Digitizing local search: An empirical analysis of mobile search behavior in offline shopping

2023 | Decision Support Systems | Citations: 0

Authors: Molitor, Dominik; Daurer, Stephan; Spann, Martin; Manchanda, Puneet

Abstract: Mobile devices have become increasingly prevalent in the context of consumers’ o ... Expand

Abstract: Mobile devices have become increasingly prevalent in the context of consumers’ offline search and shopping behavior by acting as personal decision support tools. This paper investigates the relationship between con­ sumers’ real-time location and their search behavior when shopping offline. We develop two location-specific measures based on mobile device usage to analyze the association between a consumer’s real-time location and their search behavior: Present store distance and present store density. We apply these measures to a unique dataset from a leading mobile product information app that includes >13 million search sessions from 2.5 million consumers searching for 1.8 million different products. Our findings show that store distance and store density significantly influence consumers’ mobile search behavior: detailed searches for product-specific attributes (search depth) increase as store distance decreases and store density increases, while the number of jointly searched products within the same category (search breadth) increases as store distance and density increase. We also find that durable products weaken the main effects of store distance and density on search depth but strengthen it for search breadth. These results provide insights for offline retailers to better understand locationspecific consumer demands and improve their mobile in-app targeting and product assortment decisions. Collapse

Topics: mobile application mobile system geographic information system global navigation satellite system location based service

Methods: descriptive statistic statistical hypothesis test theory development likelihood-ratio test robustness check

Theories: construal level theory

A Method for the Optimized Placement of Bus Stops Based on Voronoi Diagrams

2022 | HICSS | Citations: 0

Authors: Stadler, Timo; Hofmeister, Simon; Dünnweber, Jan

Abstract: In this paper, a new method for placing bus stops is presented. The method is su ... Expand

Abstract: In this paper, a new method for placing bus stops is presented. The method is suitable for permanently installed new bus stops and temporarily chosen collection points for call busses as well. Moreover, our implementation of the Voronoi algorithm chooses new locations for bus stops in such a way that more bus stops are set in densely populated areas and less in less populated areas. To achieve this goal, a corresponding weighting is applied to each possible placement point, based on the number of inhabitants around this point and the points of interest, such as medical centers and department stores around this point. Using the area of Roding, a small town in Bavaria, for a case study, we show that our method is especially suitable for rural areas, where there are few multi-family houses or apartment blocks and the area is not densely populated. Collapse

Topics: application programming interface Python database system geographic information system open source

Methods: computational algorithm case study literature study cluster analysis experiment

Impact of Digital-Only Bank Adoption on Consumer Consumption: Empirical Evidence

2021 | International Conference on Information Systems | Citations: 0

Authors: Fang, Sihan; Kwon, Hyeokkoo Eric; Park, Yongjin

Abstract: Emerging digital-only banks without any offline branches (i.e., digital banks), ... Expand

Abstract: Emerging digital-only banks without any offline branches (i.e., digital banks), such as Chime in the U.S. and WeBank in China, are reshaping the legacy banking industry with their novel business model. However, the extant literature focuses mainly on traditional banks' digital channels (e.g., online banking services), while paying relatively scant attention to digital banks. Thus, the ongoing policy debate swirls around digital banks' impact on consumers and traditional banks. Against this backdrop, this study examines the impact of consumers' digital bank adoption on their financial products, offline consumption, and online consumption-related transaction behavior across traditional and digital banks. To this end, we exploit a unique dataset on more than 100,000 consumers' every transaction with all their digital and traditional banks over 18 months. This study provides valuable implications for policymakers as well as traditional and digital banks regarding the potential benefits and concerns of this new business model. Collapse

Topics: mobile application competitive advantage geographic information system technology adoption online banking

Methods: experimental group longitudinal research propensity score matching difference in differences robustness check

Theories: transaction cost economics

New algorithms for automatic modelling and forecasting of decision support systems

2021 | Decision Support Systems | Citations: 2

Authors: Pedregal, Diego J.

