Pub Date : 2024-11-09DOI: 10.1016/j.dss.2024.114366
Wei Wang , Ying Li , Jian Mou , Kevin Zhu
Extending the theory of perceived risk, this study examines how risk perception, a vital factor in determining investment decisions, comprising both initiative risk statement generated by fundraisers and passive risk disclosure published by backers, influences crowdfunding financing performance. Utilizing a corpus of 126,593 innovative projects from Kickstarter, text analytics is employed to classify risks into controllable and uncontrollable types for an empirical comparative examination. The results show that initiative risk statement negatively impacts financing performance, while passive risk disclosure has a positive influence. Comparatively, passive risk disclosure is superior to initiative risk statement. Uncontrollable (controllable) risks in initiative (passive) risk statement are superior to controllable (uncontrollable) ones. Additionally, a textual cognitive load negatively impacted initiative risk statement and passive risk disclosure. Multiple additional tests, including continuous and discrete measurements of risk, endogeneity correction, and dynamic effects over time, demonstrate the robustness of the results. This study contributes to extending the understanding of online financing risks and providing practical implications for fundraisers and backers in innovative online projects.
{"title":"A comparative analysis of the effect of initiative risk statement versus passive risk disclosure on the financing performance of Kickstarter campaigns","authors":"Wei Wang , Ying Li , Jian Mou , Kevin Zhu","doi":"10.1016/j.dss.2024.114366","DOIUrl":"10.1016/j.dss.2024.114366","url":null,"abstract":"<div><div>Extending the theory of perceived risk, this study examines how risk perception, a vital factor in determining investment decisions, comprising both initiative risk statement generated by fundraisers and passive risk disclosure published by backers, influences crowdfunding financing performance. Utilizing a corpus of 126,593 innovative projects from Kickstarter, text analytics is employed to classify risks into controllable and uncontrollable types for an empirical comparative examination. The results show that initiative risk statement negatively impacts financing performance, while passive risk disclosure has a positive influence. Comparatively, passive risk disclosure is superior to initiative risk statement. Uncontrollable (controllable) risks in initiative (passive) risk statement are superior to controllable (uncontrollable) ones. Additionally, a textual cognitive load negatively impacted initiative risk statement and passive risk disclosure. Multiple additional tests, including continuous and discrete measurements of risk, endogeneity correction, and dynamic effects over time, demonstrate the robustness of the results. This study contributes to extending the understanding of online financing risks and providing practical implications for fundraisers and backers in innovative online projects.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"188 ","pages":"Article 114366"},"PeriodicalIF":6.7,"publicationDate":"2024-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142660643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-06DOI: 10.1016/j.dss.2024.114351
Prabhat Kumar , Danish Javeed , A.K.M. Najmul Islam , Xin (Robert) Luo
Businesses and industries are placing a greater emphasis on information systems for cybersecurity decision-making due to the rising cybersecurity threat landscape and the critical need to protect their digital assets. Threat hunting provides a data-driven and proactive approach to cybersecurity, enabling organizations to efficiently detect, analyze, and respond to cyber threats in real-time. Despite playing a crucial role, these systems face several obstacles, including the manual analysis of technical threat intelligence, the non-Gaussian nature of real-world data, the high rate of false positives produced during threat hunting, and the lack of interpretation and justification for these complex models. This article adopts the computational design science paradigm to develop a novel IT artifact for threat-hunting named DeepSecure. First, to automatically extract latent patterns from multivariate time series datasets, we propose a dynamic vector quantized variational autoencoder technique. Second, a multiscale hierarchical attention bi-directional gated recurrent unit-based threat-hunting mechanism is designed. Finally, we provide the visualization of attention scores to aid in model interpretation. We evaluate the DeepSecure against state-of-the-art benchmarks on two publicly available datasets, namely, ToN-IoT and CSE-CIC-IDS2018. The experimental evaluation proves that our model can efficiently identify threat types. Beyond demonstrating practical utility, the proposed framework can help address the lack of interpretation and justification for complex models in cyber threat detection and will allow organizations to respond to potential security incidents quickly.
