In the era of big data, the impact of information technologies in improving organizational performance is growing as unstructured data is increasingly important to business intelligence. Daily data gives businesses opportunities to respond to changing markets. As a result, many companies invest lots of money in big data in order to obtain adverse outcomes. In particular, analysis of commercial websites may reveal relations of different parties in digital markets that pose great value to businesses. However, complex ecommercial sites present significant challenges for primary web analysts. While some resources and tutorials of web analysis are available for studying, some learners especially entrylevel analysts still struggle with getting satisfying results. Thus, I am interested in developing a computer program in the Python programming language for investigating the relation between sellers’ listings and their seller levels in a darknet market. To investigate the relation, I couple web data retrieval techniques with doc2vec, a machine learning algorithm. This approach does not allow me to analyze the potential relation between sellers’ listings and reputations in the context of darknet markets, but assist other users of business intelligence with similar analysis of online markets. I present several conclusions found through the analysis. Key findings suggest that no relation exists between similarities of different sellers’ listings and their seller levels in rsClub Market. This study can become a great and unique example of web analysis and create potential values for modern enterprises.