Key Areas of Research
AI for Customer Journeys: A Transformer Approach
Journal of Marketing Research
AI for Customer Journeys: A Transformer Approach
Zipei Lu and P. K. Kannan, Smith School of Business, University of Maryland
(forthcoming Journal of Marketing Research)
AI for Customer Journeys: A Transformer Approach introduces a novel artificial intelligence (AI) framework for modeling customer journeys in digital marketing. Leveraging transformer-based models – originally developed for natural language processing - this approach analyzes complex sequences of customer interactions across multiple channels (e.g., search, email, display ads). Unlike traditional models, this method considers both the timing and type of interactions, making it uniquely suited to modern multi-touchpoint environments.
“Transformers give us the ability to see the journey as a whole, not just as a series of isolated interactions. That’s a major leap in marketing analytics.”
— PK Kannan
The core innovation lies in its use of multi-head self-attention mechanisms, which model each customer’s journey as a dynamic sequence of touchpoints. This allows marketers to not only predict the likelihood of purchase but also identify when and through which channels interventions are most effective. Furthermore, the model is extended to capture individual-level heterogeneity, enabling personalized insights into how different customers respond to marketing efforts.
“We designed the model to capture the complexity and individuality of digital customer journeys—something traditional models often overlook.”
— Zipei Lu
Using rich data from a major hospitality firm – including over 92,000 users and over half a million visits – the model demonstrates substantial improvements over traditional approaches (e.g., Hidden Markov Models, Poisson Point Process Models, and LSTMs). For example, the proposed model achieves an AUC of 0.92 for out-of-sample conversion predictions compared to 0.85 for LSTM and <0.70 for others. Moreover, it identifies high-potential customers with far greater precision – top-decile predictions yield an 88% true conversion rate versus 34% for LSTM.
Beyond prediction, the model offers descriptive marketing insights, such as how the effectiveness of email or display ads varies over time and across customers. For instance, the study finds that customer-initiated interactions (like direct visits) have stronger and longer-lasting effects than firm-initiated ones (like emails), and the optimal window for intervention is typically within 7 to 14 days before purchase.
The model’s structure also enables profiling and customer segmentation based on latent self-attention patterns, helping marketers understand nuanced motivations like last-minute business bookings versus long-term vacation planning. This insight can inform targeted messaging and A/B testing strategies.
Overall, this AI framework not only enhances predictive accuracy but also delivers actionable insights that can improve ROI, optimize channel mix, and enable real-time personalization in customer engagement.
Zipei Lu, Ph. D. Candidate in Marketing; P. K. Kannan, Dean's Chair in Marketing Science, both at the Smith School
The Influential Solo Consumer: When Engaging in Activities Alone (vs. Accompanied) Increases the Impact of Recommendations
Journal of Marketing Research
Information about the social context of consumption is often seen on review websites or social media when consumers sharing word-of-mouth about an experience indicate whether they engaged in the activity solo or with companions. Across a secondary dataset scraped from Tripadvisor.com, five main experiments, and one supplemental experiment, the current research finds that individuals who engage in consumption activities alone can be a more influential source of recommendations than people who engage in these same activities with others. The results support an attribution-based process, such that people are more likely to attribute a solo (vs. accompanied) review to the quality of the activity itself, leading the solo (vs. accompanied) person’s review to be particularly influential. Further, the studies test the theorizing that perceived interest on the part of the solo (vs. accompanied) consumer leads to the stronger attribution to quality, and therefore that additional cues to intrinsic interest (e.g., presence of a cue to intrinsic or extrinsic motivation) attenuate the influence of solo (vs. accompanied) word-of-mouth. This work has theoretical and managerial relevance for those who seek to understand how the social context of consumption influences other consumers.
Rebecca Ratner, Dean's Professor of Marketing, Robert H. Smith School of Business; Yuechen Wu, assistant professor, Spears School of Business, Oklahoma State
From Man vs. Machine to Man + Machine: The Art and AI of Stock Analyses
Journal of Financial Economics, July 2024
An AI analyst trained to digest corporate disclosures, industry trends, and macroeconomic indicators surpasses most analysts in stock return predictions. Nevertheless, humans win “Man vs. Machine” when institutional knowledge is crucial, e.g., involving intangible assets and financial distress. AI wins when information is transparent but voluminous. Humans provide significant incremental value in “Man + Machine”, which also substantially reduces extreme errors. Analysts catch up with machines after “alternative data” become available if their employers build AI capabilities. Documented synergies between humans and machines inform how humans can leverage their advantage for better adaptation to the growing AI prowess.
