LEE- İşletme-Doktora

Bu koleksiyon için kalıcı URI

http://hdl.handle.net/11527/19308

Gözat

Yazar "Burnaz, Şebnem" ile LEE- İşletme-Doktora'a göz atma
  • Öge
    Marketing campaign management using machine learning techniques: An uplift modeling approach
    (Graduate School, 2024-06-28) Sanisoğlu, Meltem ; Burnaz, Şebnem ; 403172012 ; Management
    In order to engage customers and increase sales, businesses in today's dynamic business environment devote a large amount of resources to a variety of marketing methods. Businesses utilize a variety of strategies to attract customers' attention and encourage them to make a purchase. However even with a wide range of marketing strategies and channels, a fundamental issue still remains: how can businesses effectively evaluate how their marketing campaigns influence consumer behavior? By focusing on the significance of uplift modeling in determining the true impact of marketing initiatives, this research directly addresses this issue. By identifying the incremental impact of marketing initiatives, uplift modeling provides a more sophisticated approach than common predictive analytics which only forecasts customer behavior. The purpose of this research is to explore the limitations of conventional predictive analytics in marketing, investigate the application of prescriptive analytics specifically uplift modeling and develop a framework for implementing uplift modeling in business-to-business (B2B) marketing instances by examining real-world data from the Turkish telecom industry. In this study, three uplift modeling methodologies (two model approach, class variable transformation and modeling uplift directly) performed on a real-world B2B marketing campaign dataset and shown that the marketing campaign can be optimized by predicting the incremental impact more precisely with uplift models than the conventional predictive models. The results revealed how uplift modeling, which enables for the targeting of customers whose behavior is most likely to be positively influenced by marketing efforts, is helpful in improving resource allocation. Out of all the uplift models, the model that used the class variable transformation approach was able to capture 46% of uplift while targeting only the half of the campaign audience. This finding confirms the earlier research in the uplift modeling literature and shows that uplift models are successful in forecasting the truly responsive customers for a direct marketing campaign. It has been demonstrated that conventional response models are inadequate to distinguish which customers are positively impacted by a marketing treatment whereas uplift models successfully identify which customers will make a purchase due to being influenced by the marketing treatment. It is also shown that in a direct marketing campaign, focusing on a larger target audience may not always yield the greatest or most effective outcomes. Instead, different uplift modeling strategies combined with machine learning algorithms can yield higher uplifts.This study makes significant contribution as being the first to introduce uplift modeling in Turkish literature and being one of the few studies to apply uplift modeling in B2B context in the world-wide academic literature that predominantly focused on researches in B2C. Further, it provides valuable managerial insights for marketers to gain deeper customer insights and foster stronger relationships with customers by leveraging uplift modeling.
  • Öge
    The impact of aggregate ratings and individual reviews on consumer decision-making: A construal level theory perspective
    (Graduate School, 2023-06-07) Çeşmeci, Caner ; Burnaz, Şebnem ; 403172011 ; Management
    In certain cases, despite a product's high overall rating, a single negative review has the potential to undermine and alter a consumer's otherwise favorable decision. Conversely, a single positive review can prompt consumers to adopt a positive attitude towards a product or service, even if the product has a low aggregate rating. This phenomenon illustrates a type of cognitive bias known as base-rate neglect, in which consumers in an online review setting may disregard average product ratings in favor of individual reviews. When faced with conflicting cues, consumers attempt to infer which cue types are more diagnostic for their decisions. To this end, the present thesis examines how consumers use aggregate review metrics (ARM) (e.g., average product ratings) and individual reviews (IR) (e.g., a single review text) to estimate the risk likelihood of and make an evaluation of a product. Drawing on construal level theory (CLT) as a theoretical foundation, the study posits that psychologically distant objects are represented as abstract categories, while psychologically close objects are represented as concrete and contextual. In this framework, conceptualizing eWOM as a communication model in light of numerous contextual factors, the thesis addresses cue types as part of a broader inquiry into the influence of base-rate information (abstract, aggregated, and category-level characteristics within a population) and case information (concrete, individuating, and case-specific instances) on risk assessment and product evaluation. By unpacking base-rate neglect in the eWOM context, this study aims to highlight mental construal as a novel moderator that determines the prominence of specific cues under certain conditions. Additionally, it identifies consumers' risk estimation as an underlying mechanism in the pathway of behavioral outcomes and also a crucial boundary condition, demonstrating that nudging base-rate cues by providing a simple reminder of the base-rate fallacy can significantly eliminate this bias in consumer decision-making. This thesis consists of eight studies, including six experiments, a survey, and a qualitative study, all of which utilize various stimuli, measures of evaluation (such as persuasion, self-report intention to adopt cue types, willingness to pay, real choice, and behavioral intention), and methods (including a survey, in-depth interviews, lab, and online experiments), as well as diverse sample populations (such as students and frequent online shoppers with different demographic characteristics), and cultural context (with the participation of individuals from the US and Turkey). Throughout the thesis, all experimental studies are designed with the presence of conflicting cues (individual favored cue [AFC] vs. aggregate favored cue [IFC]).
  • Öge
    The impact of framing on donation behavior
    (Lisansüstü Eğitim Enstitüsü, 2021) Demirel, Sibel ; Burnaz, Şebnem ; 689625 ; İşletme
    Nonprofit organizations were not used to focus on marketing but as time passed, rising competition has forced these organizations to introduce marketing to achieve the organizations' objectives. Donor and donation related factors affecting donation behavior is extensively studied by previous research. The focal point of this study is how the nonprofit organization should frame its donation request as a tool for communication. This study offers an analysis of nonprofit organization's framing of the donation request by conducting two experimental studies in which donation type is manipulated to analyse its effects on donation behavior. It further analyses what impact framing may have on mindset and how this relation is influenced by the donors' religious orientation. Study 1 establishes effects by manipulating donation type (monetary vs. nonmonetary) and observes how this relation is influenced by the donors' religious orientation (intrinsic vs extrinsic) and how it affects donation behavior. Study 2 attempts to investigate what impact donation type manipulation (monetary vs. nonmonetary) may have on mindset (rational vs. emotional) and thus on both religious orientation groups' donation behavior. Findings of the Study 1 supported that intrinsically religious donors are more likely to donate compared to extrinsically religious donors when they receive nonmonetary donation requests. However, regarding monetary donation requests there is no significant difference between intrinsic and extrinsic religious groups. Study 2 suppported the same argument but added some new insight. The second study was designed to measure situation specific thinking styles when the respondents face a monetary and a nonmonetary donation request. Monetary offer triggers rational mindset significantly higher than the nonmonetary offer and nonmonetary offer triggers emotional mindset significantly higher than the monetary offer. In monetary group, respondents with extrinsic religious orientation have significantly higher rational mindset than intrinsic. However, intrinsicly religious people become more rational when they face a monetary donation request compared to nonmonetary. Therefore, we can conclude that a monetary donation request makes both religious orientation groups think rational and avoid donation.