This research models urban travel distribution in Jakarta using Mobile Network Big Data (MNBD), particularly focusing on the complexities of human movement during the Covid-19 pandemic and the implementation of Large-Scale Social Restrictions (LSRR). MNBD, sourced from mobile devices, provides detailed, anonymous data on locations, timestamps, and network activity, offering insights into people's movements. The study spans periods before, during, and after the pandemic, including September 2019, February 16-17, 2020, and October 2022. The methodology involves collecting MNBD data from GPS trackers, mobile apps, and cellular networks, followed by filtering invalid data using percentile algorithms. Machine learning techniques are employed to analyze travel patterns and detect anomalies, resulting in the creation of an Origin-Destination (OD) Matrix and visualizations of weekly travel patterns and frequencies. These tools effectively model travel distribution and offer a detailed explanation of movement patterns. The research findings have significant implications for transportation planning and policy-making, providing a better understanding of travel behaviors and informing the development of targeted interventions to address transportation challenges, improve accessibility, and promote sustainable urban mobility. The study's methodology and results are applicable to similar urban areas, offering practical insights into the effectiveness of transportation policies and strategies. Ultimately, this research contributes to more informed decision-making in urban planning, helping to create more sustainable and resilient cities.

Big data, human mobility, trip distribution, OD matrix