“…Our paper fits well to the current high interest of marketing academics in machine learning methods to which both topic models and the RSM belong (Bradlow et al 2017;Chintagunta et al 2016;Dzyabura and Yoganarasimhan 2018;Hagen et al 2020;Wedel and Kannan 2016). Our paper also complies the call to investigate alternative machine learning methods especially for the analysis of clickstream data which Ma and Sun (2020) raise in their recent overview on machine learning in marketing.…”
The increasing importance of online distribution channels is paralleled by a rising interest in gaining insights into the customer journey and browsing behavior. We evaluate several machine learning methods (latent Dirichlet allocation, correlated topic model, structural topic model, replicated softmax model) with respect to their ability to reproduce the browsing behavior of households across websites. In addition, we compare these machine learning methods to a related classical technique, singular value decomposition. In our study, the replicated softmax model outperforms latent Dirichlet allocation, but the correlated topic model attains the overall best performance. Compared to singular value decomposition both the correlated topic model and the replicated softmax model lead to a more efficient compression of web browsing data. On the other hand, singular value decomposition surpasses latent Dirichlet allocation. We interpret results of the correlated topic model and the replicated softmax model by determining combinations of topics or hidden variables that are heterogeneous with respect to visited websites. We show that decision makers should not rely on bivariate measures of site visits, as these do not agree with measures of interdependences between sites that can be inferred from the correlated topic model or the replicated softmax model. We investigate how well topics or hidden variables measured by these methods predict yearly household expenditures. The correlated topic model leads to the best predictive performance, followed by the replicated softmax model. We also discuss how the replicated softmax model can be used to support online marketing decisions of websites.
“…Our paper fits well to the current high interest of marketing academics in machine learning methods to which both topic models and the RSM belong (Bradlow et al 2017;Chintagunta et al 2016;Dzyabura and Yoganarasimhan 2018;Hagen et al 2020;Wedel and Kannan 2016). Our paper also complies the call to investigate alternative machine learning methods especially for the analysis of clickstream data which Ma and Sun (2020) raise in their recent overview on machine learning in marketing.…”
The increasing importance of online distribution channels is paralleled by a rising interest in gaining insights into the customer journey and browsing behavior. We evaluate several machine learning methods (latent Dirichlet allocation, correlated topic model, structural topic model, replicated softmax model) with respect to their ability to reproduce the browsing behavior of households across websites. In addition, we compare these machine learning methods to a related classical technique, singular value decomposition. In our study, the replicated softmax model outperforms latent Dirichlet allocation, but the correlated topic model attains the overall best performance. Compared to singular value decomposition both the correlated topic model and the replicated softmax model lead to a more efficient compression of web browsing data. On the other hand, singular value decomposition surpasses latent Dirichlet allocation. We interpret results of the correlated topic model and the replicated softmax model by determining combinations of topics or hidden variables that are heterogeneous with respect to visited websites. We show that decision makers should not rely on bivariate measures of site visits, as these do not agree with measures of interdependences between sites that can be inferred from the correlated topic model or the replicated softmax model. We investigate how well topics or hidden variables measured by these methods predict yearly household expenditures. The correlated topic model leads to the best predictive performance, followed by the replicated softmax model. We also discuss how the replicated softmax model can be used to support online marketing decisions of websites.