Sean Cao, Robert H. Smith School of Business, University of Maryland
EPA Scrutiny and Voluntary Environmental Disclosures
Review of Accounting Studies
Market participants have called on the SEC to address the lack of disclosures about firms’ environmental impacts, investments, and exposures. However, the frictions that obstruct the flow of environmental information are not well understood. I shed light on these frictions by examining whether scrutiny by the Environmental Protection Agency (EPA) restricts the firm’s voluntary environmental disclosures in earnings conference calls. Consistent with the notion that EPA scrutiny gives rise to disclosure frictions, I find a negative relation between EPA scrutiny and the environmental disclosures of scrutinized firms. This negative relation is concentrated among firms without environmental expert directors, suggesting that environmental governance mitigates the chilling effect of EPA scrutiny. In terms of disclosure quality, I show that environmental disclosures include fewer quantitative details under EPA scrutiny. Collectively, these findings provide insights into the frictions that restrict the flow of environmental information to market participants, an important issue given the SEC’s efforts to improve current disclosure practices.
Mark Zakota, Assistant Professor, Robert H. Smith School of Business, University of Maryland
Identifying Competitors in Geographical Markets Using the CSIS Method
Journal of Marketing Research
Businesses with physical footprints – hotels, retailers, and restaurants – must identify the competitors that matter most. Traditional approaches using brand tier or proximity often fail in dynamic or asymmetric markets. We introduce the Conditional Sure Independence Screening (CSIS) method to marketing to identify true competitors based on their pricing influence on a focal firm’s demand. CSIS is computationally efficient, robust to spatial mis-specifications, and effective for identifying, asymmetric, even non-local, and segment-specific competition. It is also an effective variable selection technique.
In applying CSIS to U.S. hotel data our analysis shows that competition intensity varies not only by location or market segments, but that asymmetry is common – many hotels influence others without being influenced in return. Our methodology enables smarter, data-driven pricing and benchmarking and helps tailor strategy to segment and seasonality. In addition, it is scalable across industries such as retail, services, and hospitality.
Xian Gu, Assistant Professor, Kelley School of Business, Indiana University; P.K. Kannan, Dean's Chair in Marketing Science, Smith School of Business, University of Maryland
Logistics Service Provider Technology Report
Logistics Service Provider Technology Report
The Logistics Service Provider Technology Report (LSPTR) will be an annual report published by the University of Maryland’s Supply Chain Management Center that aims to provide technology spend visibility for logistics service providers (LSPs) in a variety of areas.
We find that LSPs do not know how much to invest in technology because public filings do not disclose specifics about IT spend, consulting firms have limited data to back their perspectives, and industry analysts are bias and do not collect hard data. Shippers also cannot compare providers' technology capabilities or investments due to LSPs alignment with strategy being unclear despite marketing various capabilities, and they cannot compare their partners’ technology investment within their segment or the broader market.
Publishing an annual technology report compiling technology spend data will provide a solution to the identified problems and create value for stakeholder groups including, but not limited to: LSPs, software vendors, hardware vendors, shippers, industry associations, trade groups, shareholders, and consulting firms.
The report will encompass all technology-related expenditures of the companies who opt in to provide a complete perspective of LSP interest, activity, and spend on technology, with an initial proof-of-concept/pilot addressing 2 key sub-sets of technology in 2025: AI and robotics.
Geoff Milsom - UMD Professor
Jaclyn Wilton - Advisor
Maggie McGuire - Fellow
Ryan Sachar - UMD Undergraduate Student
Ivy Zheng - UMD Undergraduate Student
CFO Narcissism and the Power of Persuasion Over Analysts: A Mixed-Methods Approach
Review of Accounting Studies
We study the role of CFO narcissism in the intent and ability to positively influence sell-side analysts’ perceptions of the firm. Consistent with narcissists casting favorable impressions on others, we find CFO narcissism is associated with overly optimistic analyst valuations. We then study public persuasion attempts by analyzing conference call transcripts and private persuasion attempts through a laboratory study. In the conference call setting, we provide evidence that narcissistic CFOs use more persuasive language and are more inclined to call on bearish analysts, both of which we link to higher price targets. In the lab study, we simulate a one-on-one conversation and find that narcissists are especially more likely to use coercive methods to induce higher valuations (e.g., threatening to remove private lines of communication). Collectively, we provide evidence that narcissistic CFOs exercise persuasion tactics to favorably influence analysts’ perceptions of firm value.
