Thesis Code: 19019
Thesis Type: M.Sc. thesis in Computer Science
Research Area: Urban Mobility & Logistic Systems
Requirements:
- Interest in machine learning algorithms
- Experience with Python
- Ability to critically interpret analytical results
Description:
Although smart tickets are increasingly common in public transport, few cities are equipped with an automatic fare collection (AFC) system that can provide information on both boarding (check-in) and alighting (check-out) users’ locations. In fact, usually only check-in ticket validation is mandatory, and it is therefore necessary to estimate the destination of passengers.
The student will have to study a deep learning model to estimate the destinations of public transport passengers, using the electronic ticketing data available in the province of Cuneo. The student will be asked to implement the algorithm in Python and validate the model using the data available on the passengers’ check-out. Furthermore, the student will have to evaluate the model’s performance against a Trip-Chaining model currently in use on the same data, identifying the advantages and disadvantages of the different estimation models.
The thesis will be carried out in collaboration between the Links Foundation (Urban Mobility & Logistic Systems Area) and the Polytechnic of Turin (Department of Control and Computer Engineering).
Contact: send a resume with attached the list of exams to maurizio.arnone@linksfoundation.com specifying the thesis code and title.