On Searching Product Catalog: Relational Database Versus Search Engine approaches

Context: Product queries are pivotal in various applications, such as e-commerce websites and price comparison tools. In particular, searching for products on invoices is an essential way to help monitor expenses from public entities. Problem: The volume of invoice data and the lack of standardization in product descriptions pose challenges for a search tool. In this context, query processing time and the relevance of results obtained are decisive factors. Solution: We investigated query results, considering metrics of product relevance in the retrieved outcomes, as well as query processing times in SQL Server and Elasticsearch. Statistical methods were employed to analyze the results and determine the most suitable search mechanism for the context. Information Systems Theory: We applied principles of Information Systems and experimental design techniques to conduct a comparative assessment of the effectiveness of Elasticsearch and SQL Server in searching for products in invoices. Method: We adopted a quantitative approach, utilizing a Design of Experiments (DoE) to compare Elasticsearch and SQL Server. In the relevance analysis, various queries were considered, varying the number of results returned. In the performance evaluation, we varied different parameters, including temporal filters, the number of terms in queries, and the popularity of the searched products. Summary of Results: Compared to SQL Server, Elasticsearch exhibited superior performance, providing more agile responses and delivering more relevant query results. Contributions and Impact in the IS Field: This research contributes by assisting in selecting product catalog search mechanisms, highlighting Elasticsearch as superior in performance, and promoting quantitative methods for evaluating technologies in information systems.