Matching Items (4)

Consumer Review Variation by Product Type - A Multi-method Analysis

Description

In the past decade, online shopping mode has been recognized and accepted by more and
more people. Over 200 million people were online shoppers in the United States. Convenient,
options,

In the past decade, online shopping mode has been recognized and accepted by more and
more people. Over 200 million people were online shoppers in the United States. Convenient,
options, and better prices compared to traditional shopping mode attract more people to choose
the products online. Consumer’s feedback presented as online reviews on products after the
purchase has become one of the most important factors influencing whether other consumers will
purchase products. For merchants, by studying the behavioral differences of these online
consumers when evaluating products, they can help them to understand product characteristics
and their customers to improve online marketing strategies. This article explores the differences
in the types of utilitarian and hedonic products and behavioral changes in customer opinions,
which involves 22 different categories of products from Amazon.com and customer reviews for
analysis through a variety of technical and research methods.

Contributors

Agent

Created

Date Created
  • 2020-05

158154-Thumbnail Image.png

Multivariate Statistical Modeling and Analysis of Accelerated Degradation Testing Data for Reliability Prediction

Description

Degradation process, as a course of progressive deterioration, commonly exists on many engineering systems. Since most failure mechanisms of these systems can be traced to the underlying degradation process, utilizing

Degradation process, as a course of progressive deterioration, commonly exists on many engineering systems. Since most failure mechanisms of these systems can be traced to the underlying degradation process, utilizing degradation data for reliability prediction is much needed. In industries, accelerated degradation tests (ADTs) are widely used to obtain timely reliability information of the system under test. This dissertation develops methodologies for the ADT data modeling and analysis.

In the first part of this dissertation, ADT is introduced along with three major challenges in the ADT data analysis – modeling framework, inference method, and the need of analyzing multi-dimensional processes. To overcome these challenges, in the second part, a hierarchical approach, that leads to a nonlinear mixed-effects regression model, to modeling a univariate degradation process is developed. With this modeling framework, the issues of ignoring uncertainties in both data analysis and lifetime prediction, as presented by an International Standard Organization (ISO) standard, are resolved. In the third part, an approach to modeling a bivariate degradation process is addressed. It is developed using the copula theory that brings the benefits of both model flexibility and inference convenience. This approach is provided with an efficient Bayesian method for reliability evaluation. In the last part, an extension to a multivariate modeling framework is developed. Three fundamental copula classes are applied to model the complex dependence structure among correlated degradation processes. The advantages of the proposed modeling framework and the effect of ignoring tail dependence are demonstrated through simulation studies. The applications of the copula-based multivariate degradation models on both system reliability evaluation and remaining useful life prediction are provided.

In summary, this dissertation studies and explores the use of statistical methods in analyzing ADT data. All proposed methodologies are demonstrated by case studies.

Contributors

Agent

Created

Date Created
  • 2020

157596-Thumbnail Image.png

IT-enabled monitoring in the gig economy

Description

Two-sided online platforms are typically plagued by hidden information (adverse selection) and hidden actions (moral hazard), limiting market efficiency. Under the context of the increasingly popular online labor contracting platforms,

Two-sided online platforms are typically plagued by hidden information (adverse selection) and hidden actions (moral hazard), limiting market efficiency. Under the context of the increasingly popular online labor contracting platforms, this dissertation investigates whether and how IT-enabled monitoring systems can mitigate moral hazard and reshape the labor demand and supply by providing detailed information about workers’ effort. In the first chapter, I propose and demonstrate that monitoring records can substitute for reputation signals such that they attract more qualified inexperienced workers to enter the marketplace. Specifically, only the effort-related reputation information is substituted by monitoring but the capability-related reputation information. In line with this, monitoring can lower the entry barrier for inexperienced workers on platforms. In the second chapter, I investigate if there is home bias for local workers when employers make the hiring decisions. I further show the existence of home bias from employers and it is primarily driven by statistical inference instead of personal “taste”. In the last chapter, I examine if females tend to have a stronger avoidance of monitoring than males. With the combination of the observational data and experimental data, I find that there is a gender difference in avoidance of monitoring and the introduction of the monitoring system increases the gender wage gap due to genders differences in such willingness-to-pay for the avoidance of monitoring. These three studies jointly contribute to the literature on the online platforms, gig economy and agency theory by elucidating the critical role of IT-enabled monitoring.

Contributors

Agent

Created

Date Created
  • 2019

156910-Thumbnail Image.png

Exploring the Mechanisms of Information Sharing

Description

Online product ratings offer consumers information about products. In this dissertation, I explore how the design of the rating system impacts consumers’ sharing behavior and how different players are affected

Online product ratings offer consumers information about products. In this dissertation, I explore how the design of the rating system impacts consumers’ sharing behavior and how different players are affected by rating mechanisms. The first two chapters investigate how consumers choose to share their experiences of different attributes, how their preferences are reflected in numerical ratings and textual reviews, whether and how multi-dimensional rating systems affect consumer satisfaction through product ratings, and whether and how multi-dimensional rating systems affect the interplay between numerical ratings and textual reviews. The identification strategy of the observational study hinges on a natural experiment on TripAdvisor when the website reengineered its rating system from single-dimensional to multi-dimensional in January 2009. Rating data on the same set of restaurants from Yelp, were used to identify the causal effect using a difference-in-difference approach. Text mining skills were deployed to identify potential topics from textual reviews when consumers didn’t provide dimensional ratings in both SD and MD systems. Results show that ratings in a single-dimensional rating system have a downward trend and a higher dispersion, whereas ratings in a multi-dimensional rating system are significantly higher and convergent. Textual reviews in MDR are in greater width and depth than textual reviews in SDR. The third chapter tries to uncover how the introduction of monetary incentives would influence different players in the online e-commerce market in the short term and in the long run. These three studies together contribute to the understanding of rating system/mechanism designs and different players in the online market.

Contributors

Agent

Created

Date Created
  • 2018