Search results

Purchase conversion prediction aims to improve user experience and convert visitors into real buyers to drive sales of firms; however, the total conversion rate is low, especially for e-retailers. To date, little is known about how e-retailers can scientifically detect users' intents within a purchase conversion funnel during their ongoing sessions and strategically optimize real-time marketing tactics corresponding to dynamic intent states. This study mainly aims to detect a real-time state of the conversion funnel based on graph theory, which refers to a five-class classification problem in the overt real-time choice decisions (RTCDs)—click, tag-to-wishlist, add-to-cart, remove-from-cart and purchase—during an ongoing session.

The authors propose a novel graph-theoretic framework to detect different states of the conversion funnel by identifying a user's unobserved mindset revealed from their navigation process graph, namely clickstream graph. First, the raw clickstream data are identified into individual sessions based on a 30-min time-out heuristic approach. Then, the authors convert each session into a sequence of temporal item-level clickstream graphs and conduct a temporal graph feature engineering according to the basic, single-, dyadic- and triadic-node and global characteristics. Furthermore, the synthetic minority oversampling technique is adopted to address with the problem of classifying imbalanced data. Finally, the authors train and test the proposed approach with several popular artificial intelligence algorithms.

The graph-theoretic approach validates that users' latent intent states within the conversion funnel can be interpreted as time-varying natures of their online graph footprints. In particular, the experimental results indicate that the graph-theoretic feature-oriented models achieve a substantial improvement of over 27% in line with the macro-average and micro-average area under the precision-recall curve, as compared to the conventional ones. In addition, the top five informative graph features for RTCDs are found to be Transitivity, Edge, Node, Degree and Reciprocity. In view of interpretability, the basic, single-, dyadic- and triadic-node and global characteristics of clickstream graphs have their specific advantages.

The findings suggest that the temporal graph-theoretic approach can form an efficient and powerful AI-based real-time intent detecting decision-support system. Different levels of graph features have their specific interpretability on RTCDs from the perspectives of consumer behavior and psychology, which provides a theoretical basis for the design of computer information systems and the optimization of the ongoing session intervention or recommendation in e-commerce.

To the best of the authors' knowledge, this is the first study to apply clickstream graphs and real-time decision choices in conversion prediction and detection. Most studies have only meditated on a binary classification problem, while this study applies a graph-theoretic approach in a five-class classification problem. In addition, this study constructs temporal item-level graphs to represent the original structure of clickstream session data based on graph theory. The time-varying characteristics of the proposed approach enhance the performance of purchase conversion detection during an ongoing session.

This study is to propose a more effective and efficient analytic methodology based on within-site clickstream associated with path visualization to explore the channel dependence of consumers' latent shopping intent and the related behaviors, with which in turn to gain insight concerning the interactivity between webpages.

The primary intention of the research is to design and develop a more effective and efficient approach for exploring the consumers' latent shopping intent and the related behaviors from the clickstream data. The proposed methodology is to use text-mining package, consisting of the combination of hierarchical recurrent neural networks and Hopfield-like neural network equipped with Laplacian-based graph visualization to visualize the consumers' browsing patterns. Based on the observed interactivity between webpages, consumers' latent shopping intent and the related behaviors can be understood.

The key finding is to evidence that consumers' latent shopping intent and related behaviors within website depend on channels the consumers click through. The accessing consumers through channels of paid search and display advertising are identified and categorized as goal-directed and exploratory modes, respectively. The results also indicate that the effect of the content of webpage on the consumer's purchase intent varies with channels. This implies that website optimization and attribution of online advertising should also be channel-dependent.

This is important for the managerial and theoretical implications: First, to uncover the channel dependence of consumer's latent shopping intent and browsing behaviors would be helpful to the attribution of the online advertising for the sales promotion. Second, in the past, webmasters did not understand users' preferences and make decisions of reorganization purely on the user's browsing path (sequential page view) without appraising psychological perspective, that is, user's latent shopping intent.

This study is the first to explore the channel dependences of consumer's latent shopping intent and the related browsing behaviors through within-site clickstream associated with path visualization. The findings are helpful to the attribution of the online advertising for the sales promotion and useful for webmasters to optimize the effectiveness and usability of their websites and in turn promote the purchase decision.

