Retailers are interested in understanding the amount of attention grocery shoppers pay to price information at the point of purchase, as price attention is an important determinant of price perception and purchase behavior. We utilize in-store ambulatory eye-tracking devices to directly measure the extent to which shoppers pay attention to price information as they shop for and consider grocery items for purchase. We find that shoppers visually fixate on price information in roughly 62 % of their considerations. Interestingly, the propensity of price attention changes dynamically during the course of a shopping trip, following an "inverted-U" pattern which peaks about two-thirds of the way through the trip. In addition, while the presence of a price promotion and a larger number of price tags encourage higher levels of price attention, higher purchase frequency is associated with lower levels of price attention. Our findings have important implications for retailers' pricing strategies. (c) 2024 New York University. Published by Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.

Social media listening has become an integral part of many companies marketing strategies. Using a unique dataset of social media comments to 413 movie trailers, we document the systematic differences in sentiments expressed on Facebook and YouTube. First, Facebook comments are less likely to involve sentiments. Second, when sentiments are expressed, Facebook comments tend to be more positive than those on YouTube. Third, on both platforms, comments are more likely to express sentiments after a movie's release than before it. Furthermore, the sentiment gap between Facebook and YouTube diminishes after a movie's release. We propose a behavioral explanation for our findings based on network structure and social desirability bias and test our hypothesis with an experiment. Finally, we demonstrate that cross-platform sentiment divergence is significantly associated with box office revenue.

Using in-store ambulatory eye-tracking, the authors investigate the extent to which lateral and vertical biases drive consumers’ attention in a grocery store environment. The data set offers a complete picture of both where the shopper is located and the shopper’s field of view and visual fixations during the trip. The authors address two research questions: First, do shoppers have a higher propensity to pay attention to products on their left or right side as they traverse an aisle (i.e., is the right side the “right” side)? Second, do shoppers tend to pay more attention to products at their eye level (i.e., is eye level “buy level”)? The authors utilize the exogenous variations in the direction by which shoppers traverse an aisle to identify lateral bias. The exogenous variation of shoppers’ eye-level positions is used to identify vertical bias. The authors find that shoppers pay more attention to products on their right side when traversing an aisle. Contrary to many practitioners’ belief, eye level is not “buy level”; rather, the product level that has the greatest propensity to capture shoppers’ attention is approximately 14.7 inches below eye level (which is around chest level).

Herding behavior refers to the behavior of individuals behaving similarly as a group without directions to coordinate. Herding can demonstrate rational characteristics. When consumers believe that others may have private information about a product, they infer unobserved information through other people’s behaviors, thereby engaging in similar actions themselves. While rational herding behavior has been found mostly in high involvement environments such as the financial markets, this paper provides evidence that such behavior may also occur in a comparatively lower involvement environment such as retailing. To demonstrate herding behavior and test shoppers’ rationality in such, the authors employ a unique dataset from a major TV shopping channel. In this setting, information about other buyers’ purchase decisions is only sometimes observed by shoppers. Evidence suggests that herding happens among shoppers and the herding behavior appears to exhibit rationality. The authors find that herding effects (1) are stronger when relative price discount is smaller, (2) are more prominent for a product category with less digitalizable attributes, and (3) appear to happen mainly in the earlier part of a sales pitch when shoppers have less information about a product and are more uncertain about their product valuation.

Peer education outreach to sex workers is found to be effective in facilitating early detection but not prevention of STI.

