Use of the Random Forest Model

In this book, we develop a new joint pattern recognition method that combines a network pattern-based analysis with an activity sequence-based analysis. We use the advantages of both methods to create clusters of patterns that have distinct pattern homogeneity within them and heterogeneity between patterns. The first part of the analysis here applies a more traditional approach to identify unique network patterns, with 16 of them capturing 83.05% of the 2017 NHTS workday data. Multivariate analysis of the clustered pattern data shows a different pattern preference for students, part-time workers, retirees, telecommuters, drivers, women, and young adults. In the second part of the analysis, motives are grouped into categories based on the number of places a person visits in a day and their correlation with time use and travel is explored. Time use and travel are analyzed on the basis of a minute-by-minute time allocation model identification.