Allocating budget optimally to marketing channels is an increasingly difficult venture. This difficulty is compounded by an increase in the number of marketing channels, a rise in siloed data between marketing technologies, and a decrease in individually identifiable data due to legislated privacy policies. The authors explore the rich attribution modeling literature and discuss the different model types and approaches previously used by practitioners and researchers. They also investigate the changing landscape of marketing attribution, discuss the advantages and disadvantages of different data handling approaches (i.e., aggregate vs. individualistic data), and present a research agenda for future attribution research.

This paper is designed to illustrate how clickstream data, collected from a B2B web site and then analyzed using web analytics software, can be used to evaluate and improve B2B web site performance. A number of issues in the application of clickstream data and web analytics software are to be identified and discussed.

A case study approach is used to present some of the technical issues in the field of web analytics and to demonstrate their value in B2B web site management. Three field experiments, focusing on incorporating ways to discourage shopping‐cart abandonment and the use of two different free‐shipping promotions, were used as the basic research method for collecting the data. Web traffic conversion funnels are used to conduct the analysis and present the findings.

The analysis of clickstream data using web analytics procedures serves as a useful tool in the enhancement of a B2B web site by investigating how visitors move through the web site conversion process and complete their purchase. Improved sales result from each of the three field experiments.

Researchers may use the paper as evidence that web analytics methods can be applied successfully in a B2B application for a technology‐oriented company.

The paper illustrates the use of clickstream data to measure the progression of web site visitors through the conversion process toward purchase.

Insight is provided into the usefulness of web analytics as a framework for performance measurement that is used to drive success for B2B web sites.

The purpose of this paper is to present competing risks models and show how dwell times can be applied to predict users’ online behavior. This information enables real-time personalization of web content.

This paper models transitions between pages based upon the dwell time of the initial state and then analyzes data from a web shop, illustrating how pages that are linked “compete” against each other. Relative risks for web page transitions are estimated based on the dwell time within a clickstream and survival analysis is used to predict clickstreams.

Using survival analysis and user dwell times allows for a detailed examination of transition behavior over time for different subgroups of internet users. Differences between buyers and non-buyers are shown.

As opposed to other academic fields, survival analysis has only infrequently been used in internet-related research. This paper illustrates how a novel application of this method yields interesting insights into internet users’ online behavior.

A key goal of any online retailer is to increase their customer conversation rates. Using survival analysis, this paper shows how dwell-time information, which can be easily extracted from any server log file, can be used to predict user behavior in real time. Companies can apply this information to design websites that dynamically adjust to assumed user behavior.

The method shows novel clickstream analysis not previously demonstrated. Importantly, this can support the move from web analytics and “big data” from hype to reality.

This paper aims to demonstrate how consumer clickstream data from a leading hotel search engine can be used to validate two hidden information processing stages – first eliminate alternatives, then choose – proposed by the revered information processing theory of consumer choice.

This study models the two hidden information processing stages as hidden states in a hidden Markov model, estimated on consumer search behavior, product attributes and diversity of alternatives in the consideration set.

First, the stage of information processing can be statistically characterized in terms of consumer search covariates, including trip characteristics, use of search tools and the diversity of the consideration set, operationalized in terms of: number of brands, dispersion of price and dispersion of quality. Second, users are more sensitive to price and quality in the first rather than the second stage, which is closer to purchase.

The results suggest practical implications for how search engine managers can target consumers with appropriate marketing-mix actions, based on which information processing stage consumers might be in.

Most previous studies on validating the information processing theory of consumer choice have used laboratory experiments, subjects and information display boards comprising hypothetical product alternatives and attributes. Only a few studies use observational data. In contrast, this study uniquely uses point-of-purchase clickstream data on actual visitors at a leading hotel search engine and tests the theory based on real products, attributes and diversity of the consideration set.

The objective of this paper is to propose a consumer-behavior-based intelligence (CBBI) model to identify market structure so as to monitor product competition. Competitive intelligence extracted from Chinese e-business clickstream data is exploited to examine the relevance of consumers' heterogeneous behavioral feedback, namely, click, tag-into-favorite, time-of-browsing, add-into-cart, and remove-from-cart, to visualize the competitive product market structure and to predict product-level sales.

