Causal Inference of the Traffic Density for Smart Cities

In this research, causal inference result is calculated on the real data of Istanbul Metropolitan Municipality (IMM) for smart cities. With the increase in the use of artificial intelligence and IoT, the solutions of the problems experienced by the cities have become easier and new solutions are being developed. Causal Inference is a technique whose importance has increased in recent years. In this research, the traffic problem in smart cities is handled through causal inference methods and machine learning algorithms. In the presence of real data, the causal relationships of smart cities were calculated with the newly developed double-layer causal inference method. In this way, the causal effects of weather conditions on traffic density have been clearly demonstrated. Thus, this causal inference method will contribute to the efficient planning of resource consumption in smart cities.