All eyes on me: Predicting consumer intentions on social commerce platforms using eye-tracking data and ensemble learning

2023 | Decision Support Systems | Citations: 0

Authors: Mikalef, Patrick; Sharma, Kshitij; Chatterjee, Sheshadri; Chaudhuri, Ranjan; Parida, Vinit; Gupta, Shivam

Abstract: Understanding what information is important for consumers when making a purchase ... Expand

Abstract: Understanding what information is important for consumers when making a purchase-related decision has been a key question for researchers and practitioners ever since the advent of empirical research in commerce. Nevertheless, our knowledge of what information is important has been formed primarily through post-purchase conscious capturing approaches, such as surveys and questionnaires. To overcome these limitations, we ground this research on an exploratory study that captures eye-tracking data during a decision-making task of product selection. Grounded on the dynamic attention theory, we utilize different information types and formats present on a popular social commerce platform, to identify elements which are important when deciding about online product purchase decision. Specifically, we employ a series of prediction algorithms and use an ensemble learning setup to predict the aspects that contribute to product selection by consumers. Our analysis highlights the most important informational cues to accurately predict product selection among alternatives. In addition, the results showcase how such elements shift in importance during the temporal sequence of comparing different product alternatives. Our results provide insight into how we can understand the journey of decision-making for social commerce customers when navigating through information to select a product. In addition, it opens the discussion about the shifts that eye-tracking in combination with machine learning can create for researchers and marketers. Collapse

Topics: decision making social commerce website user requirement web page

Methods: oculometry computational algorithm ensemble learning machine learning eye tracking tool

Theories: cognitive attention theory

Input Output HMM for Indoor Temperature Prediction in Occupancy Management Under User Preferences

2023 | HICSS | Citations: 0

Authors: Shahin, Kamrul Islam; Das, Anooshmita; Kjærgaard, Mikkel

Abstract: In this paper, a probabilistic machine learning method is proposed to predict th ... Expand

Abstract: In this paper, a probabilistic machine learning method is proposed to predict the indoor temperature of an office environment. An IOHMM-based model is developed to represent the office environment under different circumstances of heating sources. One year of time series data is observed and studied to learn the dynamics of the indoor thermal states. The uncertainty associated with the changing aspects of the indoor temperature and its dependence on the outdoor temperature is considered in the model development. The well-known Baum Welch and forward-backward algorithms are adapted to learn the model parameters. Then, the Viterbi algorithm is used to predict the maximum path of hidden states, leading to predicting the most likely future temperatures. A numerical application is presented to demonstrate the model development steps and the training and testing results. Finally, the model's performance is validated using leave-one-out cross-validation, which shows that the model has a prediction accuracy of about 78%. Collapse

Topics: workstation recommender system

Methods: computational algorithm experiment hidden Markov model case study personal interview

Effect of Market Information on Bidder Attrition in Online Auction Markets

2022 | Management Information Systems Quarterly | Citations: 0

Authors: Ghasemkhani, Hossein; Goes, Paulo; Tripathi, Arvind

Abstract: Information generated in online markets can affect both buyers’ and sellers’ exp ... Expand

Abstract: Information generated in online markets can affect both buyers’ and sellers’ expectations and therefore their choices. In this research, we investigate the effect of market information, generated in online auction markets, on buyers’ expectations and choices. To clear large inventories, sellers often conduct many auctions selling identical items over time, which creates an online auction market where competition dynamics spill over from one to auction to another. In these markets, bidders can participate in many auctions over a period of time, observe market information (supply, demand, and competition), and gain experience to increase their payoffs. We observe that despite having an opportunity to compete and win in future auctions, many bidders stop participating in these auction markets. We argue that observed market information affects their choices. We explore how bidders form expectations about market supply, demand, and competition based on information from two sources—market design parameters and behavior of market participants. By employing a hierarchical Bayesian latent attrition model, we empirically detect and investigate the effect of bidders’ expected market supply, demand, and competition on their attrition in these markets. Our study shows that the effect of market information on attrition is nuanced by bidders’ value heterogeneity. Through the lenses of behavioral economics theories, we show that the attrition behavior of high-value bidders is completely opposite that of low-value bidders. We discuss the practical implications of our findings. Collapse

Topics: online auction decision making electronic market willingness to pay consumer behavior

Methods: descriptive statistic hidden Markov model Markov chain Monte Carlo conceptual modelling theoretical contribution

Theories: economic theory endowment effect behavioral economics lemon market theory social learning theory

