Traffic Pattern Division Based on Mobile Signaling Data

In order to solve the problem of dividing the traffic pattern of the OD extracted by the mobile phone signaling, using resident survey data and network crawling data as samples, features such as travel attributes and traveler attributes are extracted and equivalently processed to construct model input data equivalent to mobile phone signaling data. Selecting random forest, support vector machine, and neural network machine learning model helps divide the three modes of transportation: car travel, public transportation, and other travel modes. Through multi-index evaluation and case verification, the results show that the random forest model is a better overall model with a prediction accuracy of 70%. The prediction results are stable and reliable and have certain practical application value.