Papers by Umberto Panniello
IEEE Transactions on Engineering Management, 2023
ABSTRACT Recently, methods for generating context-aware recommendations were classified into the ... more ABSTRACT Recently, methods for generating context-aware recommendations were classified into the pre-filtering, post-filtering and contextual modeling approaches. Although some of these methods have been studied independently, no prior research compared the performance ...
Value in Health, Dec 1, 2022
Most of the work on Context-Aware Recommender Systems (CARSes) has focused on demonstrating that ... more Most of the work on Context-Aware Recommender Systems (CARSes) has focused on demonstrating that the contextual information leads to more accurate recommendations and on developing efficient recommendation algorithms utilizing this additional contextual information. Little work has been done, however, on studying how much the contextual information affects purchasing behavior and trust of customers. In this paper, we study how including context in recommendations affects customers' trust, sales and other crucial business-related performance measures. To do this, we performed a live controlled experiment with real customers of a commercial European online publisher. We delivered content-based recommendations and context-aware recommendations to two groups of customers and to a control group. We measured the recommendations' accuracy and diversification, how much customers spent purchasing products during the experiment, quantity and price of their purchases and the customers' level of trust. We aim at demonstrating that accuracy and diversification have only limited direct effect on customers' purchasing behavior, but they affect trust which drives the customer purchasing behavior. We also want to prove that CARSes can increase both recommendations' accuracy and diversification compared to other recommendation engines. This means that including contextual information in recommendations not only increases accuracy, as was demonstrated in previous studies, but it is crucial for improving trust which, in turn, can affect other business-related performance measures, such as company's sales.
Journal of Product Innovation Management, Feb 9, 2023
Reward‐based crowdfunding (CF) has emerged as a method to solicit funds for innovative projects. ... more Reward‐based crowdfunding (CF) has emerged as a method to solicit funds for innovative projects. Yet, little is still known about the ability of reward‐based CF to act as a signal in the eyes of future consumers, and thus boost the future market performance of new products that innovators intend to commercialize using the campaign funds. In addition, scant research has clarified the boundary conditions that can magnify or weaken the efficacy of this CF signal. Given the relevance of reward‐based CF for supporting innovation, understanding when the CF campaign performance works as an effective signal is of great interest, especially in business settings characterized by high product quality uncertainty. By using the movie industry as a setting, we contribute to fill this gap. Specifically, we argue that the positive effect of the reward‐based CF performance is moderated by two important factors influencing consumers' purchase decisions: the degree of product innovativeness and the expert judgment about the product. Elaborating on the effects of product innovativeness, we posit that this product feature should moderate the positive relationship between CF and subsequent market performances in an inverted U‐shaped fashion. Favorable expert recommendations, on the other hand, should weaken the efficacy of the CF performance as a signal. Results from a sample of 1059 new movies (of which 152 released in theaters) confirm these predictions and offer several remarkable implications for innovators.
Sustainability, Jun 23, 2021
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
Technological Forecasting and Social Change, May 1, 2023
This paper investigates the phenomenon of business models innovation (BMI) empowered by digital t... more This paper investigates the phenomenon of business models innovation (BMI) empowered by digital technologies and activated as a response to Covid-19 crisis. In fact, during the crisis numerous digital redesigns of businesses occurred to pursue both continuity and competitive advantage. Among these, the food retail sector has undergone under the pressure of the crisis intense digital changes, which, however, have not yet been investigated under the theoretical lens of BMI. To fill this gap, the paper analyzes the digital actions taken during the pandemic crisis by two large food retailers, namely Walmart and Carrefour. Covering a wide temporal interval of the pandemic evolution and reviewing multiple geographical markets, the authors interpreted the grocer's digital responses to the crisis in terms of innovation in value creation and capture mechanisms. As a result, three phases of digital BMI have been reconstructed, each characterized by specific mechanisms of value creation and capture experienced by the two grocers during the pandemic. Leveraging these findings, the paper proposes a model capable of defining how digital BMI takes place in response to crises. Results broaden theoretical knowledge and practical suggestions on digital BMI in terms of enabling factors, actionable value mechanisms, and future business opportunities.
