Clickstream Data Research Articles

Combining self-reported and clickstream data to understand university students’ learning experiences and outcomes in flipped classrooms

This study examined the relationships between students’ self-reported perceptions of learning environment, students’ course marks, learning strategy and online study duration measured by clickstream data in an undergraduate flipped classroom course amongst a cohort of Australian first-year university students. The clickstream data identified two groups of students using two distinct learning strategies focusing either on completing the assessments in the course or on the learning activities preparing for the face-to-face learning. Students’ perceptions of learning environment were measured by a self-reported questionnaire. Using cluster analysis, students were grouped as either having positive or negative perceptions. Of the students who adopted a learning strategy focusing on assessments, a significantly higher proportion of them hold negative perceptions of learning environment. In contrast, amongst students who used a learning strategy focusing on completing the preparation activities, a significantly lower proportion of them had negative perceptions. Furthermore, students who hold negative perceptions were also found to study less hours than their classmates who had positive perceptions. The multiple regression analyses showed that self-reported perceptions could explain only 4.8% of variance in students’ course marks, whereas learning strategy and online study duration measured by clickstream data predicted around 17.2% of variance in students’ course marks.

Do Beliefs About Intelligence Drive Engagement in Online Learning?

This study investigates the relationship between students’ beliefs about intelligence (fixed vs. growth mindset) and their engagement and behaviour in an online learning platform. The data was collected from 28 students enrolled in COMP90082 – Software Project subject at The University of Melbourne. Students’ beliefs about intelligence were measured through a survey administered during the first week, while their online learning behaviours were captured through clickstream data from the learning management system. The study adopted a two-fold approach: first, students’ learning strategies were identified through cluster analysis of their online session duration. By examining over 41,000 learning actions —such as accessing course materials, participating in discussions, and completing assignments— three distinct learning strategies emerged: “light”, “light-intensive”, and “intensive.” Subsequently, the relationship between these learning strategies and students’ beliefs about intelligence was examined using data visualisation techniques, chi-square tests, and logistic regression models. The findings revealed that students with a growth mindset were more likely to adopt intensive and engaged learning approaches within the online platform. Conversely, those with a fixed mindset tended to exhibit lower engagement levels and less intensive learning strategies. The study may contribute to the growing literature on the psychology of online learning and highlight the potential for tailoring instructional interventions and platform design to foster a growth mindset, thereby enhancing student engagement and academic success in digital learning environments.

The effect of the product categories diversity recommended on cross‐buying in electronic commerce platforms: The moderating role of user navigation heterogeneity

AbstractE‐commerce platforms encourage consumers' cross‐buying behavior to boost user traffic and trading volume. However, balancing the precision and richness of recommended information with the mechanisms influencing consumer cross‐buying remains unclear, which also poses challenges to the specific operation of these platforms. Therefore, this study leverages extensive online behavioral data from an e‐commerce platform, encompassing detailed records of 26,034 consumers. By employing unsupervised machine learning algorithms to distinguish the heterogeneity of consumer browsing, we apply clickstream data to explore the mechanisms of the impact of information diversity, specifically the breadth and depth of recommended product categories, on cross‐buying. This study reveals that the effect of diverse recommendations on online decision‐making undergoes marginal variations due to alterations in both the breadth and depth of these recommendations. Specifically, the depth and breadth of recommended product categories exhibit an inverted U‐shaped relationship with cross‐buying, initially promoting, and subsequently suppressing it. Additionally, consumers with different browsing behavior characteristics respond differently to recommendation diversity. Confused visitors and hedonic visitors positively moderate the depth of information and negatively moderate the breadth of recommendations with the inverted U‐shaped effect on cross‐buying. Search‐oriented visitors positively adjust the inverted U‐shaped relationship between the depth of information and the breadth of recommendations on consumer cross‐buying. This study enriches research on cross‐buying in the domain of recommendations on e‐commerce platforms from the perspective of information diversity, providing valuable insights for optimizing recommendation strategies, promoting cross‐buying behavior, and enhancing consumer loyalty.