由于网络安全威胁的不断增加以及保护数字资产的迫切需要，各行各业都更加重视信息系统的网络安全决策。威胁猎取系统为网络安全提供了一种数据驱动的前瞻性方法，使企业能够高效地实时检测、分析和应对网络威胁。尽管这些系统发挥着至关重要的作用，但也面临着一些障碍，包括技术威胁情报的人工分析、现实世界数据的非高斯性、威胁猎取过程中产生的高误报率，以及缺乏对这些复杂模型的解释和论证。本文采用计算设计科学范式，开发了一种名为 DeepSecure 的新型 IT 工件，用于威胁猎取。首先，为了从多元时间序列数据集中自动提取潜在模式，我们提出了一种动态向量量化变分自动编码器技术。其次，我们设计了一种基于多尺度分层注意力双向门控递归单元的威胁猎捕机制。最后，我们提供了注意力分数的可视化，以帮助解释模型。我们在两个公开数据集（即 ToN-IoT 和 CSE-CIC-IDS2018）上对照最先进的基准对 DeepSecure 进行了评估。实验评估证明，我们的模型可以有效识别威胁类型。除了展示实际效用外，所提出的框架还有助于解决网络威胁检测中复杂模型缺乏解释和论证的问题，并使企业能够快速应对潜在的安全事件。
{"title":"DeepSecure: A computational design science approach for interpretable threat hunting in cybersecurity decision making","authors":"Prabhat Kumar , Danish Javeed , A.K.M. Najmul Islam , Xin (Robert) Luo","doi":"10.1016/j.dss.2024.114351","DOIUrl":"10.1016/j.dss.2024.114351","url":null,"abstract":"<div><div>Businesses and industries are placing a greater emphasis on information systems for cybersecurity decision-making due to the rising cybersecurity threat landscape and the critical need to protect their digital assets. Threat hunting provides a data-driven and proactive approach to cybersecurity, enabling organizations to efficiently detect, analyze, and respond to cyber threats in real-time. Despite playing a crucial role, these systems face several obstacles, including the manual analysis of technical threat intelligence, the non-Gaussian nature of real-world data, the high rate of false positives produced during threat hunting, and the lack of interpretation and justification for these complex models. This article adopts the computational design science paradigm to develop a novel IT artifact for threat-hunting named DeepSecure. First, to automatically extract latent patterns from multivariate time series datasets, we propose a dynamic vector quantized variational autoencoder technique. Second, a multiscale hierarchical attention bi-directional gated recurrent unit-based threat-hunting mechanism is designed. Finally, we provide the visualization of attention scores to aid in model interpretation. We evaluate the DeepSecure against state-of-the-art benchmarks on two publicly available datasets, namely, ToN-IoT and CSE-CIC-IDS2018. The experimental evaluation proves that our model can efficiently identify threat types. Beyond demonstrating practical utility, the proposed framework can help address the lack of interpretation and justification for complex models in cyber threat detection and will allow organizations to respond to potential security incidents quickly.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"188 ","pages":"Article 114351"},"PeriodicalIF":6.7,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142660644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-01DOI: 10.1016/j.dss.2024.114361
Yi-Chen Lee , Chih-Hung Peng , Choon-Ling Sia , Weiling Ke
Enhancing a website's persuasiveness and improving users' satisfaction and intention are critical for companies and website designers. Based on the Fogg Behavior Model (FBM), this study explores the perspective of persuasive technology in the context of a website. We identify and design two types of persuasive features: a visual-preview feature and an information-sidedness feature. We propose that websites with these persuasive features are perceived as more persuasive than their counterparts. We further propose that website persuasiveness is positively related to user satisfaction and behavior intention. Data collected from an experimental study lend support to our hypotheses. Theoretical contribution and managerial implications of this study are discussed.
