Search

Appraising real estate is challenging since a property's characteristics, location, and neighborhood make up for substantial shares of its price. Current Computer-Assisted Mass Appraisal (CAMA) approaches rely on hedonic models and structured real estate data. Recent work proposed to include geospatial or image data to improve CAMA’s predictive accuracy. However, the value of these data sources and their preparation costs remain unclear. In this study, we use Geographic Information Systems (GIS) and Convolutional Neural Networks (CNNs) to appraise 71,000 properties in Philadelphia. We find that geospatial data requires substantial preprocessing but increases CAMA’s predictive accuracy by 12%, while image data come with higher computational complexity and an improvement of 16%. Using both datatypes is complex to optimize but offers increased robustness towards extreme outliers. Beyond real estate appraisal, our study is one of the first to quantify the value of geospatial data for data-driven services in the information systems discipline. [ABSTRACT FROM AUTHOR]

Once the mainstay of shopping and cultural exchange, many high streets increasingly struggle to compete for their customers' wallets and leisure time against digital shopping. Besides superior convenience and broader assortments, data-driven recommendations of products that fit individual customers' needs are particular assets possessed by online stores. While first recommender systems that leverage the properties of physical environments have been designed and evaluated in shopping malls, their applicability, accuracy, impact, and business value have neither been demonstrated nor evaluated in local high streets. We set out to identify and quantify the impact of geospatial recommendations on high street retail in a large German city center. Having equipped 66 local businesses with more than 120 Bluetooth Low Energy beacons and having distributed a mobile application to 400 customers, we collect geospatial data to trace customer journeys on the high street. In a field experiment, we plan to identify, analyze, and quantify the effects of recommendations in this setting. Our results will provide new data-driven insights into the accuracy, acceptance, impact, and business implications of geospatial recommendations in high street ecosystems. [ABSTRACT FROM AUTHOR]

Employees' acceptance and resistance of new technology and social structure are frequently examined in Information Systems research. Resistance is expressed in various forms, including a lack of cooperation, workarounds, and physical sabotage. Workarounds, in particular, have a dual nature and can refer to both, undesirable behavior that contradicts organizational structure and to desired organizational innovation. While antecedents and different forms of workarounds have been explored, literature has remained silent on how and why workarounds of an individual employee can affect activities performed by other employees and thereby, change work routines on an organizational level. Since employees' day-to-day performances constitute the ostensive patterns of a routine, we argue that workarounds will not only impact performances of adjacent routines, but also transform the organization as a social structure. With a preliminary set of qualitative data from 24 interviews, we used a multiple case study design to conceptualize six patterns that illustrate how and why workarounds can spread through an organization. The patterns are systematized by a framework that considers three types of collaboration and two types of handoffs across routines. This first evidence points at the nature of complex desired and undesired consequences that can emerge through workarounds performed in an organization. [ABSTRACT FROM AUTHOR]

The Digital Transformation alters business models in all fields of application, but not all industries transform at the same speed. While recent innovations in smart products, big data, and machine learning have profoundly transformed business models in the high-tech sector, less digitalized industries--like agriculture--have only begun to capitalize on these technologies. Inspired by predictive maintenance strategies for industrial equipment, the purpose of this paper is to design, implement, and evaluate a predictive maintenance method for agricultural machines that predicts future defects of a machine's components, based on a data-driven analysis of service records. An evaluation with 3,407 real-world service records proves that the method predicts damaged parts with a mean accuracy of 86.34%. The artifact is an exaptation of previous design knowledge from high-tech industries to agriculture--a sector in which machines move through rough territory and adverse weather conditions, are utilized extensively for short periods, and do not provide sensor data to service providers. Deployed on a platform, the prediction method enables co-creating a predictive maintenance service that helps farmers to avoid resources shortages during harvest seasons, while service providers can plan and conduct maintenance service preemptively and with increased efficiency. [ABSTRACT FROM AUTHOR]

The continuing rise of online retail comes at the expense of small and medium-sized stores in local high streets. Many cities now experience substantial vacancies and the decline of independent and familyowned stores, impeding citizens' perceived quality of living. In this paper, we design the community platform 'smartmarket²', with which networks of local retailers interact with networks of customers to co-create a physical and at the same time digital customer experience in a high street. The platform connects with retailers' information systems, while interfacing with in-store technologies to connect with potential customers' smartphones. From a theoretical perspective, the platform exemplifies how previous research on value co-creation, multi-sided (engagement) platforms, and retail communities can complement each other to constitute online-offline customer experience. Based on comparing smartmarket ² with rival IT artifacts, we abstract nascent design knowledge by conceptualizing a design theory for 'community platforms for high street retail' as a new class of IT artifacts. We conclude the paper with identifying how digital services--including cross-promotions, geographical recommender systems, and geospatial analytics--may be offered on the platform to leverage the competitive position of small and medium-sized retailers in local high streets through online-offline customer experience. [ABSTRACT FROM AUTHOR]

In high street retail, abundant research has focused on conceptualizing, empirically investigating, and improving customer experience at touchpoints throughout the customer journey. However, IT--including, smartphones, near-field communication, and broadband access to the Internet--permeates local high streets increasingly and is profoundly transforming the way in which customer experience is co-created throughout a high street customer journey. Current customer experience notations are unable to express customer journeys based on data retrieved from a digitized physical servicescape. The purpose of this paper is to design a domain-specific modeling language (DSML) that enables analyzing and designing customer journeys in a digitized high street retail setting. From a design-oriented standpoint, the developed High Street Journey Modeling Language (HSJML) can be used to design and implement online-offline customer journeys in digitized high streets. From an empirical perspective, the HSJML provides the constructs required for mapping, analyzing, and predicting online-offline customer journeys in local high streets, based on analyzing event-logs from retail platforms. [ABSTRACT FROM AUTHOR]