E-Commerce is one of business mediums to offer a variety of choices to consumers. The explosion of data and information lead to the use of machine learning models to predict and customize the product categorization from online stores. This paper presents a study to assess the performance of Hidden Markov Model (HMM) in classifying e-commerce products. There are two parameter estimation approaches used in evaluating the HMM which are Baum-Welch and Viterbi Training algorithms. The results show that Baum-Welch algorithm performed better than Viterbi Training algorithm in estimating parameters of HMM. Hence, the former algorithm provides a better parameter estimation for the HMM in the study.