SOLVING THE DATA-DRIVEN NEWSVENDOR WITH ATTENTION TO TIME

2023 | European Conference On Information Systems | Citations: 0

Authors: Feddersen, Leif; Cleophas, Catherine

Abstract: Inventory management systems support firms in planning for an uncertain future ... Expand

Abstract: Inventory management systems support firms in planning for an uncertain future by using demand forecasts and optimization models to make restocking decisions. Recent work on the "data-driven" newsvendor found that incorporating machine learning (ML) can improve the success of inventory management by accounting for demand-driving information. However, ML methods are infamously hard to interpret, which may hinder their acceptance. To ameliorate this, we show how to apply an interpretable attention-based architecture, the Temporal Fusion Transformer (TFT), to the data-driven newsvendor problem. Our approach replicates and extends the original TFT time series forecasting method to the inventory management domain. We evaluate our method on two real-world retail datasets, each covering 260 perishable food items, and provide domain-specific benchmarks. The computational study illustrates TFT's interpretable predictions and their comparatively high accuracy. Our work aims to lay the groundwork for further design science research on transparency in human-AI collaboration in this domain. Collapse

Topics: human AI collaboration human computer interaction Python decision making accounting

Methods: time series analysis longitudinal research artificial neural network feature engineering machine learning

Theories: learning theory

Novel role-wise attention mechanism for predicting purchases made through chat-based online customer services

2023 | Decision Support Systems | Citations: 0

Authors: Wang, Yajing; Chen, Gang; Xu, Yunjie (Calvin); Lu, Xianghua

Abstract: Online chat has become a key channel for firms to provide pre-purchase customer ... Expand

Abstract: Online chat has become a key channel for firms to provide pre-purchase customer services and generate pur­ chases. Firms must deploy their service personnel based on the customers' purchase probability. Conversational contingency is indicative of purchase probability. However, the unstructured nature of textual data hinders the use of interaction information. We develop a novel role-wise attention mechanism to capture the conversational contingency among customers and service agents. Our results reveal that the role-wise attention mechanism is effective for measuring service interaction quality. When the mechanism is combined with a deep-learning model, it outperforms traditional self-attention mechanisms for predicting customer purchases. The area under the curve of the model is 0.85. Ablation studies indicate that external attention, a core element of the role-wise attention mechanism, substantially improves prediction performance by capturing the conversational contin­ gency between communicators. Collapse

Topics: customer service social media online chat Python service-support information system

Methods: machine learning BERT deep learning design artifact ablation analysis

Unlocking the Power of Voice for Financial Risk Prediction: A Theory-Driven Deep Learning Design Approach

2023 | Management Information Systems Quarterly | Citations: 0

Authors: Yang, Yi; Qin, Yu; Fan, Yangyang; Zhang, Zhongju

Abstract: Unstructured multimedia data (text and audio) provides unprecedented opportunit ... Expand

Abstract: Unstructured multimedia data (text and audio) provides unprecedented opportunities to derive actionable decision-making in the financial industry, in areas such as portfolio and risk management. However, due to formidable methodological challenges, the promise of business value from unstructured multimedia data has not materialized. In this study, we use a design science approach to develop DeepVoice, a novel nonverbal predictive analysis system for financial risk prediction, in the setting of quarterly earnings conference calls. DeepVoice forecasts financial risk by leveraging not only what managers say (verbal linguistic cues) but also how managers say it (vocal cues) during the earnings conference calls. The design of DeepVoice addresses several challenges associated with the analysis of nonverbal communication. We also propose a two-stage deep learning model to effectively integrate managers' sequential vocal and verbal cues. Using a unique dataset of 6,047 earnings call samples (audio recordings and textual transcripts) of S&P 500 firms across four years, we show that DeepVoice yields remarkably lower risk forecast errors than that achieved by previous efforts. The improvement can also translate into nontrivial economic gains in options trading. The theoretical and practical implications of analyzing vocal cues are discussed.Challenge 1: Time variation. Managers' vocal features can vary substantially during conference calls. For example, during the presentation section, when the manager is reading a forward-looking statement, the voice pitch may be quite stable. However, individuals' vocal cues may change as a result of being nervous, uncertain, or excited (Scherer et al., 1991). As such, in the question-answer section, when the manager is being scrutinized by analysts, the voice pitch may change. Mayew et al. (2020) found that the voice pitch of managers during dialogues with analysts is lower by about 4 Hz, on average, compared to their voice pitch during presentation sessions. Therefore, the time-varying patterns of managers' vocal cues may contain useful information. However, prior studies have ignored the time-varying pattern of managers' vocal cues in earnings conference calls (Mayew et al., 2020;, and it is unclear how a predictive model could effectively summarize time-varying vocal sequences.Challenge 2: Vocal-verbal integration. According to nonverbal communication theory (Mehrabian, 1972), vocal cues play a key role in nonverbal communication, as they can either affirm or discredit a message. For example, if a manager claims the company has strong future growth but uses a pessimistic tone of voice, market participants listening to the conference call may spot the irregularity and interpret the verbal message differently. This implies that to accurately gauge the information contained in managers' communication, one should integrate verbal language with the accompanying vocal cues. However, existing computational models (Poria et al., 2017) are limited in terms of integrating these two different communication channels (i.e., vocal and verbal).Challenge 3: Vocal complexity. Identifying the specific acoustic constructs from voice is a complex process, and the literature is still evolving without any consensus on an appropriate model for measuring affective states, emotions, and trust (Mayew & Venkatachalam, 2013). There is also little agreement about how a speaker's vocal cues should be combined to identify emotional states (Schuller, 2010)-e.g., which vocal cues to investigate and measure and how much weight to place on each vocal cue. As a result, attempts to develop constructs from vocal cues may suffer from high measurement errors. Collapse

