Analysis and modeling of ride-sharing service user behavior in urban area

Artificial Intelligence driven optimal route planning for urban transit

“…In (Duo et al, 2017), they analyzed the ride-sharing services of three TNCs based on their temporal, spatial and distribution characteristics. They noted that TNCs can effectively reduce the time it normally takes to find a client as well as providing a secure and automated way for trip cost handling.…”

“…Some researchers employed multi-staged algorithms that divided the prediction tasks into separate smaller tasks and helped address the problem of computational resources, some of the research works also focused on privacy policies and how customers and driver's information can be protected using advanced encryption technology. Transportation data is generally spatial-temporal in nature, particularly exciting research work by the authors in (Duo et al, 2017) involved utilizing users online behaviors on ride-sharing applications to identify patterns on how users prefer to travel which could be used to build either a single or multi-modal intelligent transportation systems, the identified patterns were used to determine the time of day users preferred to share rides. The work by (Bicocchi et al, 2015) highlighted that the current number of mobile phone users alongside the pervasive nature of mobile devices create an environment where social media tools can be used to collect voluminous amounts of data for understanding users mobility habits.…”

“…In (Duo et al, 2017), they obtained mobile phone data collected by a traffic monitoring system (TMS) used by a large number of internet service providers (ISP) to monitor traffic scenarios in a production environment. The data contained information from all 2G and 3G users in Northern China from April 18 to April 24, the data traffic collected was generated by software installed on smartphones or via the smartphone itself, the data is sent to a close-by base station for transmission.…”