With an estimated market size of nearly $18 billion in 2016, casual games (games played over social networks or mobile devices) have become increasingly popular. Because most casual games are free to install, understanding repeat playing behavior is important for game developers as it directly drives advertising revenue. Game developers are keenly interested in benchmarking their game versus the market average, and understanding how genre and various game mechanics drive repeat playing behavior. Such cross-sectional analysis, however, is difficult to conduct because individual-level data on competitors’ games are not publicly available, and that the casual gaming industry is highly fragmented with each firm making only a handful of games. I develop a Bayesian approach, based on a parsimonious Hidden Markov Model at the individual level in conjunction with data augmentation, to study repeat playing behavior using only publicly available data. After applying the proposed approach to a sample of 379 casual games, I find that the average daily attrition rate across game is around 36.5%, with an average “play” rate of 47.9%, resulting in an average ARPU (average revenue per user) across games of around 20.5 cents. Certain genres are linked to higher attrition rates and play rates. In addition, giving out a “daily bonus” or limiting the amount of time that gamers can play each day are associated with a 17.7% and 16.4% higher ARPU, respectively.

This work bridges theory and practice on mobile promotions and proposes a research agenda. We do so by first defining mobile promotions and distinguishing them from mobile advertising. We then develop a framework for various stakeholders in the mobile promotion ecosystem. Finally, we advance research questions concerning each stakeholder and view these questions through the lens of several overarching themes that surround mobile promotions, such as the privacy–value tradeoff, return on investment, spatiotemporal targeting, inter-media substitution, and channel and consumer power.

ObjectivePeer-led outreach is a critical element of HIV and STI-reduction interventions aimed at sex workers. We study the association between peer-led outreach to sex workers and the time to utilize health facilities for timely STI syndromic-detection and treatment. Using data on the timing of peer-outreach interventions and clinic visits, we utilize an Extended Cox model to assess whether peer educator outreach intensity is associated with accelerated clinic utilization among sex workers.MethodsOur data comes from 2705 female sex workers registered into Pragati, a women-in-sex work outreach program, and followed from 2008 through 2012. We analyze this data using an Extended Cox model with the density of peer educator visits in a 30-day rolling window as the key predictor, while controlling for the sex workers' age, client volume, location of sex work, and education level. The principal outcome of interest is the timing of the first voluntary clinic utilization.ResultsMore frequent peer visit is associated with earlier first clinic visit (HR: 1.83, 95% CI, 1.75-1.91, p <.001). In addition, 18% of all syndrome-based STI detected come from clinic visits in which the sex worker reports no symptoms, underscoring the importance of inducing clinic visits in the detection of STI. Additional models to test the robustness of these findings indicate consistent beneficial effect of peer educator outreach.ConclusionsPeer outreach density is associated with increased likelihood of and shortened duration to clinic utilization among female sex workers, suggesting potential staff resourcing implications. Given the observational nature of our study, however, these findings should be interpreted as an association rather than as a causal relationship.

Researchers often collect continuous consumer feedback (moment-to-moment, or MTM, data) to understand how consumers respond to a variety of experiences (e.g., viewing a TV show, undergoing a colonoscopy). Analyzing how MTM judgments are integrated into overall evaluations allows researchers to determine how the structure of an experience influences consumers' post-experience satisfaction. However, this analysis is challenging because of the functional nature of MTM data. As such, previous research has typically been limited to identifying the influence of heuristics, such as relying on the average intensity, peak, and ending. We develop a Bayesian functional linear model to study how the different “moments” in the MTM data contribute to the overall judgment. Our approach incorporates a (temporally) weighted average of MTM data as well as specific “patterns” such as peak and trough, thus nesting previous approaches such as the “peak-end” rule as special cases. We apply our methodology to analyze data on TV show pilots collected by CBS. Our results reveal several interesting empirical findings. First, the last quintile of a TV show is weighted about four times as much as each of the first four quintiles. Second, patterns such as peak and trough do not play substantial roles in driving overall evaluations for TV shows. Finally, the last quintile is more important for procedural dramas than for serial dramas. We discuss the managerial implications of our results and other potential applications of our general methodology.

We develop a methodology to predict box office performance of a movie at the point of green-lighting, when only its script and estimated production budget are available. We extract three levels of textual features (genre and content, semantics, and bag-of-words) from scripts using screenwriting domain knowledge, human input, and natural language processing techniques. These textual variables define a distance metric across scripts, which is then used as an input for a kernel-based approach to assess box office performance. We show that our proposed methodology predicts box office revenues more accurately (29 percent lower mean squared error (MSE)) compared to benchmark methods.

