Masters Theses

Abstract

"Ridesharing platforms rely on connecting available taxi drivers to potential passengers to maximize their revenue. However, predicting the stopping decision made by every driver, i.e., the final task performed during a given day, is crucial to achieving this goal. Unfortunately, little research has been done on predicting drivers’ stopping decisions, especially when they deviate from expected utility maximization behavior. This research proposes a Dynamic Discounted Satisficing (DDS) heuristic to model and learn the task at which human agents will stop working for that day, assuming that the human agents are taking sequential decisions based on their preference order. We apply this approach to the problem of predicting the stopping decision of taxi drivers in a ridesharing platform. To estimate the model parameters and predict the stopping time, we propose an algorithm - Sampling Based Back Propagation Through Time (SBPTT) and evaluate it using real-time data from the Chicago taxi dataset. The proposed model consistently has better accuracy on simulated and real-world data sets, when compared with discounted satisficing model"--Abstract, p. iii

Advisor(s)

Nadendla, V. Sriram Siddhardh

Committee Member(s)

Luo, Tony T.
Tripathy, Ardhendu S.

Department(s)

Computer Science

Degree Name

M.S. in Computer Science

Publisher

Missouri University of Science and Technology

Publication Date

Spring 2023

Pagination

vi, 32 pages

Note about bibliography

Includes_bibliographical_references_(pages 29-31)

Rights

© 2023 Sree Pooja Akula, All Rights Reserved

Document Type

Thesis - Open Access

File Type

text

Language

English

Thesis Number

T 12285

Electronic OCLC #

1426046173

Download

Share

 
COinS