability of the proposed methodology is demonstrated through a real-life issue and its resolution.