Comparison of Sequential and Logarithmic Data Access Methods based on Archiving Scenarios Validity

Abstract

The growing volume of customer documents in financing companies presents challenges in archive retrieval when the search method is not well suited to increasing data volumes. This study aims to compare Linear Search and Binary Search methods within a web-based customer document archiving information system at PT Multindo Auto Finance. An experimental comparative analysis was conducted by empirically evaluating both algorithms under identical conditions and using the same dataset. The dataset consisted of 4,996 customer documents and was evaluated under two testing scenarios: searching for data that exists in the system and searching for data that does not exist. The primary performance metric was execution time, measured in milliseconds (ms). The results show that Binary Search outperformed Linear Search in both scenarios, achieving an execution time of 0.01 ms, while Linear Search required 0.09 ms when the target data was found and 0.23 ms when the target data was not found. However, Binary Search requires the data to be sorted, which may limit its suitability for systems containing frequently updated or dynamically changing data. The study concludes that Binary Search is recommended for large-volume systems with relatively static datasets, whereas Linear Search is more suitable for systems with dynamic datasets that are continuously updated.