Abstract: Decision support systems often rely on time series forecasting, making the accur ... Expand

Abstract: Decision support systems often rely on time series forecasting, making the accuracy of such systems of paramount importance for their efficiency. Since most systems nowadays require the processing of massive amount of data, automatic identification of time series models has become inevitable. This automatism is inherent in artificial intelligence methods, but it often goes unnoticed that forecasting ‘classical’ methods have also been developing their own automatic methods for a long time. The radical novelty of this paper is the development of a brand new algorithm for identification of structural Unobserved Components models from which decision support systems may benefit. A second point is that combination of forecasts is more fruitful than competition or method selection in some cases. Both points are illustrated in two examples that show the effectiveness of the identification procedure and the forecasting gains when fairly different methods are combined. Collapse

Topics: decision support system

Methods: computational algorithm autoregressive integrated moving average time series analysis longitudinal research Student's t-test

The Impact of AI-powered Shelf Monitoring on Product Sales

2020 | International Conference on Information Systems | Citations: 0

Authors: Deng, Yipu; Zheng, Jinyang; Huang, Liqiang; Kannan, Karthik

Abstract: We collaborate with Danone to study how AI-based shelf monitoring helps with man ... Expand

Abstract: We collaborate with Danone to study how AI-based shelf monitoring helps with manufacturers' shelf management efforts by using data from a field experiment. We find that AI-powered shelf monitoring significantly improves product sales. This effect is only partially persistent in that it diminishes after monitoring is terminated. We further reveal that the positive effect is attributed to independent retailers rather than chained retailers. Since the major difference in shelf monitoring between these two types of retailers is the degree of heterogeneity in shelf space rental contracts, this finding indicates that AIpowered monitoring is better than human monitoring when facing more heterogeneous shelf displays. The finding further suggests the better scalability of AI in coping with more heterogeneous objects. We also interview with the delegates and find a low marginal cost of adopting, which suggests a long-term applicability of AI-powered shelf monitoring to generate value for the manufacturer. Collapse

Topics: artificial intelligence organizational value marketing management

Methods: qualitative interview field experiment experiment experimental group Student's t-test

Complementarity and Cannibalization of Offline-Toonline Targeting: A Field Experiment on Omnichannel Commerce

2020 | Management Information Systems Quarterly | Citations: 0

Authors: Xueming Luo; Yuchi Zhang; Fue Zeng; Zhe Qu

Abstract: As the online channel is crucially important, traditional offline retail stores ... Expand

Abstract: As the online channel is crucially important, traditional offline retail stores seek to induce their existing consumers to buy online with incentives (i.e., offline-to-online targeting). However, it is debatable whether such targeting is truly effective. While advocates argue that online shopping should complement a firm’s store channel, critics counter that doing so may result in cannibalization. Drawing on the channel interplay literature and considering customers’ travel costs, we examine whether and how inducing online shopping complements or cannibalizes a firm’s offline sales. Using a randomized field experiment on over 11,200 customers of a large department store, we provide causal evidence for both the complementarity and cannibalization effects of online and offline channels. Offline-to-online targeting engenders higher online purchases (as intended) than no targeting. The local average treatment effects models suggest that once induced to buy online, consumers who live near the retailer’s physical store tend to increase their offline spending and total sales by 47% (i.e., complementarity effects for nearby consumers). However, for consumers who live far away from the brick-and-mortar store, inducing them to buy online can backfire by reducing offline and total sales by approximately 5.7% for each additional kilometer of distance (i.e., cannibalization effects for distant consumers). Explorations of these mechanisms suggest that distant consumers who are induced to buy online may fail to return to shop in the offline store and purchase less experiential category products with a smaller basket size than other customers, thus leading to a negative net impact on the total sales. These findings alert managers to the dangers of improper targeting and investment in information technology and the importance of consumer heterogeneity for omnichannel commerce across online and offline channels. Collapse

Topics: electronic commerce IT investment online banking virtual reality accounting

Methods: randomized field experiment experimental group field experiment experiment robustness check

Trajectory Dynamics in Innovation: Developing and Transforming a Mobile Money Service Across Time and Place

2019 | Organization Science | Citations: 32

Authors: Oborn, Eivor; Barrett, Michael; Orlikowski, Wanda; Kim, Anna

Abstract: This paper examines how and why innovations are reshaped as they become implemen ... Expand

Abstract: This paper examines how and why innovations are reshaped as they become implemented and used in locales that are distant and distinct from those where the innovation was initially developed. Drawing on an in-depth field study of the innovation process that produced a mobile money system for Kenya, we contribute an understanding of the particular dynamics that arise when an innovation trajectory interacts with local trajectories that constitute the local conditions and practices of specific places. We identify four distinct patterns of trajectory dynamics—separation, coordination, diversification, and integration—each of which has different implications for the innovation, its implementation, and consequences on the ground. Developing a model of trajectory dynamics in innovation, we theorize the processes through which innovations are transformed over time as they interact with multiple local trajectories and the specific innovation outcomes that are generated as a result. Such theorizing reconceptualizes traditional notions of innovation diffusion by explicating how and why innovations change in multiple and unexpected ways as they move to particular places and engage with local conditions and practices. Collapse