Retailers and manufacturers are keenly interested in understanding unplanned consideration and purchase conversion, but data that capture in-store product consideration have been unavailable in the past. In the current research, the authors use in-store video tracking to collect a novel data set that records shopping behavior at the point of purchase, including product consideration. In conjunction with an entrance survey of purchase intentions, they conduct several descriptive analyses that focus on the incidence, category propensity, behavioral characteristics, and outcome of unplanned consideration. The results reveal several new empirical insights. First, the authors find significant category-level complementarities between planned items and unplanned considerations, which they capture using a latent category map. Second, planned consideration and unplanned consideration differ in key behavioral characteristics (e.g., likelihood of purchase, time of occurrence, number of product touches). Third, greater likelihood of purchase conversion is significantly associated with dynamic factors (e.g., remaining in-store slack, outcome of the previous consideration) and behavioral characteristics (e.g., number of displays viewed, distance to shelf, references to a shopping list). The authors conclude with a discussion of implications of these findings for research and shopper marketing.

The gaming industry is the largest entertainment industry in the United States, with more than $80 billion in revenue annually. Because of the stochasticity of gambling outcomes and the complexity of the casino context, forecasting individual‐level revenues in a casino setting is extremely challenging, and yet crucial for customer relationship management. Current approaches for customer base analysis are usually too general to handle the unique context of the casino setting. To fill this gap between research and practice, this paper develops a stochastic model that incorporates visitation, wagering, and gambling outcomes to forecast gamers' revenues for a major casino operator. The proposed model is parsimonious and can be scaled to handle massive casino customer databases. Despite its parsimony, a holdout prediction test shows that the proposed model provides more accurate individual‐level revenue predictions than other forecasting methods that are based only on the observed data. Copyright © 2012 John Wiley & Sons, Ltd.

Typically, shoppers' paths only cover less than half of the areas in a grocery store. Given that shoppers often use physical products in the store as external memory cues, encouraging shoppers to travel more of the store may increase unplanned spending. Estimating the direct effect of in-store travel distance on unplanned spending, however, is complicated by the difficulty of collecting in-store path data and the endogeneity of in-store travel distance. To address both issues, the authors collect a novel data set using in-store radio frequency identification tracking and develop an instrumental variable approach to account for endogeneity. Their analysis reveals that the elasticity of unplanned spending on travel distance is 57% higher than the uncorrected ordinary least squares estimate. Simulations based on the authors' estimates suggest that strategically promoting three product categories through mobile promotion could increase unplanned spending by 16.1%, compared with the estimated effect of a benchmark strategy based on relocating three destination categories (7.2%). Furthermore, the authors conduct a field experiment to assess the effectiveness of mobile promotions and find that a coupon that required shoppers to travel farther from their planned path resulted in a substantial increase in unplanned spending ($21.29) over a coupon for an unplanned category near their planned path ($13.83). The results suggest that targeted mobile promotions aimed at increasing in-store path length can increase unplanned spending.

With an estimated market size of over $6 billion in 2011, “social” games (games played over social networks such as Facebook or Google+) have become increasingly popular recently. Understanding gamer retention and churn is important for game developers, as retention rate is a key input to gamer lifetime value. However, as individual-level data on gaming behavior are not publicly available, developers generally rely on only aggregate statistics such as DAU (daily active users) and MAU (monthly active users), and compute ad hoc metrics such as the DAU/MAU ratio to assess retention rate, often resulting in very inaccurate estimates. I propose a Bayesian approach to estimate retention rates of social games using only aggregate DAU and MAU data. The proposed method is based on a BG/BB model (Fader et al. 2010) at the individual level in conjunction with a data augmentation approach to estimate the model parameters. After validating the performance of the proposed method through a simulation study, I apply the proposed approach to a sample of 379 social games. I find that the average 1-day and 7-day retention rates for new players across games are 59.0% and 10.5%, respectively. Further, my results suggest that the median break-even acquisition cost per gamer is about 13.1 cents. In addition, giving out a “daily bonus” or limiting the amount of time that gamers can play each day may increase 1-day retention rate by 6.3% and 6.9%, respectively.