Topics: database system enterprise information system website accounting social media

Methods: deep learning experiment meta design machine learning design artifact

Theories: transaction cost economics communication theory

Exploring Future Personalization Opportunities in Technologies used by Older Adults with Mild to Moderate Dementia

2023 | HICSS | Citations: 0

Authors: Wood, Rachel; Dixon, Emma; Elsayed-Ali, Salma; Shokeen, Ekta; Lazar, Amanda; Lazar, Jonathan

Abstract: Technologies for aging are a growing market. These technologies have significant ... Expand

Abstract: Technologies for aging are a growing market. These technologies have significant potential to support individuals whose cognitive changes can make everyday activities challenging. However, the adoption and use of these technologies by people with dementia (PwD) remain poor, indicating potential accessibility and usability issues. Such barriers limit PwD’s ability to contribute to the digital economy and fully engage with society. Personalization, which aligns technology with someone’s unique needs and preferences, may address these issues. We used mixed methods with ten people with mild to moderate dementia to explore how previous ways to personalize (i.e., Windows OS built-in features and settings) and newer personalization applications (i.e., Morphic) might reveal future opportunities for personalization features in technology for aging. This study contributes fifteen design considerations, which, if implemented, may increase the involvement of PwD in the digital economy and society. Collapse

Topics: usability personalization information system use user experience Microsoft Windows

Methods: design science usability testing personal interview experiment cognitive walkthrough

Theories: cognitive load theory

Assessing and Enhancing Adversarial Robustness of Predictive Analytics: An Empirically Tested Design Framework

2022 | Journal of Management Information Systems | Citations: 4

Authors: Li, Weifeng; Chai, Yidong

Abstract: As predictive analytics increasingly applies supervised machine learning (SML) m ... Expand

Abstract: As predictive analytics increasingly applies supervised machine learning (SML) models to inform mission-critical decision-making, adversaries become incentivized to exploit the vulnerabilities of these SML models and mislead predictive analytics into erroneous decisions. Due to the limited understanding and awareness of such adversarial attacks, the predictive analytics knowledge and deployment need a principled technique for adversarial robustness assessment and enhancement. In this research, we leverage the technology threat avoidance theory as the kernel theory and propose a research framework for assessing and enhancing the adversarial robustness of predictive analytics applications. We instantiate the proposed framework by developing a robust text classification system, the ARText system. The proposed system is rigorously evaluated in comparison with benchmark methods on two tasks extensively enabled by SML: spam review detection and spam email detection, which then confirmed the utility and effectiveness of our ARText system. Results from numerous experiments revealed that our proposed framework could significantly enhance the adversarial robustness of predictive analytics applications. Collapse

Topics: email spam electronic mail artificial intelligence decision making risk management

Methods: machine learning ensemble learning experiment computational algorithm meta design

Theories: technology threat avoidance theory

System Design Principles for Intergenerational Knowledge Sharing

2022 | DESRIST | Citations: 0

Authors: Nurhas, Irawan; Mattick, Xelia; Geisler, Stefan; Pawlowski, Jan

Abstract: Up to four generations are potentially involved in education and workspaces. Thi ... Expand

Abstract: Up to four generations are potentially involved in education and workspaces. This means that people of different generations can increasingly learn together and share knowledge virtually in the digital age. Nevertheless, the principles for designing systems to support intergenerational knowledge sharing (IKS) are inconclusive. Our results demonstrate the value of applying design science research methodology to capture design principles for IKS systems. We articulate what design goals should be considered and bring more conceptual clarity to this phenomenon by presenting five design principles: a) positive personalization, b) progressive design ecosystem, c) effectual system design, d) iterative goal reflection, e) coopetitive intergenerational tasks. By reflecting on the design process and formalizing a class of design principles, we contribute to design-oriented IKS systems in the digital age. Collapse

