Travel behaviour exists in both culture and the surrounding environment. It is crucial to understand it because it helps the policymakers to effectively develop the urban and transportation planning policies. Large scale mobility of people by motorized transport is making our cities polluted and more congested that ultimately affects urban assets. A single paradigm, e.g. land use or socio-demographics, might not clearly demonstrate people’s preferences, it is necessary to take several paradigms in isolation. This study examined the joint influence of multiple attributes that includes land use, socio-demographic and travel information on travel behaviour and particularly preferred travel mode. A structured questionnaire was designed and interviews were conducted to obtain the data. Multinomial logit model (MNL) was applied to estimate the relationships among variables. Furthermore, spatial maps were prepared to highlight the classification of land uses. It was estimated that with the increase in income level people switched from walking to riding a vehicle and most of them prefer to ride a vehicle for longer trips. It was further investigated that people prefer to walk or ride a vehicle in residential and commercial areas. Based on the results, several planning related policies were recommended.
Predictive modeling is the key fundamental method to study passengers’ behavior in transportation research. One of the limited studied topic is modeling of public transport usage frequency, which can be used to estimate present and future demand and users’ trend toward public transport services. The artificial intelligence and machine learning methods are promising to be better substitute to statistical techniques. No doubt, traditionally been used econometrics models are better for causal relationship studies among variables, but they made rigid assumptions and unable to recognize the pattern in data. This paper aims to build a predictive model to solve passengers’ classification, and public transport usage frequency using socio-demographic survey data. The supervised machine learning algorithm, K-Nearest Neighbor (KNN) applied to build a predictive model, which is the better machine learning method for dealing with small datasets, because of its ability of having less parameter tuning. Survey data has been used to train and validate the model performance, which is able to predict public transport usage frequency of future users of public transport. This model can practically be used by public transport agencies and relevant government organizations to predict the public transport demand for new commuters before introducing any new transportation projects.