{"title":"Effects of visual-preview and information-sidedness features on website persuasiveness","authors":"Yi-Chen Lee , Chih-Hung Peng , Choon-Ling Sia , Weiling Ke","doi":"10.1016/j.dss.2024.114361","DOIUrl":"10.1016/j.dss.2024.114361","url":null,"abstract":"<div><div>Enhancing a website's persuasiveness and improving users' satisfaction and intention are critical for companies and website designers. Based on the Fogg Behavior Model (FBM), this study explores the perspective of persuasive technology in the context of a website. We identify and design two types of persuasive features: a visual-preview feature and an information-sidedness feature. We propose that websites with these persuasive features are perceived as more persuasive than their counterparts. We further propose that website persuasiveness is positively related to user satisfaction and behavior intention. Data collected from an experimental study lend support to our hypotheses. Theoretical contribution and managerial implications of this study are discussed.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"188 ","pages":"Article 114361"},"PeriodicalIF":6.7,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142660645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-29DOI: 10.1016/j.dss.2024.114353
Arpan Kumar Kar , Patrick Mikalef , Rohit Nishant , Xin (Robert) Luo , Manish Gupta
Metaverse ecosystems are fast growing platforms which are witnessing wide adoption. Different digital platforms like social media are trying to evolve into metaverse ecosystems which are perceived to enhance the overall experiences of different users. However there is a lack of impactful empirical literature which have attempted to document diverse socio-technical perspectives surrounding these emerging digital platforms. We highlight an overview of current literature in information systems, whereby discourse in metaverse is currently situated. Our editorial also introduces the studies which have been published in the special issue on metaverse, whereby many of the unique socio-technical elements of design, adoption, usage and impacts of metaverse platforms have been discussed. The studies included in the special issue also highlight specific areas of future research, surrounding metaverse platforms. We conclude by showcasing how research in metaverse may evolve to become more impactful over time.
{"title":"The evolution of organizations and stakeholders for metaverse ecosystems: Editorial for the special issue on metaverse part 1","authors":"Arpan Kumar Kar , Patrick Mikalef , Rohit Nishant , Xin (Robert) Luo , Manish Gupta","doi":"10.1016/j.dss.2024.114353","DOIUrl":"10.1016/j.dss.2024.114353","url":null,"abstract":"<div><div>Metaverse ecosystems are fast growing platforms which are witnessing wide adoption. Different digital platforms like social media are trying to evolve into metaverse ecosystems which are perceived to enhance the overall experiences of different users. However there is a lack of impactful empirical literature which have attempted to document diverse socio-technical perspectives surrounding these emerging digital platforms. We highlight an overview of current literature in information systems, whereby discourse in metaverse is currently situated. Our editorial also introduces the studies which have been published in the special issue on metaverse, whereby many of the unique socio-technical elements of design, adoption, usage and impacts of metaverse platforms have been discussed. The studies included in the special issue also highlight specific areas of future research, surrounding metaverse platforms. We conclude by showcasing how research in metaverse may evolve to become more impactful over time.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"188 ","pages":"Article 114353"},"PeriodicalIF":6.7,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142660642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-28DOI: 10.1016/j.dss.2024.114354
Xiang Shi, Jiawei Liu, Yinpeng Liu, Qikai Cheng, Wei Lu
The advent of Large Language Models (LLMs) has shown the potential to improve relevance and provide direct answers in web searches. However, challenges arise in validating the reliability of generated results and the credibility of contributing sources due to the limitations of traditional information retrieval algorithms and the LLM hallucination problem. We aim to transform LLM into a relevant, responsible, and trustworthy searcher in response to these challenges. Rather than following the traditional generative retrieval approach, simply allowing the LLM to summarize the search results, we propose a novel generative retrieval framework leveraging the knowledge of LLMs to foster a direct link between queries and web sources. This framework reforms the retrieval process of the traditional generative retrieval framework by integrating an LLM retriever, and it redesigns the validator while adding an optimizer to ensure the reliability of the retrieved web sources and evidence sentences. Extensive experiments show that our method outperforms several SOTA methods in relevance, responsibility, and trustfulness. It improves search result validity and precision by 2.54 % and 1.05 % over larger-parameter-scale LLM-based systems. Furthermore, it demonstrates significant advantages over traditional frameworks in question-answering and downstream tasks.