Model selection for mixture hidden Markov models: an application to clickstream data

AbstractIn a clickstream analysis setting, Mixture Hidden Markov Models (MHMMs) can be used to examine categorical sequences assuming they evolve according to a mixture of latent Markov processes, each related to a different subpopulation. These models involve identifying both the number of subpopulations and hidden states. This study proposes a model selection criterion based on an integrated completed likelihood approach that accounts for the two latent classes in the model. We implemented a Monte Carlo simulation study to compare selection criteria performance. In scenarios characterised by categorical short length sequences, our proposed measure outperforms the most commonly used model selection criteria in identifying components and states. The paper presents a case study on clickstream data collected from the website of a company operating in the hospitality industry and modelled by an MHMM selected by the proposed score.

Improving Shopping Mall Revenue by Real-Time Customized Digital Coupon Issuance

With the development of big data and deep learning technology, big data and deep learning technology have also been applied to the marketing field, which was a part of business administration. Customer churn management is one of the most important areas of marketing. In this paper, we proposed a method to prevent customer churn and increase purchase conversion rate by issuing customized discount coupons to customers with high churn rate based on big data in real time. After segmenting customer segments with two-dimensional segment analysis, a real-time churn rate estimation model based on clickstream data was generated for each segment. After that, we issued customized coupons to our customers. Finally, we tested the conversion rate and sales growth. A two-dimensional cluster analysis-based churn rate estimation combined with a recommendation system was found to be significantly more useful than the respective simple models. Using this proposed model, it is possible to increase sales by automatically estimating the customer’s churn probability and shopping propensity without the burden of marketing costs in the online shopping mall. Keyword: Customer churn prediction, deep learning, digital marketing, ecommerce, recommendation system.

Forecasting using reference prices with exposure effect

AbstractReference prices (RPs) are consumers' subjective perceptions of prices that have important influences on purchase decisions. The standard RP formulation, which defines RP as an exponentially weighted average of past prices, ignores a certain asymmetry in weights between the regime of a price decrease and that of a price increase, which can be observed by the demand trend during the few days after a price decrease or increase. Such oversight usually leads to overestimation in demand as we illustrate by empirical evidence. We introduce the novel concept of RP with exposure effect (RPEE) that captures such asymmetry in RP formulation by imposing a weight proportional to how much the price is exposed to consumers. The exposure effect can be measured by clickstream data that are available for most e‐retailing platforms. We develop a customer behavioral model that can explain the formation of standard RP, and extend it in a natural way to provide foundation to the use of RPEE, especially for products with few repeat purchases. We then establish empirically the extensive benefit of forecasting from RPEE for e‐retailers that sell thousands of products. We demonstrate that RPEE exhibits significant and consistent improvement over standard RP for products, with around reduced weighted mean absolute percentage error.

Real-Time Clickstream Analytics with Apache

The purpose of this research work is to provide an overview of setting up an Apache-based real-time clickstream data lifecycle for user behaviour analysis and marketing strategy improvement. It uses tools like Apache Kafka, Apache Spark, Amazon S3, AWS Glue Data Catalog, Hive Metastore, and Tableau to meet the challenges of data collecting, purification, and storage. The design offers rapid data processing and analysis using Spark, high-throughput and fault-tolerant data import with Kafka, and scalable storage in Amazon S3. Data retrieval, querying, and transformation are made easier by AWS Glue Data Catalogue and Hive Metastore, while Tableau offers interactive visualisations. Data management capabilities are improved by optional interaction with a data warehouse and data lake. The scalable architecture accommodates increased data quantities and user traffic, and a mathematical model derives useful insights from clickstream data.

