Implementation of Supervised Machine Learning Algorithm to Classify Multi-Criteria Interval Valued Inventory Data

A good management system ensures that the organization has enough goods and materials to meet organization’s needs without causing material shortages or surpluses. But in some cases, uncertainties or imprecisions may exist in the measurement of inventory levels. Interval Valued Data (IVD) allows a more flexible representation of the associated uncertainty. Multi-Criteria interval valued inventory data refers to the inventories those are expressed as intervals based on different criteria. Organizations classify inventory into different classes, allowing managers to set appropriate policies for sourcing, storing, manufacturing, and distributing items. ABC classification based on Pareto Principle (Named after the Italian economist Vilfredo Pareto) is a well-known technique to classify items. In this work, initially classify the dataset into ABC classes using Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) model. A new approach has proposed based on Supervised Machine Learning (ML) Algorithms for IVID which will be used to classify an item in an appropriate class. Supervised ML is a type of ML where the computer uses labeled dataset (splitted into a training set and a test set) to train algorithms that to predict outcomes accurately. Numerical experiments are carried out by applying the approach on some benchmarking data set.