Transportation planning is a critical component of the urban development, relying heavily on accurate travel demand forecasting. With the number of vehicles more than doubling, increasing the reliance on private cars has exacerbated the traffic congestion and environmental pollution. This study aims to develop a statistical forecasting model to examine the relationship between the socioeconomic factors and trip generation, thereby supporting data-driven infrastructure improvements to alleviate congestion. Two data collection methods were employed: in-home interviews and questionnaire-based household surveys. The study found that the trip production is significantly influenced by variables, such as the number of students and workers in the household, family size and composition, gender distribution, household age groups, income levels, and car ownership. A total of 5,529 trips were recorded. Trip generation models were developed for three primary journey purposes: home-based work, education, and total trips, using SPSS software. The multiple regression analysis yielded a coefficient of determination (R²) of 0.850 and an average accuracy (AA%) of 72.5%. The results underscore that the household socioeconomic characteristics are key determinants of the travel behavior, and their integration into planning models can enhance the urban mobility strategies.
Lafta et al. (Mon,) studied this question.