Enhancing Customer Retention through Clickstream Data Integration in Pega Customer Profiles

Enhancing Customer Retention through Clickstream Data Integration in Pega Customer Profiles

Understanding self-regulated learning and learner performance in MOOCs

Self-regulated learning (SRL) has been viewed as a critical skill for learner success in MOOCs, but due to methodological limitations of self-reported measures, the relationship between SRL and learner performance remains unquantified. Therefore, this study sought to investigate how SRL impacted learner performance in MOOCs by linking clickstream data about SRL to learner performance variables. Following a social cognitive perspective of SRL, learner traces were categorized into three phases including forethought, performance/volition control, and self-reflection phase. Then separate multiple linear regression analyses were performed to examine the relationship between SRL traces in each phase and learner performance variables (e.g., quizzes scores and forum participation record). The findings of this study indicated that SRL traces in performance/volition control and self-reflection phases positively predict learners’ quizzes scores. In addition, SRL traces in each of the three phases were significantly correlated to learners’ forum participation, despite a small effect of the model. Particularly, self-reflective traces negatively predicted learners’ forum participation but SRL traces in the other two phases had a positive relationship with the outcome variable. Practical implications about supporting learners in MOOCs are discussed in the end.

Exploring the relationship between LMS interactions and academic performance: A Learning Cycle approach

Research on the relationship between the digital traces of students in Learning Management Systems (LMS) and their academic performance has traditionally been an area of interest in the field of learning analytics. Aiming at achieving high interpretability and generalizability, this study reviews past research, defines a new categorization scheme for interactions in LMS and investigates the relationships between clickstream data of students’ activity and course performance, measured as final grade. The results of the multiple regression analysis of Moodle log data collected from three courses of diverse nature using various classifications of interactions suggest that the new categorization, the CILC (Classification of Interactions based on the Learning Cycle), improves the explanatory power when compared to previous classifications. The analysis suggests that the predictive ability of the models could depend on the delivery mode, with predictions improving as the delivery mode transitions from face-to-face learning to online learning. This finding highlights the need for context-specific considerations about the learning process. Compared to previous research, the analysis also reveals nuances that suggest that the relationships may depend on the instructional design. Finally, the findings also seem to support the notion that increased data quantity and quality may improve predictive models. In summary, the study contributes with valuable insights into the interplay between LMS interactions, course delivery mode, instructional design, and academic performance, and advocates for a balanced exploration of white-box and black-box modeling approaches in learning analytics research.

Personalized Advertising in E-Commerce: Using Clickstream Data to Target High-Value Customers

The growing popularity of e-commerce has prompted researchers to take a greater interest in deeper understanding online shopping behavior, consumer interest patterns, and the effectiveness of advertising campaigns. This paper presents a fresh approach for targeting high-value e-shop clients by utilizing clickstream data. We propose the new algorithm to measure customer engagement and recognizing high-value customers. Clickstream data is employed in the algorithm to compute a Customer Merit (CM) index that measures the customer’s level of engagement and anticipates their purchase intent. The CM index is evaluated dynamically by the algorithm, examining the customer’s activity level, efficiency in selecting items, and time spent in browsing. It combines tracking customers browsing and purchasing behaviors with other relevant factors: time spent on the website and frequency of visits to e-shops. This strategy proves highly beneficial for e-commerce enterprises, enabling them to pinpoint potential buyers and design targeted advertising campaigns exclusively for high-value customers of e-shops. It allows not only boosts e-shop sales but also minimizes advertising expenses effectively. The proposed method was tested on actual clickstream data from two e-commerce websites and showed that the personalized advertising campaign outperformed the non-personalized campaign in terms of click-through and conversion rate. In general, the findings suggest, that personalized advertising scenarios can be a useful tool for boosting e-commerce sales and reduce advertising cost. By utilizing clickstream data and adopting a targeted approach, e-commerce businesses can attract and retain high-value customers, leading to higher revenue and profitability.

