TRAIN DELAY PREDICTION USING MACHINE LEARNING

Abstract

Transport systems are critical pieces of infrastructure and they have substantially increased in size in many countries 
worldwide. This includes rail transport systems that have evolved significantly, including to provide longdistance 
travel services. Passenger train delay significantly influences riders’ decision to choose rail transport as their mode 
choice. Poor on-time performance can impact passenger trust and their satisfaction, and it may result in a shift to 
other modes of transport, especially private vehicles and air transport. Service disruption is a root cause of lower rail 
punctuality and customer satisfaction. Major service disruptions result from various conditions or factors such as 
accidents, problems in train operation, malfunctioning or damaged equipment, routine maintenance, construction, 
passenger boarding or alighting, and even  
extreme weather conditions. Train delay can also negatively affect connecting trains and passengers’ journeys or 
activities. Thus, delay estimates or predictions can help train operators develop better plans to manage, reschedule, 
or adjust the timetable of the current and consecutive trains more effectively, as well as to inform passengers in 
advance so they themselves can adjust their travel plans in time. In light of these problems, the main objective is to 
model passenger train delay prediction based on three Machine Learning.