Masters Theses

Keywords and Phrases

Bounded Rationality; Crowdsourcing; Discounted Satisficing; Human sequential decision-making; Quadratic Programming


“Human sequential decision-making involves two essential questions: (i) "what to choose next?", and (ii) "when to stop?". Assuming that the human agents choose an alternative according to their preference order, our goal is to model and learn how human agents choose their stopping time while making sequential decisions. In contrary to traditional assumptions in the literature regarding how humans exhibit satisficing behavior on instantaneous utilities, we assume that humans employ a discounted satisficing heuristic to compute their stopping time, i.e., the human agent stops working if the total accumulated utility goes beyond a dynamic threshold that gets discounted with time. In this thesis, we model the stopping time in 3 scenarios where the payoff of the human worker is assumed as (i) single-attribute utility, (ii) multi-attribute utility with known weights, and (iii) multi-attribute utility with unknown weights. We propose algorithms to estimate the model parameters followed by predicting the stopping time in all three scenarios and present the simulation results to demonstrate the error performance. Simulation results are presented to demonstrate the convergence of prediction error of stopping time, in spite of the fact that model parameters converge to biased estimates. This observation is later justified using an illustrative example to show that there are multiple discounted satisficing models that explain the same stopping time decision. A novel web application is also developed to emulate a crowd-sourcing platform in our lab to capture multi-attribute information regarding the task in order to perform validations of the proposed algorithms on real data”--Abstract, page iii.


Nadendla, V. Sriram Siddhardh

Committee Member(s)

Wunsch, Donald C.
Luo, Tony Tie


Computer Science

Degree Name

M.S. in Computer Science


Missouri University of Science and Technology

Publication Date

Summer 2020


viii, 49 pages

Note about bibliography

Includes bibliographic references (pages 45-48).


© 2020 Mounica Devaguptapu, All rights reserved.

Document Type

Thesis - Open Access

File Type




Thesis Number

T 11741

Electronic OCLC #