Firm Competitive Structure and Consumer Reaction in Search Advertisings

Sponsored search advertising has become an important venue for firms competing for consumers. As a result, many keywords attract a large number of bidders, and the competing advertisers may be quite heterogeneous. We examine whether this heterogeneity impacts how consumers perceive and react to such competitions. To this end, we draw on the theory of strategic groups to prescribe the structure of the competitive environment and investigate how strategic groups impact consumers’ clicking and website-visit behavior when viewing sponsored search results. Our unique datasets that combine search results from Google and consumers’ clickstream data enable us to disentangle such an impact. We find strong positive externality for within-group competitors relative to across-group competitors: (1) consumers are more likely to co-visit two firms that belong to the same strategic group, as opposed to two firms from different groups when both firms appear in the search results; (2) the presence of a firm in the search results primes consumers to visit other firms from the same strategic group even when the other firms do not appear in the search results. Our findings contribute to the sponsored search and strategic group literature by theorizing and empirically verifying consumers’ website-visit behaviors from the strategic group perspective.

Furnishing your home? The impact of voice assistant avatars in virtual reality shopping: A neurophysiological study

This study provides insights into the informational cues consumers use in virtual reality (VR)-based retail shopping experiences. The aim of the study is to identify the number and type (extrinsic versus intrinsic) of informational cues that most attract consumers' visual attention, and that are most important in their purchase decision-making in a VR store, with special emphasis on the role of voice assistant (VA) avatars. A sample of 152 Spanish consumers participated in a laboratory-based 2 × 2 between-subjects experiment. The study's main stimulus was a recreation, in both 2D and VR, of a living room in a home. The participants were asked to view the recreation using either a computer screen (2D) or a head-mounted display (HMD). Clickstream data, neurophysiological measures (eye-tracking and GSR) and self-reported measures were used to test the hypotheses. We found that consumers used more informational cues in the product choice process in the 2D online store than in the VR store, but that the VR store generated higher flow state; that the type of cue used depended on the type of platform and that the presence of VA avatars did not influence the number of informational cues consumers used but made them pay more visual attention to the products, and evoked higher arousal.

Building a Data Webhouse to support clickstream data analysis

Building a Data Webhouse to support clickstream data analysis

Newly subscribed! Effects of e-mail newsletters on news-reading habit and subscriber retention during onboarding: evidence from clickstream and subscription data

ABSTRACT Despite the increasing popularity of e-mail newsletters, there have been few studies that examine the effects of signing up for e-mail newsletters among news subscribers, especially its role in enhancing news reading behaviors and subscriber retention for new subscribers. This study investigates how e-mail newsletter sign-ups influence news-reading habits and subscriber retention during onboarding. Using single-source data that combine clickstream data from news sites, e-mail newsletter sign-up records, and payment histories of 16,284 new digital news subscribers across four major markets in the U.S. this study finds that signing up for e-mail newsletters improves news reading habits and digital news subscription duration, with an additive effect of the number of e-mail newsletters signed up for. Regarding the retention mechanism, signing up for e-mail newsletters contributes to retention by helping new subscribers read more frequently and intensely (measures of reading habit), which in turn positively affects subscriber retention.

The Impact of Negative Reviews on Online Search and Purchase Decisions

Despite evidence indicating the significant influence of online reviews on purchase decisions, even after considering a product's average rating ( Vana and Lambrecht 2021 ), the underlying factors behind this effect and the broader impact of reviews on consumer decision making remain uncertain. This study uses clickstream data from a major online retailer to explore how negative reviews affect consumer search and purchase decisions. Leveraging exogenous variation created by the display of online reviews sorted by recency, the authors find that negative reviews significantly reduce a product's purchase probability because they (1) contrast with the often-high average product rating, (2) decrease the probability that consumers continue browsing for information about the focal product, (3) increase the probability of visiting the page of substitute products, and (4) increase the probability of viewing reviews about substitute products. Importantly, these effects apply to utilitarian products but not hedonic products and when reviews pertain to product functionality or customer service but not to taste-related factors. The authors estimate a product's vulnerability to negative reviews along two dimensions—purchase and search probability for substitutes—and display these effects on a two-dimensional map.