Chad Ham and Mark Piorkowski - Indiana University; Nick Seybert - University of Maryland; Sean Wang - Southern Methodist University
Conflicted About Coworkers: How Coworker Support Influences Engagement After Status Loss
Personnel Psychology, February 2025
People's needs for status and support are theoretically distinct, yet little research has considered how people cope with having one but not the other. We examine how people react to losing status as a function of whether they typically perceive their coworkers as supportive. Although social support is documented as a resource people can draw on to cope with failure at work, we argue that in the case of failures that implicate status (i.e., status loss), experiencing these events in a more supportive work group may not aid recovery and reengagement. Specifically, we predict that when the preexisting group context is one of more (rather than less) supportive coworkers, status loss may elicit greater ambivalence about those coworker relationships, triggering psychological reactions that undermine engagement. Consistent with this model, in a weekly experience sampling study of working adults (Study 1), having more supportive coworkers led to a stronger negative effect of weekly status loss on subsequent engagement. In scenario-based (Study 2) and high-involvement laboratory (Study 3) experiments featuring different manipulations of coworker support and status loss, we found that when individuals experienced status loss in more (rather than less) supportive work groups, status loss led to lower engagement because it heightened ambivalence about their coworker relationships, which triggered anxiety (Study 2), and self-threat and hurt feelings (Study 3). Theoretical and practical implications are discussed.
Jennifer Carson Marr (UMD), Edward P. Lemay (UMD), Hyunsun Park (Georgia Tech)
Public Pension Contract Minimalism
American Business Law Journal, November 2024
The national pension debt and COVID crises have collided. Post-pandemic economic decline has escalated existing financial strains on state and local pension plans, impacting workers and the public welfare. With unfunded obligations exceeding one trillion dollars, many of these plans are in jeopardy. But the movement to reform government pension contracts has yet to adopt an anchoring idea, leaving judicial decisions in disarray and policymakers without guidance about how to shore up troubled retirement systems. The crux of the problem is the many meanings of contract under state and U.S. Contract Clauses that prevent pension reform. This Essay endorses a promising path forward—contract minimalism. “Contract minimalism” concentrates on the duration of government pension contracts. It posits that public and private employment law should be treated the same. Like its private law counterpart, public sector employment at-will ought to consist of a daily contract interval. A contract-a-day concept entitles employers to change the plan prospectively, with employees receiving a proportionate share of benefits for work performed. Just as several agreements safeguard salaries for labor, they should also mirror the protection afforded to deferred benefits like pensions. Contract minimalism additionally puts public and private sector employers on the same legal footing as to the authority to change pension plan terms. Thus, it aligns public pension benefits with overlapping fields of law, placing them on a firm conceptual foundation. The minimalist approach also has the advantage over approaches that are insufficiently attentive to scarce government resources or employee old-age security. By protecting pension benefits early and incrementally, it advances a middle path with fairer, more coherent results. In the present post-pandemic era of hard choices, minimalism provides an equilibrium between the over and under-protection of pension benefits.
T. Leigh Anenson, Professor of Business Law, University of Maryland and Hannah R. Weiser, Assistant Professor of Law, Bentley University
The Impact of App Crashes on Consumer Engagement
Journal of Marketing
The authors develop and test a theoretical framework to examine the impact of app crashes on app engagement. The framework predicts that consumers increase engagement after encountering a single crash due to their need-for-closure and curiosity, yet reduce engagement after experiencing repeated and concentrated crashes, primarily because of frustration and perceived task unattainability; the recency of crashes moderates these effects. Field data analysis reveals that while a crash truncates a session and reduces content consumption, it increases page views in the following session. However, this increase in page views does not compensate for the loss during the crashed session. Frequent and more concentrated crashes curtail engagement. Three experiments in which crashes are exogenously manipulated in a different context support the validity and generalizability of these findings, confirm the proposed mediators, and demonstrate how to lessen the negative impact of repeated crashes with post-crash messages. The research adds new dimensions to the task pursuit literature and provides managers with a framework to quantify the economic impact of crashes, analyze content substitution behavior, and assess the bias of a transactional view of crash incidents. Additionally, it offers insights into targeted feature release to more tolerant users and strategic design of post-crash messages.
Savannah Wei Shi, Associate Professor of Marketing & J.C. Penney Research Professor, Leavey School of Business Santa Clara University
Seoungwoo Lee*, Assistant Professor, Yonsei School of Business, Yonsei University Seoul
Kirthi Kalyanam, L.J. Skaggs Distinguished Professor Leavey School of Business, Santa Clara University
Michel Wedel, PepsiCo Chaired Professor of Consumer Science, Robert H. Smith School of Business, University of Maryland