As more firms adopt big data analytics to better understand their customers and differentiate their offerings from competitors, it becomes increasingly difficult to generate strategic value from isolated and unfocused ad hoc initiatives. To attain sustainable competitive advantage from big data, firms must achieve agility in combining rich data across the organization to deploy analytics that sense and respond to customers in a dynamic environment. A key challenge in achieving this agility lies in the identification, collection, and integration of data across functional silos both within and outside the organization. Because it is infeasible to systematically integrate all available data, managers need guidance in finding which data can provide valuable and actionable insights about customers. Leveraging relationship marketing theory, we develop a framework for identifying and evaluating various sources of big data in order to create a value-justified data infrastructure that enables focused and agile deployment of advanced customer analytics. Such analytics move beyond siloed transactional customer analytics approaches of the past and incorporate a variety of rich, relationship-oriented constructs to provide actionable and valuable insights. We develop a customized kernel-based learning method to take advantage of these rich constructs and instantiate the framework in a novel prototype system that accurately predicts a variety of customer behaviors in a challenging environment, demonstrating the framework’s ability to drive significant value.

An expanding body of information systems research is adopting a design perspective on artificial intelligence (AI), wherein researchers prescribe solutions to problems using AI approaches rather than describing or explaining AI-related phenomena being studied. In this editorial, we address some of the challenges faced in publishing design research related to AI and articulate viable pathways for publishing such work. More specifically, we highlight six major impediments, use the explosion in the state of the art for large language models to underscore these impediments, propose some pathways for overcoming the impediments, and use several example articles to illustrate how the pathways can be followed for different types of AI-related design artifacts. History: Senior Editor; Associate Editor. Funding: A. Abbasi was funded by the National Science Foundation (NSF) [Grants 2240347 and IIS-2039915] and a Kemper Faculty Award. J. Parsons was funded by the Natural Sciences and Engineering Council of Canada (NSERC) [Grant RGPIN-2020-04916].

Analysts, managers, and policymakers are interested in predictive analytics capable of offering better foresight. It is generally accepted that in forecasting scenarios involving organizational policies or consumer decision making, personal characteristics, including personality, may be an important predictor of downstream outcomes. The inclusion of personality features in forecasting models has been hindered by the fact that traditional measurement mechanisms are often infeasible. Text-based personality detection has garnered attention due to the public availability of digital textual traces, however state-of-the-art models proposed by IBM, Google, Facebook, and academic research are not accurate enough to be used for downstream real-world forecasting tasks. We propose a novel text-based personality measurement approach that improves detection of personality dimensions by 10–20 percentage points relative to the best existing methods developed in industry and academia. Using case studies in the finance and health domains, we show that more accurate text-based personality detection can translate into significant improvements in downstream applications such as forecasting future firm performance or predicting pandemic infection rates. Our findings have important implications for managers focused on enabling, producing, or consuming predictive analytics for enhanced agility in decision making.

Phishing is a significant security concern for organizations, threatening employees and members of the public. Phishing threats against employees can lead to severe security incidents, whereas those against the public can undermine trust, satisfaction, and brand equity. At the root of the problem is the inability of Internet users to identify phishing attacks even when using anti-phishing tools. We propose the phishing funnel model (PFM), a framework for predicting user susceptibility to phishing websites. PFM incorporates user, threat, and tool-related factors to predict actions during four key stages of the phishing process: visit, browse, consider legitimate, and intention to transact. We evaluated the efficacy of PFM in a 12-month longitudinal field experiment in two organizations involving 1,278 employees and 49,373 phishing interactions. PFM significantly outperformed competing models in terms of its ability to predict user susceptibility to phishing attacks. A follow-up three-month field study revealed that employees using PFM were significantly less likely to interact with phishing threats relative to comparison models and baseline warnings. Results of a cost-benefit analysis suggest that interventions guided by PFM could reduce annual phishing-related costs by nearly $1,900 per employee relative to comparison prediction methods.

With greater impetus on broad postmarket surveillance, the Voice of the Customer (VoC) has emerged as an important source of information for understanding consumer experiences and identifying potential issues. In organizations, risk management groups are increasingly interested in working with their information technology teams to develop robust VoC listening platforms. Two key challenges have impeded success. First, prior work has leveraged diverse sets of channels, adverse event types, and modeling methods, resulting in diverging conclusions regarding the viability and efficacy of various user-generated channels and accompanying modeling methods. Second, many existing detection methods rely on “mention models” that have low detection rates, have high false positives, and lack timeliness.

Objective: The current clinical practice of psychiatric evaluation suffers from subjectivity and bias, and requires highly skilled professionals that are often unavailable or unaffordable. Objective digital biomarkers have shown the potential to address these issues. In this work, we investigated whether behavioral and physiological signals, extracted from remote interviews, provided complimentary information for assessing psychiatric disorders. Methods: Time series of multimodal features were derived from four conceptual modes: facial expression, vocal expression, linguistic expression, and cardiovascular modulation. The features were extracted from simultaneously recorded audio and video of remote interviews using task-specific and foundation models. Averages, standard deviations, and hidden Markov model-derived statistics of these features were computed from 73 subjects. Four binary classification tasks were defined: detecting 1) any clinically diagnosed psychiatric disorder, 2) major depressive disorder, 3) self-rated depression, and 4) self-rated anxiety. Each modality was evaluated individually and in combination. Results: Statistically significant differences in various features were found between controls and subjects with mental health conditions. Correlations were found between features and self-rated depression and anxiety scores. In classification tasks, visual heart rate dynamics achieved the best unimodal performance with areas under the receiver-operator curve (AUROCs) of 0.68-0.75 (depending on the classification task). Combining multiple modalities achieved AUROCs of 0.72-0.82. Features from task-specific models outperformed features from foundation models. Conclusion: Multimodal features extracted from remote interviews revealed informative characteristics of clinically diagnosed and self-rated mental health status. Significance: The proposed multimodal approach has the potential to facilitate objective, remote, and low-cost assessment for low-burden automated mental health services.