Predicting Online Item-Choice Behavior: A Shape-Restricted Regression Approach

This paper examines the relationship between user pageview (PV) histories and their itemchoice behavior on an e-commerce website. We focus on PV sequences, which represent time series of the number of PVs for each user–item pair. We propose a shape-restricted optimization model that accurately estimates item-choice probabilities for all possible PV sequences. This model imposes monotonicity constraints on item-choice probabilities by exploiting partial orders for PV sequences, according to the recency and frequency of a user’s previous PVs. To improve the computational efficiency of our optimization model, we devise efficient algorithms for eliminating all redundant constraints according to the transitivity of the partial orders. Experimental results using real-world clickstream data demonstrate that our method achieves higher prediction performance than that of a state-of-the-art optimization model and common machine learning methods.

Clustering and semi‐supervised classification for clickstream data via mixture models

AbstractFinite mixture models have been used for unsupervised learning for some time, and their use within the semisupervised paradigm is becoming more commonplace. Clickstream data are one of the various emerging data types that demand particular attention because there is a notable paucity of statistical learning approaches currently available. A mixture of first‐order continuous‐time Markov models is introduced for unsupervised and semisupervised learning of clickstream data. This approach assumes continuous time, which distinguishes it from existing mixture model‐based approaches; practically, this allows account to be taken of the amount of time each user spends on each webpage. The approach is evaluated and compared with the discrete‐time approach, using simulated and real data.

Key Event Analysis of Customer Behaviour Using Clickstream Data in Airline Market

COVID-19 travel restrictions have significantly affected airline markets. A behavioural analysis is presented of 1 million customers of a major airline company over 3 years, using clickstream data, combined with COVID-19 Government Response Tracker (OxCGRT) data. The main results are that pre-pandemic, the variations in traffic volumes were seasonal and there was a consistent ratio of search (76%), buy (5%) and e-service (19%) activities across the year. The start of the pandemic caused a sharp drop in website traffic, which minimised at 1/3 of normal levels and then gradually increased so that post-covid volumes are now 20% higher, which reflects pent-up demand and consumer confidence. At the start of the pandemic, e-service increased sharply and then dropped to below pre-pandemic levels. The proportion of buyers decreased significantly at the start of the pandemic and then returned to just below pre-pandemic levels. The proportion of searchers remained high throughout the pandemic. Comparing post-pandemic with pre-pandemic, the proportion of searchers remains higher, buyers has dropped, and e-service remains the same. These results show the importance of distinguishing between different types of online activity, defined by three broad phases in the customer lifecycle: search, buy and e-service, which can only be achieved by using raw, clickstream data. Typically, web server analytics software employ aggregate data and it is much more difficult to uncover nuanced changes that are apparent at the granular level of individual clickstream data. The contribution of the research is to demonstrate a novel analytical methodology that exploits detailed clickstream data to characterize the dynamic changes in customer behaviour, which gives important insights into how online markets change in response to exogenous shocks by enabling key event analysis. Using the approaches outlined in this paper, airlines and e-commerce companies can anticipate, measure behavioural changes and be pro-active in their strategic responses to significant external events in the competitive environment that are likely to affect customer behaviour.

Exploring the Impact of Time Spent Reading Product Information on E-Commerce Websites: A Machine Learning Approach to Analyze Consumer Behavior

In this study, we aim to investigate the influence of the time spent reading product information on consumer behavior in e-commerce. Given the rapid growth of e-commerce and the increasing importance of understanding online consumer behavior, our research focuses on gaining a deeper understanding of customer navigation on e-commerce websites and its effects on purchasing decisions. Recognizing the multidimensional and dynamic nature of consumer behavior, we utilize machine learning techniques, which offer the capacity to handle complex data structures and reveal hidden patterns within the data, thereby augmenting our comprehension of underlying consumer behavior mechanisms. By analyzing clickstream data using Machine Learning (ML) algorithms, we provide new insights into the internal structure of customer clusters and propose a methodology for analyzing non-linear relationships in datasets. Our results reveal that the time spent reading product-related information, combined with other factors such as bounce rates, exit rates, and customer type, significantly influences a customer’s purchasing decision. This study contributes to the existing literature on e-commerce research and offers practical implications for e-commerce website design and marketing strategies.