Topics: knowledge sharing innovation management usability systems design video conference

Methods: design artifact design requirement design science meta design design principle

Designing the Metaverse

2022 | HICSS | Citations: 11

Authors: Seidel, Stefan; Berente, Nicholas; Nickerson, Jeffrey; Yepes, Gregory

Abstract: The Metaverse, a term coined in science fiction, is now being discussed seriousl ... Expand

Abstract: The Metaverse, a term coined in science fiction, is now being discussed seriously as a new form of infrastructure. The Metaverse is intended to make possible thematically interconnected immersive experiences. In this paper, we conceptualize the Metaverse as a meta design space. Within this space, designers create various interconnected design spaces. We highlight how the key dimensions of human experience (time, space, actors, and artifacts) each introduce tensions for making decisions in those design spaces, and we highlight the transitions between design spaces. This conceptual language opens up this novel and emergent phenomenon both to those wishing to design new disruptive technologies and those seeking to improve existing platform strategies. We conclude by highlighting how the Metaverse will not only comprise immersive virtual experiences but also transitions between physical and virtual experiences. Collapse

Topics: virtual reality digital ecosystem virtual world user experience video game

Methods: meta design theory development simulation

Theories: theory of affordance

Firm Profiling and Competition Assessment via Heterogeneous Occupation Network

2022 | International Conference on Information Systems | Citations: 0

Authors: Zhong, Hao; Liu, Chuanren

Abstract: Extensive efforts have been made by both academics and practitioners to underst ... Expand

Abstract: Extensive efforts have been made by both academics and practitioners to understand inter firm competitive relationship. However, it has never been an easy task to fully character ize firms and assess their competitive relationship owing to the challenge of information heterogeneity. In this regard, we propose a novel IT artifact for firm profiling and inter firm competition assessment guided by Information System Design Theory (ISDT). We start by constructing a Heterogeneous Occupation Network (HON) using employees' oc cupation details and education attainments. Then we adopt a Methpath2Vecbased het erogeneous network embedding model to learn firms' latent profiles (embeddings). Using firm embeddings as input, we train multiple classifiers to assess the competitive relation ship among the firms. We demonstrate the utility of our IT artifact with extensive experi mental study and indepth discussions. Our study also reveals that employees' occupation and education information significantly contribute to the identification of the focal firm's potential competitors. Collapse

Topics: human resource management LinkedIn database system computer software information retrieval

Methods: design artifact machine learning experiment kernel theory design science

Citizen Involvement in Service Co-creation in Urban Living Labs

2021 | HICSS | Citations: 0

Authors: Akasaka, Fumiya; Nakatani, Momoko

Abstract: Urban Living Lab (ULL) is a living lab in which citizens and companies collabora ... Expand

Abstract: Urban Living Lab (ULL) is a living lab in which citizens and companies collaborate to create services for solving problems in a city or region. In ULLs, a variety of citizens participate in a long-term co-creation process including design activities such as concept creation, development, and testing. Unfortunately, few studies have provided useful knowledge about or insights into how to effectively involve citizens with diverse characteristics in such co-creation processes. In this paper, we present a case study illustrating how to involve various citizens in the long-term co-creative design process in ULLs. In this study, we first analyze our ULL project and clarify the various roles that citizens may perform in the co-creation process. Then, on the basis of the analysis results as well as our handson experiences, we provide key insights into obtaining effective citizen involvement in ULLs, which should be helpful to other practitioners and researchers. Collapse

Topics: participatory design communication service infrastructure smartphone systems development electronic mail

Methods: survey design methodology case study design process meta design

Guidance for Cloud Service Selection: Evaluation of a Cloud Broker Platform

2021 | European Conference On Information Systems | Citations: 0

Authors: Hentschel, Raoul; Richter, Alexander; Strahringer, Susanne

Abstract: Cloud brokers are intermediaries supporting the evaluation, selection, and impl ... Expand

Abstract: Cloud brokers are intermediaries supporting the evaluation, selection, and implementation of cloud services. Especially small and medium-sized enterprises with limited technical competencies struggle with a complex and non-transparent market, selecting and combining services from different cloud service providers. They need guidance in the pre-adoption phase to successfully handle selection decisions. Using decisional guidance theory, we have designed a cloud broker platform that aims to provide such guidance. The results of its evaluation show how such a platform improves selection decisions by reducing complexity and structuring the selection process. They also show that the platform's usefulness may be limited in the case of very complex cloud services depending, for example, on the degree of customization needs. Our study provides design knowledge for decisional guidance (in the context of cloud broker platforms) and shows how cloud service selection can be implemented in practice. Collapse

Topics: cloud computing digital platform decision making cloud storage software as a service

Methods: qualitative interview design artifact design science personal interview computational algorithm

Theories: information systems theory