Search results1 – 3 of 3
The purpose of this paper is to estimate individual promotional campaign impacts through Bayesian inference. Conventional statistics have worked well for analyzing the…
The purpose of this paper is to estimate individual promotional campaign impacts through Bayesian inference. Conventional statistics have worked well for analyzing the impact of direct marketing promotions on purchase behavior. However, many modern marketing programs must drive multiple purchase objectives, requiring more precise arbitration between multiple offers and collection of more data with which to differentiate individuals. This often results in datasets that are highly dimensional, yet also sparse, straining the power of statistical methods to properly estimate the effect of promotional treatments.
Improvements in computing power have enabled new techniques for predicting individual behavior. This work investigates a probabilistic machine-learned Bayesian approach to predict individual impacts driven by promotional campaign offers for a leading global travel and hospitality chain. Comparisons were made to a linear regression, representative of the current state of practice.
The findings of this work focus on comparing a machine-learned Bayesian approach with linear regression (which is representative of the current state of practice among industry practitioners) in the analysis of a promotional campaign across three key areas: highly dimensional data, sparse data and likelihood matching.
Because the findings are based on a single campaign, future work includes generalizing results across multiple promotional campaigns. Also of interest for future work are comparisons of the technique developed here with other techniques from academia.
Because the Bayesian approach allows estimation of the influence of the promotion for each hypothetical customer’s set of promotional attributes, even when no exact look-alikes exist in the control group, a number of possible applications exist. These include optimal campaign design (given the ability to estimate the promotional attributes that are likely to drive the greatest incremental spend in a hypothetical deployment) and operationalizing efficient audience selection given the model’s individualized estimates, reducing the risk of marketing overcommunication, which can prompt costly unsubscriptions.
The original contribution is the application of machine-learning to Bayesian Belief Network construction in the context of analyzing a multi-channel promotional campaign’s impact on individual customers. This is of value to practitioners seeking alternatives for campaign analysis for applications in which more commonly used models are not well-suited, such as the three key areas that this paper highlights: highly dimensional data, sparse data and likelihood matching.
A new business model online to offline (O2O) has emerged in recent years. Similar to many new models at an early stage, O2O has inconsistent definitions which not only…
A new business model online to offline (O2O) has emerged in recent years. Similar to many new models at an early stage, O2O has inconsistent definitions which not only inhibit its adoption but also poorly differentiate O2O from other existing business models. To resolve the two issues, the authors propose an approach of definition development.
To show the usefulness of the approach, the authors demonstrate the differences among O2O and other business models with the use of the distinctive definition and thereby evaluate adoption of O2O from a practical perspective and identify research directions from a theoretical perspective based on the differences.
The authors' proposed approach of definition development integrates the work of Tatarkiewicz (1980) and Nickerson et al. (2013). The approach generates a distinctive definition of O2O with important analytical dimensions which help decision-making of adoption of O2O.
The paper aims to make several contributions. First, on theoretical contribution, the authors confine the scope of O2O studies and facilitate accumulation of more coherent knowledge of O2O. The authors help O2O evolve from a “buzz word” of successful stories in real businesses to a more serious concept from an academic perspective. Second, from a practical perspective, the authors' definition provides business executives with critical evaluative dimensions for gauging the adoption of O2O. Lastly, from a methodological perspective, the proposed approach can be used in future to define an emerging concept in real life businesses.
The purpose of this paper is to review and integrate the extensive literature base which examines judgment and decision‐making biases, to introduce this literature to the…
The purpose of this paper is to review and integrate the extensive literature base which examines judgment and decision‐making biases, to introduce this literature to the field of supply management, to create a valid, mutually exclusive, and exhaustive taxonomy of decision biases that can affect supply managers, and to provide guidance for future research and applications of this taxonomy.
The authors use a qualitative cluster analysis, combined with a Q‐sort methodology, to develop a taxonomy of decision biases.
A mutually exclusive, and exhaustive taxonomy of nine decision biases is developed through a qualitative cluster analysis. The Q‐sort methodology provides initial confirmation of the reliability and validity of the cluster analysis results. The findings, along with numerous examples provided in the text, suggest that supply management decisions are vulnerable to the described biases.
This paper provides a comprehensive review of the judgment and decision bias literature, and creates a logical and manageable taxonomy of biases which can impact supply management decision making. The introduction and organization of this vast extant literature base provides a contrasting perspective to much of the existing supply management research, which has incorporated the assumption of the rational agent, or what is known in the economics literature as homo economicus. In addition, the authors describe the use of qualitative cluster analysis and the Q‐sort methodology, techniques which have been used rarely if at all in within the field of supply chain management.