{"title":"Know where to go: Make LLM a relevant, responsible, and trustworthy searchers","authors":"Xiang Shi, Jiawei Liu, Yinpeng Liu, Qikai Cheng, Wei Lu","doi":"10.1016/j.dss.2024.114354","DOIUrl":"10.1016/j.dss.2024.114354","url":null,"abstract":"<div><div>The advent of Large Language Models (LLMs) has shown the potential to improve relevance and provide direct answers in web searches. However, challenges arise in validating the reliability of generated results and the credibility of contributing sources due to the limitations of traditional information retrieval algorithms and the LLM hallucination problem. We aim to transform LLM into a relevant, responsible, and trustworthy searcher in response to these challenges. Rather than following the traditional generative retrieval approach, simply allowing the LLM to summarize the search results, we propose a novel generative retrieval framework leveraging the knowledge of LLMs to foster a direct link between queries and web sources. This framework reforms the retrieval process of the traditional generative retrieval framework by integrating an LLM retriever, and it redesigns the validator while adding an optimizer to ensure the reliability of the retrieved web sources and evidence sentences. Extensive experiments show that our method outperforms several SOTA methods in relevance, responsibility, and trustfulness. It improves search result validity and precision by 2.54 % and 1.05 % over larger-parameter-scale LLM-based systems. Furthermore, it demonstrates significant advantages over traditional frameworks in question-answering and downstream tasks.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"188 ","pages":"Article 114354"},"PeriodicalIF":6.7,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142587027","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-28DOI: 10.1016/j.dss.2024.114352
Cecil Eng Huang Chua , Fred Niederman
This editorial essay argues the design science decision support literature has unduly focused on developing technical systems when organizational problem solving and decision making often require socio-technical ones. Decision making in uncertain environments requires other aspects the technical view actively suppresses, such as effectiveness and innovation. We explore this in a three-step argument. First, we show the necessity of a socio-technical mindset using the example of how cholera was demonstrated to be a waterborne disease in 1854 London in two independent investigations - one technical and one socio-technical. The insights from the socio-technical investigation were ultimately found correct; the technical one arrived at a completely wrong conclusion. Second, we argue authors are discouraged from publishing research on socio-technical design artifacts. We use spreadsheets as an example, and show developers prefer publishing their incremental contributions in other outlets. Puzzlingly, researchers prefer publishing technical design science contributions in DSS journal given their preponderance in our pages. Thus, in our third step, we argue the lack of socio-technical design science research arises from a mismatch of evaluation criteria. We suggest DSS journal cultivate a subset of editorial board members with a socio-technical mindset to apply the appropriate criteria while encouraging submissions of this type.