Topics: innovation management mobile system mobile payment digital innovation information and communication technology for development

Methods: qualitative interview field study theory development longitudinal research archival research

Theories: theory of economic development

Leveraging Deep-learning and Field Experiment Response Heterogeneity to Enhance Customer Targeting Effectiveness

2019 | International Conference on Information Systems | Citations: 0

Authors: Zhang, Kunpeng; Luo, Xueming

Abstract: Firms seek to better understand heterogeneity in the customer response to market ... Expand

Abstract: Firms seek to better understand heterogeneity in the customer response to marketing campaigns, which can boost customer targeting effectiveness. Motivated by the success of modern machine learning techniques, this paper presents a framework that leverages deep-learning algorithms and field experiment response heterogeneity to enhance customer targeting effectiveness. We recommend firms run a pilot randomized experiment and use the data to train various deep-learning models. By incorporating recurrent neural nets and deep perceptron nets, our optimal deep-learning model can capture both temporal and network effects in the purchase history, after addressing the common issues in most predictive models such as imbalanced training, data sparsity, temporality, and scalability. We then apply the learned optimal model to identify customer targets from the large amount of remaining customers with the highest predicted purchase probabilities. Our application with a large department store on a total of 2.8 million customers supports that optimal deep-learning models can identify higher-value customer targets and lead to better sales performance of marketing campaigns, compared to industry common practices of targeting by past purchase frequency or spending amount. We demonstrate that companies may achieve suboptimal customer targeting not because they offer inferior campaign incentives, but because they leverage worse targeting rules and select low-value customer targets. The results inform managers that beyond gauging the causal impact of marketing interventions, data from field experiments can also be leveraged to identify high-value customer targets. Overall, deep-learning algorithms can be integrated with field experiment response heterogeneity to improve the effectiveness of targeted campaigns. Collapse

Topics: marketing management network effect big data logistics management missing data

Methods: deep learning machine learning field experiment experiment random forest classification

Feedback, task performance, and interface preferences

2018 | European Journal of Information Systems | Citations: 7

Authors: Bellman, Steven; Murray, Kyle B.

Abstract: Interface preferences are influenced by switching costs, including cognitive swi ... Expand

Abstract: Interface preferences are influenced by switching costs, including cognitive switching costs of thinking and task performance. In this research, we use feedback intervention theory to predict that feedback can have psychological effects that override the lock-in effect of cognitive switching costs on interface preference. To demonstrate this effect, we use normative feedback, which compares a user’s task performance to the performance of others. This focuses attention on the user’s self-concept and away from task performance. We use a hedonic information systems (IS) interface – an online game – as feedback valence should have a stronger effect on preferences for hedonic IS as opposed to utilitarian IS. Hedonic IS are preferred for their enjoyment value, as well as their productivity, and positive feedback should be more enjoyable than negative feedback. Results from an online experiment that manipulated the presence of feedback and feedback valence, for a sample of 482 users, support our hypotheses. The theoretical and managerial implications of these results are discussed. Collapse

Topics: task productivity video game hedonistic information system human resource management online game

Methods: experiment chi squared test self reported survey PLS tool survey

Theories: feedback intervention theory

Use of Social CRM to improve Targeted Marketing Campaigns in the Retail Sector

2018 | Americas Conference on Information Systems | Citations: 0

Authors: Lopez, Victor W Bohorquez; Huaynate, Edwin; Mendez, Christiam

Abstract: This study aims to demonstrate that the effectiveness of a targeted marketing ca ... Expand

Abstract: This study aims to demonstrate that the effectiveness of a targeted marketing campaign using coupons can be improved using elements of Social CRM. To achieve this, an experiment was carried out consisting in granting the benefit of 40% discount in the clothing department at Department Stores Paris, a large retail chain with presence in several cities of Peru, only applied by one day in the 10 stores at the national level. For the Traditional CRM, mailing and couponing were used, while for Social CRM, Targeted Facebook was used; in both cases, the customer had to present the coupon (physical or virtual), since it had a bar code to apply the discount and allow the campaign to be tracked. The results show that the proportion of customers who used the coupon received through Social CRM was significantly different from those who used mailing and couponing. Collapse

Topics: marketing management Facebook blog web 2.0

Methods: experiment