Are We There Yet? Analyzing Progress in the Conversion Funnel Using the Diversity of Searched Products

2022 | Management Information Systems Quarterly | Citations: 0

Authors: Goldstein, Anat; Oestreicher-Singer, Gal; Barzilay, Ohad; Yahav, Inbal

Abstract: The conversion funnel is a model describing the stages consumers go through in t ... Expand

Abstract: The conversion funnel is a model describing the stages consumers go through in their journey toward a purchase. This journey often lasts several days to weeks and can include multiple visits to a seller’s website. A large body of literature has focused on using observable search patterns to identify consumers’ hidden purchasing stages and to estimate their likelihood of conversion. We propose a novel set of measures to better reveal the consumer’s hidden stage in the funnel. These measures are based on the diversity of the searches that a customer engages in while browsing an e-commerce website, and they include not only the number of different products that are searched for, but also measures that rely on unobserved similarities among products, captured in a product network (in which products are assumed to be “similar” if they are frequently co-searched). We operationalize and evaluate our proposed measures using a large-scale dataset from a medium-sized tourism website used for comparing and booking flights. We estimate a hidden Markov model to show that our proposed diversity measures are associated with progress in the funnel and consumers’ conversion likelihood. Specifically, we show that consumers go through different distinguishable stages (states) in their journey, characterized by different values of our proposed diversity measures. To demonstrate the managerial and business implications of our theory, we show that incorporating search-diversity measures into a baseline prediction model significantly improves the model’s performance in predicting purchase likelihood and churn. Collapse

Topics: website electronic commerce accounting marketing management information storage and retrieval system

Methods: XGBoost machine learning random forest classification principal component analysis classification method

The dynamic customer engagement behaviors in the customer satisfaction survey

2022 | Decision Support Systems | Citations: 2

Authors: Han, Saram; Anderson, Christopher K.

Abstract: Conducting customer satisfaction surveys (CSS) as a means of encouraging custome ... Expand

Abstract: Conducting customer satisfaction surveys (CSS) as a means of encouraging customers’ engagement with a firm is a widely used managerial practice. In an effort to convert this customer-to-firm engagement into customer-to-customer engagement, many firms have recently started to ask customers who reach the final question of the CSS to write an online review that will be automatically posted on a review site (e.g., Google or TripAdvisor). Using a unique longitudinal data set provided by a large global hotel chain, we aim to understand the drivers behind CSS participation and, ultimately, behind online review posting in response to a prompt at the end of a survey. We employ the Hidden Markov model (HMM) to analyze how a customer’s engagement state changes as a function of previous managerial responses, loyalty program membership, and satisfaction. The results reveal that customers have a greater tendency to transfer to higher engagement states if managers have responded to prior customer surveys. We have also found that the higher the customer’s loyalty program membership status is, the more likely it is that they will participate in a survey. Lastly, we show that customers have a greater tendency to post negative versus positive reviews. We then discuss the implications of this study for researchers and managers. Collapse

Topics: online review user-generated content marketing management customer satisfaction social media

Methods: survey longitudinal research hidden Markov model Markov chain Monte Carlo Markov chain

Theories: social exchange theory

Introduction to “Digital Transformations of Business Operations” Minitrack

2022 | HICSS | Citations: 0

Authors: Seidmann, Abraham; Jiang, Yabing; Zhang, Jie

Abstract: ... Expand

Abstract: Collapse

Topics: health information system criminality mobile application mobile channel

Methods: hidden Markov model

A multistate modeling approach for organizational cybersecurity exploration and exploitation

2022 | Decision Support Systems | Citations: 0

Authors: Zadeh, Amir; Jeyaraj, Anand

Abstract: This study examines the dynamic stages of exploration and exploitation efforts b ... Expand

Abstract: This study examines the dynamic stages of exploration and exploitation efforts by organizations in their cybersecurity responses using multistate modeling. Using textual data from the annual 10-K reports of S&P 100 organizations, this study uses a combination of text analytics and Markov chain approach to quantify exploration and exploitation in organizational cybersecurity responses. The study models two and four states of exploration and exploitation based on their cybersecurity responses over time and uses a continuous-time Markov chain approach to analyze transitions between states as organizations adapt their responses over time to achieve ambidexterity. The two-state Markov model focuses on the firm-level Exploration and Exploitation states whereas the four-state model captures deeper levels of exploration and exploitation by considering Surviving, Investigating, Reinforcing, and Balancing as possible states for exploration and exploitation of cybersecurity responses. We analyze the dynamics of organizational exploration-exploitation behaviors by modeling longitu­ dinal transition probabilities across different states. Implications for research and practice are discussed. Collapse