Our proposed CBBI model consists of visualization and prediction, which explore e-business clickstream data. We conduct the visualization and segmentation of market structure in the form of a perceptual map by employing K-means clustering algorithm and multidimensional scaling technique. Concurrently, we developed an updated Bayesian linear regression (BLR) to predict product-level sales by considering consumers' heterogeneous feedback. Our updated BLR specifically integrated the estimated knowledge of the previous periods to verify whether product sales are period-dependent due to the consumer memory effect in e-commerce, improving the conventional BLR of diffuse prior distribution setup in terms of mean absolute error (MAE) and root mean squared error (RMSE).

Considering the performance of consumers' heterogeneous actions, the present research visualized three different segments of the competitive market structure in a perceptual map, and its horizontal axis is shown as a signal of the ascending trend of product sales. The previous five-day period was ascertained to be the best size of a time window for the consumer memory effect on product sales prediction. This hypothesis is supported by the concept that product sales are period-dependent. The results of the proposed updated BLR indicate that consumer tag-into-favorite, add-into-cart, and remove-from-cart feedback have positive impacts on product-level sales while click and time-of-browsing have the opposite effect.

While the identified competitive product market structure elaborates consumer heterogeneous feedback toward alternative product choices, this paper contributes by extending those homogeneous consumer preferences-related marketing studies. The perceptual map's configuration in respect to period-dependent product sales facilitates the effective inclusion of consumer behavior application in product sales prediction research in e-commerce. This paper helps sellers and retailers better comprehend the impacts of heterogeneous feedback and the consumer memory effect on the degree of competition in the form of product sales. The research results also offer a managerial implication about shaping the competitive edge by conducting different product management strategies in e-commerce platforms.

The headlines of online news are created carefully to influence audience news selection today. The purpose of this paper is to investigate the relationships between news headline presentation and users’ clicking behavior.

Two types of unobtrusive data were collected and analyzed jointly for this purpose. A two-month server log file containing 39,990,200 clickstream records was obtained from an institutional news site. A clickstream data analysis was conducted at the footprint and movement levels, which extracted 98,016 clicks received by 7,120 headlines ever displayed on the homepage. Meanwhile, the presentation of these headlines was characterized from seven dimensions, i.e. position, format, text length, use of numbers, use of punctuation marks, recency and popularity, based on the layout and content crawled from the homepage.

This study identified a series of presentation characteristics that prompted users to click on the headlines, including placing them in the central T-shaped zones, using images, increasing text length properly for greater clarity, using visually distinctive punctuation marks, and providing recency and popularity indicators.

The findings have valuable implications for news providers in attracting clicks to their headlines. Also, the successful application of nonreactive methods has significant implications for future user studies in both information science and journalism.

This paper estimates demand for Internet portals using a clickstream data panel of 2654 users. It shows that familiar econometric methodologies used to study grocery store scanner data can be applied to analyze advertising-supported Internet markets using clickstream data. In particular, it applies the methodology of Guadagni and Little (1983) to better understand households' Internet portal choices. The methodology has reasonable out of sample predictive power and can be used to simulate changes in company strategy.

Over the past two decades, online booking has become a predominant distribution channel of tourism products. As online sales have become more important, understanding booking conversion behavior remains a critical topic in the tourism industry. The purpose of this study is to model airline search and booking activities of anonymous visitors.

This study proposes a stochastic approach to explicitly model dynamics of airline customers’ search, revisit and booking activities. A Markov chain model simultaneously captures transition probabilities and the timing of search, revisit and booking decisions. The suggested model is demonstrated on clickstream data from an airline booking website.

Empirical results show that low prices (captured as discount rates) lead to not only booking propensities but also overall stickiness to a website, increasing search and revisit probabilities. From the decision timing of search and revisit activities, the author observes customers’ learning effect on browsing time and heterogeneous intentions of website visits.

This study presents both theoretical and managerial implications of online search and booking behavior for airline and tourism marketing. The dynamic Markov chain model provides a systematic framework to predict online search, revisit and booking conversion and the time of the online activities.