<![CDATA[The dynamic pricing system on Grab causes frequent fare fluctuations, complicating travel budget planning. This study analyzes GrabBike Reguler fare patterns from Campus 3 of Universitas Mercu Buana Yogyakarta (UMBY) to Mirota Kampus Babarsari. It implements linear interpolation as a lightweight numerical baseline for rough estimation, rather than a robust predictive model. Primary data were collected through direct observation over seven days at 15-minute intervals during morning (07:00–09:00 WIB), noon (12:00–13:00 WIB), and evening (16:00–19:00 WIB) peak periods, noting rainy and non-rainy conditions. This method was deployed via a Python-Flask web application. Results indicate the morning fare stabilizes at IDR 12,000 after a peak of IDR 14,500, while the noon fare remains constant at IDR 12,000. The evening period shows the highest volatility, peaking at IDR 14,342 (17:30 WIB, non-rainy) and IDR 21,250 (18:45 WIB, rainy). Accuracy evaluation across 21 paired data points from morning and evening sessions yielded MAE = IDR 1,047.62, MSE = 4,117,767.24, and RMSE = IDR 2,029.23, representing an 8.7% average error relative to the IDR 12,000 base fare. This margin confirms linear interpolation serves only as a rough baseline reference tool, not a reliable predictive model.]]>
Copyrights © 2026
