Precise travel time prediction allows travelers and system controllers to be aware of the future conditions on roadways and helps in pre-trip planning and traffic control strategy formulation to lessen the travel time and mitigate traffic congestion problems. This research investigates the possibility of using the GPS trajectory dataset for travel time prediction in Indian traffic conditions having heterogeneous disordered traffic and improvement in prediction accuracy by shifting from the traditional historical average method to modern machine learning algorithms such as linear regressions, decision tree, random forest, and gradient boosting regression. The present study uses massive location data consisting of historical trajectories that were collected by installing GPS devices on the probe vehicles. A 3.6 km long stretch of the Delhi–Noida Direct (DND) flyway is selected as a case study to predict the travel time and compare the performance as well as the efficiency of various travel time prediction algorithms.

Investigating travel time variability is critical for pre-trip planning, reliable route selection, traffic management, and the development of control strategies to mitigate traffic congestion problems cost-effectively. Hence, a large number of studies are available in the literature which determine the most suitable distribution to fit the travel time data, but these studies recommend different distributions for the travel time data, and there is a disagreement on the best distribution option for fitting to the travel time data. The present study proposes a novel framework to determine the best distribution to represent the travel time data obtained from probe vehicles by using the modern machine learning technique. This study employs vast travel time data collected by fitting GPS tracking units on the probe vehicles and offers a comprehensive investigation of travel time distribution in different scenarios generated due to spatiotemporal variation of the travel time. The study also considers the effect of weather and uses the three most commonly used non-parametric goodness-of-fit tests (namely, Kolmogorov–Smirnov test, Anderson–Darling test, and chi-squared test) to fit and rank a comprehensive set of around 60 unimodal statistical distributions. The framework proposed in the study can determine the travel time distribution with 91% accuracy. Additionally, the distribution determined by the framework has an acceptance rate of 98.4%, which is better than the acceptance rates of the distributions recommended in existing studies. Because of its robustness and applicability in many different traffic situations, the proposed framework can also be used in developing countries with heterogeneous disordered traffic conditions to evaluate the road network’s performance in terms of travel time reliability.