Learning from Gamettes: Imitating Human Behavior in Supply Chain Decisions

Mohaddesi, Omid; Machado, Tiago; Harteveld, Casper

doi:10.1145/3334480.3382996

Cited by 4 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Player modeling is aimed at understanding how players experience their interaction with the game by focusing on their patterns of behavior through modeling cognitive or afective states [83]. Previous studies in the realm of player modeling used various methods for modeling and imitating player actions, including clustering techniques [20,21], imitation learning [46,53], neural networks [9], and Bayesian models [52,71]. Other researchers used Hidden Markov Models (HMM) for modeling player actions in the game [8,56].…”

Section: Player Modelingmentioning

confidence: 99%

To Trust or to Stockpile: Modeling Human-Simulation Interaction in Supply Chain Shortages

Mohaddesi

Griffin

Ergün

et al. 2022

CHI Conference on Human Factors in Computing Systems

Self Cite

View full text Add to dashboard Cite

Understanding decision-making in dynamic and complex settings is a challenge yet essential for preventing, mitigating, and responding to adverse events (e.g., disasters, fnancial crises). Simulation games have shown promise to advance our understanding of decisionmaking in such settings. However, an open question remains on how we extract useful information from these games. We contribute an approach to model human-simulation interaction by leveraging existing methods to characterize: (1) system states of dynamic simulation environments (with Principal Component Analysis), (2) behavioral responses from human interaction with simulation (with Hidden Markov Models), and (3) behavioral responses across system states (with Sequence Analysis). We demonstrate this approach with our game simulating drug shortages in a supply chain context. Results from our experimental study with 135 participants show diferent player types (hoarders, reactors, followers), how behavior changes in diferent system states, and how sharing information impacts behavior. We discuss how our fndings challenge existing literature. CCS CONCEPTS• Human-centered computing → Empirical studies in HCI.

show abstract

Section: Player Modelingmentioning

confidence: 99%

To Trust or to Stockpile: Modeling Human-Simulation Interaction in Supply Chain Shortages

Mohaddesi

Griffin

Ergün

et al. 2022

CHI Conference on Human Factors in Computing Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…Player modeling is aimed at understanding how players experience their interaction with the game by focusing on their patterns of behavior through modeling cognitive or affective states [83]. Previous studies in the realm of player modeling used various methods for modeling and imitating player actions, including clustering techniques [20,21], imitation learning [46,53], neural networks [9], and Bayesian models [52,71]. Other researchers used Hidden Markov Models (HMM) for modeling player actions in the game [8,56].…”

Section: Player Modelingmentioning

confidence: 99%

To Trust or to Stockpile: Modeling Human-Simulation Interaction in Supply Chain Shortages

Mohaddesi,

Griffin,

Ergun

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Understanding decision-making in dynamic and complex settings is a challenge yet essential for preventing, mitigating, and responding to adverse events (e.g., disasters, financial crises). Simulation games have shown promise to advance our understanding of decision-making in such settings. However, an open question remains on how we extract useful information from these games. We contribute an approach to model humansimulation interaction by leveraging existing methods to characterize: (1) system states of dynamic simulation environments (with Principal Component Analysis), (2) behavioral responses from human interaction with simulation (with Hidden Markov Models), and (3) behavioral responses across system states (with Sequence Analysis). We demonstrate this approach with our game simulating drug shortages in a supply chain context. Results from our experimental study with 135 participants show different player types (hoarders, reactors, followers), how behavior changes in different system states, and how sharing information impacts behavior. We discuss how our findings challenge existing literature.CCS Concepts: • Human-centered computing → Empirical studies in HCI.

show abstract

“…imitation learning [140,141], neural networks [142], and Bayesian models [143,144]. Machine Learning (ML) techniques have been widely applied in game research too, including Game Analytics, which combines data-mining, telemetry, and visualization tools to identify behavioral patterns and player types [45,145,146].…”

Section: Modeling Behavior In Gamesmentioning

confidence: 99%

“…Bridging the gap between the three disciplines of BOM, BOR, and HCI was not an easy task. Prior to developing the ATE framework, I explored various methods to model individual player behavior, such as regression analysis and Imitation Learning [141]. However, these methods fell short in providing clear insights into human behavior and individual differences in supply chain decision-making.…”

Section: Pilot Testingmentioning

confidence: 99%

Understanding human decision-making in supply chains: using serious gaming for modeling action, thought, and the environment

Mohaddesi

View full text Add to dashboard Cite

Dissertation xivEvery significant accomplishment is the fruit of the collective effort, inspiration, and guidance from many. This dissertation is no exception, and I find myself deeply grateful to everyone who has accompanied me on this journey.First and foremost, I would like to express my sincerest appreciation to my advisor, Dr. Casper Harteveld, whose unwavering support, guidance, and invaluable mentorship have been indispensable. Not only did Casper fund my research but has also shared his wealth of insights and expertise at every stage of my Ph.D. journey. From teaching me to be rigorous in conducting experiments to offering guidance on when to pivot during my research, he has always illuminated my path and played a pivotal role in shaping the trajectory and quality of my work.My gratitude extends to the members of my dissertation committee, Dr. Ozlem Ergun, Dr. Jaqueline Griffin, and Dr. Stacy Marsella. Their thoughtful comments, constructive criticism, and valuable suggestions have significantly enhanced the overall quality of my dissertation. Their expertise has been invaluable to me, and with their continuous support and guidance, they played a significant role in shaping the final outcome of this work. I am equally thankful to Dr. David Kaeli, for his constant feedback and guidance, particularly regarding the setup of game servers for my experiments. Prof. Kaeli's support greatly contributed to the success of this research. Additionally, as co-authors, Dr. Ergun, Dr. Griffin, Dr. Marsella, and Dr. Kaeli have all made significant contributions to the writing of publications associated with this dissertation. I am truly grateful for their dedication and commitment to my academic journey.The research undertaken in the preparation of this dissertation was both collaborative and interdisciplinary in its truest sense. In light of this, I feel compelled to extend my heartfelt thanks to my esteemed collaborators from the Drug Shortages team at Northeastern University. From the inception of my Ph.D. journey, Dr. Rozhin Doroudi and Dr. Rana Azghandi provided vital inputs to shape my research. Additionally, the instrumental role of Dr. Yifan Sun cannot be overstated. His expertise and assistance in setting up the game server for data collection from experiments was pivotal. The contributions of Noah Chicoine and Min Gong were equally significant, particularly in their help with qualitative data analysis. These individuals have proven themselves to be much more than collaborators; they have been critical contributors as co-authors of the articles produced from this research. Last but not least, I would like to express my gratitude to Dr. Pedro Sequeira for his insightful comments which enhanced the quality of my work.An integral part of this dissertation was the employment of StudyCrafter, an innovative platform used for designing games and conducting behavioral experiments. Given the significance of this tool in my research, it is fitting that I convey my deepest appreciation to the dedicated members of the Study...

show abstract

Learning from Gamettes: Imitating Human Behavior in Supply Chain Decisions

Cited by 4 publications

References 20 publications

To Trust or to Stockpile: Modeling Human-Simulation Interaction in Supply Chain Shortages

To Trust or to Stockpile: Modeling Human-Simulation Interaction in Supply Chain Shortages

To Trust or to Stockpile: Modeling Human-Simulation Interaction in Supply Chain Shortages

Understanding human decision-making in supply chains: using serious gaming for modeling action, thought, and the environment

Contact Info

Product

Resources

About