{"title":"Returning the “socio” to decision support research: Expanding beyond a purely technical mindset","authors":"Cecil Eng Huang Chua , Fred Niederman","doi":"10.1016/j.dss.2024.114352","DOIUrl":"10.1016/j.dss.2024.114352","url":null,"abstract":"<div><div>This editorial essay argues the design science decision support literature has unduly focused on developing technical systems when organizational problem solving and decision making often require socio-technical ones. Decision making in uncertain environments requires other aspects the technical view actively suppresses, such as effectiveness and innovation. We explore this in a three-step argument. First, we show the necessity of a socio-technical mindset using the example of how cholera was demonstrated to be a waterborne disease in 1854 London in two independent investigations - one technical and one socio-technical. The insights from the socio-technical investigation were ultimately found correct; the technical one arrived at a completely wrong conclusion. Second, we argue authors are discouraged from publishing research on socio-technical design artifacts. We use spreadsheets as an example, and show developers prefer publishing their incremental contributions in other outlets. Puzzlingly, researchers prefer publishing technical design science contributions in DSS journal given their preponderance in our pages. Thus, in our third step, we argue the lack of socio-technical design science research arises from a mismatch of evaluation criteria. We suggest DSS journal cultivate a subset of editorial board members with a socio-technical mindset to apply the appropriate criteria while encouraging submissions of this type.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"188 ","pages":"Article 114352"},"PeriodicalIF":6.7,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142553841","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-16DOI: 10.1016/j.dss.2024.114350
Heng Zhao , Sijia Zhou
Using empirical data from a third-party platform and a comprehensive public hospital (equipped with an official online healthcare platform) in China, this study employs a two-stage Heckman selection model and find that third-party online healthcare platforms (OHPs) should not be considered an obstacle to promoting official OHPs. Instead, doctors' activities on third-party OHPs increase the demand for doctors on official OHPs. Moreover, this study explores the heterogeneity in the effects of the doctor groups. For example, the impact of specific efforts is stronger for doctors with higher professional titles but weaker for doctors with higher online ratings. This study provides valuable insights for policymakers and hospital administrators to promote and coordinate online services across multiple platforms.
{"title":"Foot in both camps: How do activities on third-party online healthcare platforms affect doctors' demand on official online healthcare platforms?","authors":"Heng Zhao , Sijia Zhou","doi":"10.1016/j.dss.2024.114350","DOIUrl":"10.1016/j.dss.2024.114350","url":null,"abstract":"<div><div>Using empirical data from a third-party platform and a comprehensive public hospital (equipped with an official online healthcare platform) in China, this study employs a two-stage Heckman selection model and find that third-party online healthcare platforms (OHPs) should not be considered an obstacle to promoting official OHPs. Instead, doctors' activities on third-party OHPs increase the demand for doctors on official OHPs. Moreover, this study explores the heterogeneity in the effects of the doctor groups. For example, the impact of specific efforts is stronger for doctors with higher professional titles but weaker for doctors with higher online ratings. This study provides valuable insights for policymakers and hospital administrators to promote and coordinate online services across multiple platforms.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"188 ","pages":"Article 114350"},"PeriodicalIF":6.7,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142530950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-09DOI: 10.1016/j.dss.2024.114349
Dan Gao , He Xu , Pin Zhou
We consider a content market with an ad-supported content platform and a representative producer in the presence of altruistic consumers. The platform may launch different subsidy policies (i.e., a monetary subsidy based on the content demand that directly improves marginal profit or a traffic subsidy that directly improves content quality), and the producer creates content under two pricing strategies (i.e., a fixed pricing strategy and a pay-as-you-wish strategy where consumer can pay for the content as they wish). We develop a stylized model and investigate which subsidy policy is a better choice for the platform when the producer is delegated pricing power. Under a fixed pricing strategy, the platform gets a higher profit in the traffic subsidy policy when the consumers’ basic utility is not too low or the quality cost is small, while the producer gets a higher profit in the traffic subsidy when consumers’ basic utility is high or the quality cost is small. Hence, both subsidy policies can achieve the “win-win” situation under certain conditions. Under the pay-as-you-wish strategy, the platform always gets a higher profit in the traffic subsidy policy, while the producer gets a higher profit in the traffic subsidy policy when the consumers’ basic utility for content is high. Hence, only the traffic subsidy policy can achieve the “win-win” situation under certain conditions. Due to the tradeoff between the subsidy enhancement effect on quality and the quality cost, we observe that although the traffic subsidy policy brings a higher content quality than the monetary subsidy policy under both pricing strategies, the producer can increase or decrease his content quality in the traffic subsidy policy compared with the monetary subsidy policy. Our paper provides guidance on how content platforms can provide the right subsidy policy to the producer.