Topics: IT security organization learning IT security threat organizational productivity analytical information system

Methods: Markov chain Monte Carlo Markov model natural language processing post-hoc analysis computational algorithm

Theories: punctuated equilibrium theory

How Is Mobile User Behavior Different? A Hidden Markov Model of Cross-Mobile Application Usage Dynamics

2022 | Information Systems Research | Citations: 0

Authors: Wu, Shaohui; Tan, Yong; Chen, Yubo; Liang, Yitian (Sky)

Abstract: Mobile application use has become an essential activity in many people’s daily l ... Expand

Abstract: Mobile application use has become an essential activity in many people’s daily lives in the mobile Internet era. Driven by its ubiquity and strong context dependence, Internet companies are in a race of cross-industry expansion to build a seamless ecosystem incorporating various contexts. Amid such trends, a better understanding of cross-app uses and the impact of contexts becomes critical and imperative. Yet, research on cross-app uses in information systems and marketing is scarce. In this paper, we aim to fill this gap. We develop a hidden Markov model to study cross-app uses (choice and duration), capturing their interdependence and the impacts of contextual factors. We calibrate it using a consumer panel that contains real-time app use information. Our key findings are as follows. (1) In addition to the utilitarian and hedonic states behind consumer decisions identified in prior literature, we uncover a novel social state behind mobile user behavior. App use behavior exhibits large differences across three states. (2) Within-state app interdependence is strongest in the hedonic state, followed by the social and utilitarian states. (3) Social state is the most transient (i.e., mostly likely to switch away), followed by the hedonic and utilitarian states. (4) Contextual factors—in particular, location and time of day—influence the state dynamic. Compared with the intrinsic state transition, being at home or on the way (versus office) and in the morning or evening (versus night) leads to higher volatility. We discuss the managerial implications for a variety of mobile digital strategies. Collapse

Topics: mobile application user behavior wireless LAN mobile system internet technology

Methods: theory development hidden Markov model latent class analysis computational algorithm descriptive statistic

Personalized Recommendation for Balancing Content Generation and Usage on Two-Sided Entertainment Platforms

2022 | International Conference on Information Systems | Citations: 0

Authors: Zhang, Hao; Guo, Zhiling; Wang, Mingzheng

Abstract: Online entertainment platforms such as Youtube host a vast amount of user-gener ... Expand

Abstract: Online entertainment platforms such as Youtube host a vast amount of user-generated content (UGC). The unique feature of two-sided UGC entertainment platforms is that creators' content generation and users' content usage can influence each other. However, traditional recommender systems often emphasize content usage but ignore content generation, leading to a misalignment between these two goals. To address the challenge, this paper proposes a prescriptive uplift framework to balance content generation and usage through personalized recommendations. Specifically, we first predict the heterogeneous treatment effects (HTEs) of recommended contents on creators' content generation and users' content usage, then consider these two predicted HTEs simultaneously in an optimization model to determine the recommended contents for each user. Using a large-scale real-world dataset, we demonstrate that the proposed recommendation method better balances content generation and usage and brings a 42% increase in participants' activity compared to existing benchmark methods. Collapse

Topics: recommender system cloud computing digital service music streaming service information system use

Methods: optimization model hidden Markov model regression analysis method machine learning causality analysis

Content Spending and Network Quality in Mobile Channels: A Hidden Markov Model of User Engagement and Content Consumption

2022 | HICSS | Citations: 0

Authors: Zhao, Xia; Huang, Lu; Wang, Lei; Yazdani, Elham; Zhang, Cheng

Abstract: Nowadays, individuals increasingly depend on mobile devices and apps for every a ... Expand

Abstract: Nowadays, individuals increasingly depend on mobile devices and apps for every aspect of their daily lives. Even though the number of mobile users and the time that they spend on mobile apps have grown tremendously, app providers are still struggling with low user engagement and a high attrition rate. This study examines how users’ prior content spending and network delay impact consumers’ mobile content consumption decisions and how the impacts vary in different engagement states. We develop a Hidden Markov Model and calibrate it using a large tapstream data set of individual users’ reading activities from a mobile app provider. We identify three engagement states and heterogeneous impacts of the financial and operational factors. This study will generate important implications on content pricing and user engagement in mobile channels. Collapse

Topics: mobile application price management advertising management

Methods: simulation hidden Markov model computational algorithm