Genetic Algorithm to Estimate Cumulative Prospect Theory Parameters for Selection of High-Occupancy-Vehicle Lane

Abstract

Recent literature suggests a need for a more realistic representation of driver behavior. In an effort to integrate prospect theory as a potential descriptive method into traveler behavior, it is important to determine the validity of previous estimated parameters obtained from empirical studies and interviews of people who are not in the same fast-paced, dynamic, travel time disutility setting as real drivers. A genetic algorithm is used to simultaneously estimate the parameters of the cumulated prospect theory (CPT) value and weight functions as well as the coefficients of the random utility model; this procedure leads to estimates that have a higher likelihood value and statistical significance than an equivalent expected utility–based logit model or a CPT-based logit model using the empirical values developed earlier. The value function parameters generally conform to conclusions from previous literature. The weight function parameters, however, suggest that drivers in a fast-paced changing environment with multiple subjects for prospect evaluation may become overwhelmed by the certainty effect.