{"title":"Strategic analysis of an ad-supported content platform’s subsidy policy: The perspective of the producer’s pricing strategies","authors":"Dan Gao , He Xu , Pin Zhou","doi":"10.1016/j.dss.2024.114349","DOIUrl":"10.1016/j.dss.2024.114349","url":null,"abstract":"<div><div>We consider a content market with an ad-supported content platform and a representative producer in the presence of altruistic consumers. The platform may launch different subsidy policies (i.e., a monetary subsidy based on the content demand that directly improves marginal profit or a traffic subsidy that directly improves content quality), and the producer creates content under two pricing strategies (i.e., a fixed pricing strategy and a pay-as-you-wish strategy where consumer can pay for the content as they wish). We develop a stylized model and investigate which subsidy policy is a better choice for the platform when the producer is delegated pricing power. Under a fixed pricing strategy, the platform gets a higher profit in the traffic subsidy policy when the consumers’ basic utility is not too low or the quality cost is small, while the producer gets a higher profit in the traffic subsidy when consumers’ basic utility is high or the quality cost is small. Hence, both subsidy policies can achieve the “win-win” situation under certain conditions. Under the pay-as-you-wish strategy, the platform always gets a higher profit in the traffic subsidy policy, while the producer gets a higher profit in the traffic subsidy policy when the consumers’ basic utility for content is high. Hence, only the traffic subsidy policy can achieve the “win-win” situation under certain conditions. Due to the tradeoff between the subsidy enhancement effect on quality and the quality cost, we observe that although the traffic subsidy policy brings a higher content quality than the monetary subsidy policy under both pricing strategies, the producer can increase or decrease his content quality in the traffic subsidy policy compared with the monetary subsidy policy. Our paper provides guidance on how content platforms can provide the right subsidy policy to the producer.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"188 ","pages":"Article 114349"},"PeriodicalIF":6.7,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142530949","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-09DOI: 10.1016/j.dss.2024.114348
Pengyuan Wang , Guiyang Xiong , Will Wei Sun , Jian Yang
Companies increasingly combine multiple media outlets when launching advertising campaigns. This study employs causal forest to examine the effects of complex multimedia campaigns. The model effectively corrects for selection bias, automatically identifies informative consumer features, and performs automated data-driven consumer segmentation based on the consumer features identified. We analyze a large dataset involving around seven million consumers and four thousand covariates, and provide empirical evidence on the nonlinear effect of repeated ad exposures in the multimedia context, how such effect varies across consumer groups, and the contingent existence of multimedia synergy. We demonstrate that negligence of the selection bias and heterogeneity across segments results in suboptimal conversions and a waste of advertising resources. The analysis procedure that we propose can facilitate decision making for complex advertising campaigns to improve their effectiveness.
{"title":"Evaluating multimedia advertising campaign effectiveness","authors":"Pengyuan Wang , Guiyang Xiong , Will Wei Sun , Jian Yang","doi":"10.1016/j.dss.2024.114348","DOIUrl":"10.1016/j.dss.2024.114348","url":null,"abstract":"<div><div>Companies increasingly combine multiple media outlets when launching advertising campaigns. This study employs causal forest to examine the effects of complex multimedia campaigns. The model effectively corrects for selection bias, automatically identifies informative consumer features, and performs automated data-driven consumer segmentation based on the consumer features identified. We analyze a large dataset involving around seven million consumers and four thousand covariates, and provide empirical evidence on the nonlinear effect of repeated ad exposures in the multimedia context, how such effect varies across consumer groups, and the contingent existence of multimedia synergy. We demonstrate that negligence of the selection bias and heterogeneity across segments results in suboptimal conversions and a waste of advertising resources. The analysis procedure that we propose can facilitate decision making for complex advertising campaigns to improve their effectiveness.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"187 ","pages":"Article 114348"},"PeriodicalIF":6.7,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142531487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-02DOI: 10.1016/j.dss.2024.114342
Stephanie Beyer Diaz, Kristof Coussement, Arno De Caigny
