Northern Kentucky University
Analyzing Human Dynamics through the Analysis of an Extensive Auction Dataset
Grade Level at Time of Presentation
Sophomore
Major
Data Science
Minor
Computer Science
Faculty Advisor/ Mentor
Dr. Nicholas Caporusso, Dr Alina Campan
Department
College of Informatics
Abstract
Auctions provide a unique lens through which human behavior can be studied, particularly in the realms of decision-making, strategy, and economic interaction. The data generated in auction environments, characterized by competitive bidding, time constraints, and varying levels of information asymmetry, offers rich insights into how individuals make decisions under pressure, uncertainty, and scarcity. For instance, auction data can reveal patterns of irrational biddings, such as the “winner’s curse”, where winners tend to overpay due to competition. Also, by analyzing bid increments, winning bids, and participant behavior across various auction types, researchers can gain a deeper understanding of cognitive biases and strategic decision-making in competitive environments.
In this paper, the authors present the result of a study that focused on publicly available data from a very popular online auction platform where users can bid on different types of retail products. The dataset, which contains over 300.000 auctions, involves more than 32 million items and over 1 billion user interactions. The paper presents a preliminary study of some human dynamics that emerge from the dataset, which highlights the unique opportunity offered by the breadth of the dataset for groundbreaking and interdisciplinary research in several areas, from big data analytics to machine learning, from database design to user experience analysis, from software development to behavioral economics
Analyzing Human Dynamics through the Analysis of an Extensive Auction Dataset
Auctions provide a unique lens through which human behavior can be studied, particularly in the realms of decision-making, strategy, and economic interaction. The data generated in auction environments, characterized by competitive bidding, time constraints, and varying levels of information asymmetry, offers rich insights into how individuals make decisions under pressure, uncertainty, and scarcity. For instance, auction data can reveal patterns of irrational biddings, such as the “winner’s curse”, where winners tend to overpay due to competition. Also, by analyzing bid increments, winning bids, and participant behavior across various auction types, researchers can gain a deeper understanding of cognitive biases and strategic decision-making in competitive environments.
In this paper, the authors present the result of a study that focused on publicly available data from a very popular online auction platform where users can bid on different types of retail products. The dataset, which contains over 300.000 auctions, involves more than 32 million items and over 1 billion user interactions. The paper presents a preliminary study of some human dynamics that emerge from the dataset, which highlights the unique opportunity offered by the breadth of the dataset for groundbreaking and interdisciplinary research in several areas, from big data analytics to machine learning, from database design to user experience analysis, from software development to behavioral economics