Lyft, Inc.

Davide Crapis

Ehud Milo

Saurabh Bajaj

Omar Khalid

Eran Davidov

Hao Yi Ong

Praveen Athmanathan Panneer Selvam

Shashi Kant Sharma

Ramon Dario Iglesias

Jae Ik Jin

Daniel Freund

David Elijah Alpern Boehm

Varun Kashyap Krishnan

Shengke Zhou

Jiayu Gong

Derek William Salama

Xiaoling Charlene Zhou

Su Wang

Kevin Hsing-Chiang Fan

This disclosure describes methods, non-transitory computer readable media, and systems that can determine locations and geospatial scores for pick-up events and other transportation events relative to geocoded areas at a given time period and generate geospatial-based proportion metrics for provider devices corresponding to such transportation events as proportional premiums for performing the events. For example, the systems determine locations of provider devices across geocoded areas for a particular time period. The systems can generate geospatial scores for transportation events of the provider devices occurring within the time period based on the specific locations and times of the events relative to the geocoded areas. Based on the geospatial scores and cumulative metrics accounting for such transportation events relative to the geocoded areas, the systems can generate geospatial-based-proportion metrics corresponding to such events for a graphical display on provider devices.

Dynamically generating geospatial-based-proportion metrics based on transportation events relative to geocoded areas

The present application discloses an improved transportation matching system, and corresponding methods and computer-readable media. According to disclosed embodiments, a transportation matching system trains a predictive request model to generate a metric predicted to trigger an increase in transportation provider activity within the geographic area for a given time period. Furthermore, the system determines a predicted gap between expected request activity and expected transportation provider activity for the geographic area during a future time period, utilizes the predictive request model and the predicted gap to generate a metric for the geographic area, and generates an interactive map associated with a customized schedule for the geographic area and the future time period based on the generated metric.

Using a predictive request model to optimize provider resources

The present application discloses systems, methods, and computer-readable media that can dynamically control a number of provider devices operating in a prioritized-dispatch mode by determining a range of prioritized-dispatch-mode slots for a target time based on differences between value metrics received by provider devices operating in multiple dispatch modes and sending availability nudges to provider devices based on the range of prioritized-dispatch-mode slots. For instance, the disclosed systems can generate a threshold-noticeable-value difference between historical value metrics received by provider devices while operating in a prioritized-dispatch mode and in a basic-dispatch mode. Based on the threshold-noticeable-value difference, the disclosed systems determine a range of slots for the prioritized-dispatch mode during a target time period for a geographic area. Based on the determined range of slots, the disclosed systems can transmit prioritized-mode-availability indicators to provider devices to indicate varying levels of availability of the prioritized-dispatch mode for the geographic area.

Dynamically adjusting a pool of transportation provider devices in a prioritized-dispatch mode using availability indicators

The present disclosure relates to systems, methods, and non-transitory computer-readable media that validate the performance of a dispatch model, such as a directive-based model, utilized for facilitating transportation matching services. For example, the disclosed systems can generate critical situations clusters composed of groups of critical transportation provider performance scenarios. From the critical situation clusters, the disclosed systems can sample one or more critical transportation provider situations that present a risk of degradation for the transportation matching services. Accordingly, the disclosed systems can measure a performance of the dispatch model by employing a simulation model that utilizes the dispatch model to propagate the critical transportation provider situations through time.

Modifying directive-based transportation dispatch models based on digital critical situation simulations

Growing community of inventors

Berkeley, CA, United States of America

Davide Crapis