System and method for ranking in alternative destination recommendation on ridesharing platforms

A system comprising one or more processors and one or more non-transitory computer-readable memories coupled to the one or more processors, the one or more non-transitory computer-readable memories storing instructions that, when executed by the one or more processors, cause the system to perform operations comprising:

• receiving, by a computing device of a ridesharing platform from a terminal device, a trip request comprising an origin and an initial destination;
• determining, by the computing device of the ridesharing platform, one or more alternative destinations based on one or more features of the initial destination;
• for each of the alternative destinations, determining, by the computing device of the ridesharing platform based on a machine-learning classifier, a probability for the rider to select a trip option from the origin to the alternative destination, wherein the machine-learning classifier is trained to accept input comprising one or more attributes of the trip option and generate output comprising the probability for the rider to select the alternative destination;
• generating, by the computing device of the ridesharing platform, a score for each of the alternative destinations based at least on the probability;
• and
• ranking, by the computing device of the ridesharing platform, the alternative destinations based on the scores.

A non-transitory computer-readable storage medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

• receiving, by a computing device of a ridesharing platform from a terminal device, a trip request comprising an origin and an initial destination;
• determining, by the computing device of the ridesharing platform, one or more alternative destinations based on one or more features of the initial destination;
• for each of the alternative destinations, determining, by the computing device of the ridesharing platform based on a machine-learning classifier, a probability for the rider to select a trip option from the origin to the alternative destination, wherein the machine-learning classifier is trained to accept input comprising one or more attributes of the trip option and generate output comprising the probability for the rider to select the alternative destination;
• generating, by the computing device of the ridesharing platform, a score for each of the alternative destinations based at least on the probability;
• and
• ranking, by the computing device of the ridesharing platform, the alternative destinations based on the scores.