“…The black-box vision systems (e.g., Google's Vision API) are convenient because they provide access to complex machine learning methods with a wide array of customization; moreover, they more easily accessed than many other open-source algorithms. Thus, they are available, cheap, and easy to implement and can be leveraged for empirical studies ( [79,11,80]. They also use very large knowledge graphs as part of the training and validation of algorithms.…”
Section: Number Of Concepts and Ease Of Concept Identificationmentioning
Despite an increase in the empirical study of crowdfunding platforms and the prevalence of visual information, operations management and marketing literature has yet to explore the role that image characteristics play in crowdfunding success. The authors of this manuscript begin by synthesizing literature on visual processing to identify several image characteristics that are likely to shape crowdfunding success. After detailing measures for each image characteristic, they use them as part of a machine-learning algorithm (Bayesian additive trees), along with project characteristics and textual information, to predict crowdfunding success. Results show that the inclusion of these image characteristics substantially improves prediction over baseline project variables, as well as textual features. Furthermore, image characteristic variables exhibit high importance, similar to variables linked to the number of pictures and number of videos. This research therefore offers valuable resources to researchers and managers who are interested in the role of visual information in ensuring new product success.Crowdfunding allows entrepreneurs to request funding from many investors simultaneously, usually in exchange for future products or equity stakes [1,2]. Recent legislative changes also give consumers and firms new ways to interact along these lines. Since 2016, when the U.S. Securities and Exchange Commission (SEC) allowed investors of all net worth amounts to participate in crowdfunding, there has been a substantial increase in the amount of money raised on crowdfunding platforms; in 2020, it reached $500 million in the United States alone, according to the Crowdfunding Center 1 . Dozens of different crowdfunding platforms support rewards-based investing (e.g., Kickstarter, Indiegogo) and equity-based investing (e.g., SeedInvest, StartEngine), and others specialize in individual help (e.g., GoFundMe) and nonprofit funding (e.g., Mightycause). The number of international crowdfunding platforms also has grown, with platforms covering all regions of the world (e.g., JD Crowdfunding and Jingdong in China, Babyloan in France, Crowdprop in South Africa).Both operations management and marketing literature have found many interesting uses for increasingly available crowdfunding data. Some operations management authors leverage crowdfunding data to substantiate the role of new technologies in selecting and disseminating new ideas [3,4], whereas others have sought to identify predictors of crowdfunding success (c.f., [5,6])-such as backer dynamics [7], referral timing [8], founder updates [9], and frequency 1 https://www.thecrowdfundingcenter.com/
“…Since we aim to provide an epistemological picture on AI ethics in marketing, the list of AI applications we cover does not claim to be exhaustive. We also refrain from providing technical or methodological details on respective AI applications and systems (for brief overviews of different AI methods such as machine or deep learning, see for instance Campbell et al, 2020 ; De Bruyn et al, 2020 ; Hagen et al, 2020 ; Ma & Sun, 2020 ). Fig.…”
Section: The Ethics Of Ai In Marketingmentioning
confidence: 99%
“…A focal advantage of leveraging AI in marketing is the opportunity to personalize and customize products and services and the entire marketing mix to maximize engagement, relevance and persuasion, as well as customer satisfaction (Huang & Rust, 2021a , 2021b ; Kumar et al, 2019 ; Puntoni et al, 2021 ). For example, predicting individuals’ psychological traits from their digital footprints and smartphone data (e.g., Gladstone et al, 2019 ; Stachl et al, 2020 ; Youyou et al, 2015 ) offers substantial opportunities for psychological targeting by crafting psychologically tailored advertising and persuasive appeals (Hagen et al, 2020 ; Matz & Netzer, 2017 ; Matz et al, 2017 ; Matz, Appel, et al, 2019 ; Matz, Menges, et al, 2019 ; Matz, Segalin, et al, 2019 ). Recent research showed that even individuals’ income can be predicted from their Facebook Likes and status updates with an accuracy of up to r = 0.43 (Matz, Menges et al, Matz, Appel, et al, 2019 ).…”
Artificial intelligence (AI) is (re)shaping strategy, activities, interactions, and relationships in business and specifically in marketing. The drawback of the substantial opportunities AI systems and applications (will) provide in marketing are ethical controversies. Building on the literature on AI ethics, the authors systematically scrutinize the ethical challenges of deploying AI in marketing from a multi-stakeholder perspective. By revealing interdependencies and tensions between ethical principles, the authors shed light on the applicability of a purely principled, deontological approach to AI ethics in marketing. To reconcile some of these tensions and account for the AI-for-social-good perspective, the authors make suggestions of how AI in marketing can be leveraged to promote societal and environmental well-being.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