We show how a retailer can estimate the optimal price of a new product using observed transaction prices from online second-price auction experiments. For this purpose we propose a Bayesian Pólya tree approach which, given the limited nature of the data, requires a specially tailored implementation. Avoiding the need for a priori parametric assumptions, the Pólya tree approach allows for flexible inference of the valuation distribution, leading to more robust estimation of optimal price than competing parametric approaches. In collaboration with an online jewelry retailer, we illustrate how our methodology can be combined with managerial prior knowledge to estimate the profit maximizing price of a new jewelry product.

Researchers typically use prediction markets to conduct “event studies” by comparing the price of a contract before and after an event occurs. However, the underlying assumption that market participants react to new events in an unbiased manner is rarely tested. In this paper, we study overand underreactions in prediction markets using in-play soccer betting data. Our results suggest that overand underreactions are driven by how surprising the event is: while market participants in general underreact to new events, they tend to overreact to events that are highly surprising. We propose a behavioral explanation based on conservatism and information salience, and discuss how researchers can deal with these biases when conducting prediction market event studies.

Previous research in finance has found evidences of both overreaction and underreaction to unanticipated events, but has yet to explain why investors overreact to certain events while underreacting to others. In this paper, we hypothesize that while market participants generally underreact to new events due to conservatism, the extent of underreaction is moderated by “surprise,” thus causing market participants to overreact to events that are highly surprising. We test our hypothesis using data from an in-play soccer betting market, where new events (goals) are clearly and exogenously defined, and the degree of “surprise” can be directly quantified (goals scored by underdogs are more surprising). We provide both statistical and economic evidences in support of our hypothesis.

In order to optimize their shopper marketing strategies, retailers and manufacturers are interested in understanding in-store drivers of unplanned spending. In particular, they are interested in understanding shopping behavior at the point of purchase, termed the “first moment of truth” (Inman et al. 2009). In this research, we present and test a conceptual framework of the shopping trip-level drivers of unplanned considerations and the point-of-purchase behavior drivers of conversion to unplanned purchases. We test our hypotheses in a field study where we employ video tracking to measure shoppers’ point-of-purchase behavior. We find that longer in-store travel distance and lower “shopping efficiency” are associated with more unplanned considerations. Further, we show that an unplanned consideration is more likely to turn into a purchase if a shopper (i) spends more time in consideration, (ii) engages in more product touches, (iii) views fewer product shelf displays, (iv) stands closer to the shelf, (v) references external information, and (vi) interacts with the store staff. Implications of these findings for research and shopper marketing are discussed.

Marketing researchers have become increasingly interested in spatial datasets. A main challenge of analyzing spatial data is that researchers must a priori choose the size and make-up of the areal units, hence the resolution of the analysis. Analyzing the data at a resolution that is too high may mask “macro” patterns, while analyzing the data at a resolution that is too low may result in aggregation bias. Thus, ideally marketing researchers would want a “data-driven” method to determine the “optimal” resolution of analysis, and at the same time automatically explore the same dataset under different resolutions, to obtain a full set of empirical insights to help with managerial decision making. In this paper, we propose a new approach for multi-resolution spatial analysis that is based on Bayesian model selection. We demonstrate our method using two recent marketing datasets from published studies: (i) the Netgrocer spatial sales data in Bell and Song (Quantitative Marketing and Economics 5:361–400, 2007), and (ii) the Pathtracker® data in Hui et al. (Marketing Science 28:566–572, 2009b; Journal of Consumer Research 36:478–493, 2009c) that track shoppers’ in-store movements. In both cases, our method allows researchers to not only automatically select the resolution of the analysis, but also analyze the data under different resolutions to understand the variation in insights and robustness to the level of aggregation.