Journal of hospitality and tourism management, Dec 1, 2021
Prior literature has reported significant price and revenue reductions in the hotel industry due ... more Prior literature has reported significant price and revenue reductions in the hotel industry due to the emergence of Airbnb. Other studies have documented that hotels' price reactions to the penetration of Airbnb depend on their service level, e.g., low/medium-end versus high end. Relying on a large sample from the Italian market, we contribute by showing that the effect of Airbnb on hotels' price decisions does not only depend on incumbents' quality level, but also on the difference between booking and check-in time. That is, the effect of the penetration of Airbnb on hotels' dynamic price decisions varies over time depending on the core segment hotels target.
International Journal of Electronic Commerce Studies, Jun 1, 2015
Much work has been done on recommender systems (RS) and much evidence was collected from applicat... more Much work has been done on recommender systems (RS) and much evidence was collected from applications about their effectiveness on business. As a consequence, the use of RS has quickly shifted from information retrieval to automatic marketing tools. The main aim of marketing tools is to positively affect customers' purchasing decisions and we know through marketing literature that purchasing decisions are strongly influenced by price. However, few works have explored the issue of including price in a recommendation engine. In this paper, we want to describe the main issues of designing this type of price-sensitive recommendation engine. We want also to demonstrate what the effect is of this design on recommendations' accuracy and on business performance. We demonstrate that including price in an RS improves the accuracy of recommendations, but it has to be properly modeled in order to also improve business performance. We have experimented with a Price-Sensitive RS in a laboratory setting and compared it to a traditional one by varying several settings.
Electronic Commerce Research, Feb 2, 2012
Recently, there has been growing interest in recommender systems (RSs) and particularly in contex... more Recently, there has been growing interest in recommender systems (RSs) and particularly in context-aware RSs. Methods for generating context-aware recommendations were classified into the pre-filtering, post-filtering and contextual modeling approaches. This paper focuses on comparing the pre-filtering, the post-filtering, the contextual modeling and the un-contextual approaches and on identifying which method dominates the others and under which circumstances. Although some of these methods have been studied independently, no prior research compared the relative performance to determine which of them is better. This paper proposes an effective method of comparing the three methods to incorporate context and selecting the best alternatives. As a result, it provides analysts with a practical suggestion on how to pick a good approach in an effective manner to improve the performance of a context-aware recommender system.
International Journal of Production Economics, Aug 1, 2019
In this paper, we examine how the emergence of sharing economy platforms influences incumbents' p... more In this paper, we examine how the emergence of sharing economy platforms influences incumbents' price responses. Grounding on the literature on price reactions to new entrants and on the unique characteristics of the sharing economy, we argue that the effect of the penetration of the sharing economy on incumbents' prices is not straightforward, and actually depends on the type of incumbents as well as certain product/service offer characteristics. Indeed, relying on a large sample of hotel price offerings from the Italian market, we find that the effect of the growing relevance of the sharing economy (exemplified by Airbnb) on incumbents' prices depends on the type of incumbents (low/medium-end versus high-end hotels) as well as on the accommodation period (weekend versus weekdays), and thus on the type of consumers looking for accommodation. Specifically, low/medium-end incumbents set lower prices in geographical areas where sharing economy has a higher penetration, but this occurs only for weekend accommodation search. In contrast, high-end incumbents tend to set higher prices in geographical areas where sharing economy has a higher penetration, irrespective of the accommodation period. We discuss the important implications of our findings for incumbents, sharing economy platforms, consumers, and policy makers.
Technology Analysis & Strategic Management, Apr 29, 2016
ABSTRACT The present article sheds new light on the role of established technologies as a driving... more ABSTRACT The present article sheds new light on the role of established technologies as a driving force behind technological evolution, hence unveiling their breakthrough potential. Specifically, going against the conventional wisdom that only nascent technologies significantly shape future technological developments, we examine the likelihood that established technologies have to become breakthrough solutions. Furthermore, we also analyse if and how the breadth of knowledge base characterising those inventions influences this probability. Based on a sample of 21,000 patents belonging to the aerospace industry granted at the United States Patent and Trademark Office (USPTO), our results reveal that established technologies have an inverted U-shaped effect on the likelihood of becoming breakthroughs, and that such relationship is negatively influenced by a wide knowledge breadth.