Life event prediction is an important tool for customer relationship management (CRM), because life events shift customers’ preferences towards different products and services. Existing life event research mainly uses cross-sectional data, whereas in the CRM field, incorporating longitudinal data is increasingly common. Because longitudinal data can capture the dynamics of customer behavior, opportunities arise to benchmark the power of longitudinal customer data for predictions of cross-sectional versus longitudinal life events. Therefore, this study compares statistical and machine learning (SaML) classifiers, such as logistic regression, random forest, and XGBoost, with long- and short-term memory networks (LSTM), using data represented in both cross-sectional and longitudinal setups for life event prediction. Through a real-life longitudinal customer data set from a European bank, the authors represent the longitudinal data in a cross-sectional data format, using featurization in the form of aggregation. The available data cover 42 end-of-month snapshots for 760,438 unique customers. For marketing decision-making literature, this article (1) introduces three novel life events (i.e., primary, secondary, and rental residence purchases) to life event predictions; (2) offers guidance for how to leverage longitudinal customer data, according to the comparison of various featurization approaches and benchmarking SaML classifiers against LSTM; and (3) clarifies the importance of features and timing for improving marketing decision-making dynamically. The results show that aggregating features over time is preferable as a featurization approach for cross-sectional modeling using SaML classifiers. Furthermore, LSTM can capture behavioral changes over time, unlike SaML classifiers. It also performs significantly better than SaML classifiers on the area under curve and F1 metrics. Insights into the uses of integrated gradients reveal that feature importance changes over time. An integrated gradients method can assist decision-makers in their efforts to plan effective communication with customers in advance, such as by allocating more resources to customers who exhibit high probabilities of a particular life event occurrence.
{"title":"Improved decision-making through life event prediction: A case study in the financial services industry","authors":"Stephanie Beyer Diaz, Kristof Coussement, Arno De Caigny","doi":"10.1016/j.dss.2024.114342","DOIUrl":"10.1016/j.dss.2024.114342","url":null,"abstract":"<div><div>Life event prediction is an important tool for customer relationship management (CRM), because life events shift customers’ preferences towards different products and services. Existing life event research mainly uses cross-sectional data, whereas in the CRM field, incorporating longitudinal data is increasingly common. Because longitudinal data can capture the dynamics of customer behavior, opportunities arise to benchmark the power of longitudinal customer data for predictions of cross-sectional versus longitudinal life events. Therefore, this study compares statistical and machine learning (SaML) classifiers, such as logistic regression, random forest, and XGBoost, with long- and short-term memory networks (LSTM), using data represented in both cross-sectional and longitudinal setups for life event prediction. Through a real-life longitudinal customer data set from a European bank, the authors represent the longitudinal data in a cross-sectional data format, using featurization in the form of aggregation. The available data cover 42 end-of-month snapshots for 760,438 unique customers. For marketing decision-making literature, this article (1) introduces three novel life events (i.e., primary, secondary, and rental residence purchases) to life event predictions; (2) offers guidance for how to leverage longitudinal customer data, according to the comparison of various featurization approaches and benchmarking SaML classifiers against LSTM; and (3) clarifies the importance of features and timing for improving marketing decision-making dynamically. The results show that aggregating features over time is preferable as a featurization approach for cross-sectional modeling using SaML classifiers. Furthermore, LSTM can capture behavioral changes over time, unlike SaML classifiers. It also performs significantly better than SaML classifiers on the area under curve and F1 metrics. Insights into the uses of integrated gradients reveal that feature importance changes over time. An integrated gradients method can assist decision-makers in their efforts to plan effective communication with customers in advance, such as by allocating more resources to customers who exhibit high probabilities of a particular life event occurrence.</div></div>","PeriodicalId":55181,"journal":{"name":"Decision Support Systems","volume":"187 ","pages":"Article 114342"},"PeriodicalIF":6.7,"publicationDate":"2024-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142423770","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号