Modeling Traffic Congestion in Developing Countries Using Google Maps Data

Traffic congestion research is on the rise, thanks to urbanization, economic growth, and industrialization. Developed countries invest a lot of money in collecting traffic data using Radio Frequency Identification (RFID), loop detectors, speed sensors, high-end light, GPS. However, these processes are expensive, infeasible, non-scalable for developing with numerous non-motorized vehicles, proliferated ride-sharing services, frequent pedestrians. This paper proposes novel approach collect from Google Map’s layer minimal cost. We have implemented widely used models such as Historical Averages (HA), Support Vector Regression (SVR), Graph (SVR-Graph), Auto-Regressive Integrated Moving Average (ARIMA) show efficacy collected forecasting future congestion. that even simple models, we could predict ahead time. also demonstrate patterns significantly different between weekdays weekends.