Information Processing and Management, Sep 1, 2023
Webology, 2014
Recommender systems (RS) were developed by research as a means to manage the information retrieva... more Recommender systems (RS) were developed by research as a means to manage the information retrieval problem for users searching large databases. Recently they have become very popular among businesses as online marketing tools. Several online companies base their success on these systems, among other conditions. By looking at the last decades, the research on RS can be summarized into two main streams. The first research stream is focused on technical aspects of the algorithms and on identifying new ways to make them more accurate, while the second stream is focused on the effects of RS on customers. Therefore, we can draw several indications from the research on RS about the mistakes that companies should avoid when using RS. In this work we conduct an extensive literature and industrial review and we identify some crucial points managers should mind when developing a RS in order to make it as effective as possible in real world applications, or at least to avoid making it a failure.
International Journal of Bank Marketing, Sep 6, 2018
Purpose The purpose of this paper is to demonstrate that a deeper analysis of customer experience... more Purpose The purpose of this paper is to demonstrate that a deeper analysis of customer experience (CE) can identify idiosyncratic and critical perceptions in the experiences of groups of customers. Design/methodology/approach The methodology that the authors used is made of three main steps: segmentation analysis, profiling and identification of idiosyncratic clusters’ profiles (i.e. those with a CE perception different respect to the whole sample) and among these idiosyncratic clusters, identification of those that may be critical for the business. Findings The authors identified clusters of customers showing significant differences in their perceived experience with respect to the holistic CE model. Nevertheless, a sample of bank managers assessed three cluster profiles among them to be critical signals a company. The identification of these idiosyncratic patterns provides managers with interesting additional insights that would be hidden in a holistic CE model. Practical implications Managers can gain valuable insights of CE from this analysis that should be added to those coming from an holistic CE model. Originality/value This paper contributes to the scientific research in that it extends the knowledge about CE by showing how personal factors can be identified and how drawing additional managerial insights.
Springer eBooks, 2009
T. Di Noia and F. Buccafurri (Eds.): EC-Web 2009, LNCS 5692, pp. 348359, 2009. © Springer-Verlag... more T. Di Noia and F. Buccafurri (Eds.): EC-Web 2009, LNCS 5692, pp. 348359, 2009. © Springer-Verlag Berlin Heidelberg 2009 ... Comparing Pre-filtering and Post-filtering Approach in ... Umberto Panniello1, Michele Gorgoglione1, and Cosimo Palmisano2
Journal of intelligent learning systems and applications, 2011
Customer churn may be a critical issue for banks. The extant literature on statistical and machin... more Customer churn may be a critical issue for banks. The extant literature on statistical and machine learning for customer churn focuses on the problem of correctly predicting that a customer is about to switch bank, while very rarely considers the problem of generating personalized actions to improve the customer retention rate. However, these decisions are at least as critical as the correct identification of customers at risk. The decision of what actions to deliver to what customers is normally left to managers who can only rely upon their knowledge. By looking at the scientific literature on CRM and personalization, this research proposes a number of models which can be used to generate marketing actions, and shows how to integrate them into a model embracing both the analytical prediction of customer churn and the generation of retention actions. The benefits and risks associated with each approach are discussed. The paper also describes a case of application of a predictive model of customer churn in a retail bank where the analysts have also generated a set of personalized actions to retain customers by using one of the approaches presented in the paper, namely by adapting a recommender system approach to the retention problem.
AbstractRecent research has shown that including context in a recommender system may improve its... more AbstractRecent research has shown that including context in a recommender system may improve its performance. The context-based recommendation approaches are classified as pre-filtering, post-filtering and contextual modeling. Moreover, in real e-commerce ...
Abstract Despite the growing popularity of Context-Aware Recommender Systems (CARSs), only limite... more Abstract Despite the growing popularity of Context-Aware Recommender Systems (CARSs), only limited work has been done on how contextual recommendations affect the behavior of customers in real-life settings. In this paper, we study the effects of contextual ...
Uploads
Papers by Umberto Panniello