Optimal pricing in e-commerce based on sparse and noisy data
01 Feb 2018-Vol. 106, pp 53-63
TL;DR: A novel machine-learning based framework based on Bayesian inference combined with bootstrap-based confidence estimation and kernel regression for estimating optimal prices under dynamic pricing constraints is proposed.
Abstract: In today's transparent markets, e-commerce providers often have to adjust their prices within short time intervals, e.g., to take frequently changing prices of competitors into account. Automating this task of determining an “optimal” price (e.g., in terms of profit or revenue) with a learning-based approach can however be challenging. Often, only few data points are available, making it difficult to reliably detect the relationships between a given price and the resulting revenue or profit. In this paper, we propose a novel machine-learning based framework for estimating optimal prices under such constraints. The framework is generic in terms of the optimality criterion and can be customized in different ways. At its core, it implements a novel algorithm based on Bayesian inference combined with bootstrap-based confidence estimation and kernel regression. Simulation experiments show that our method is favorable over existing dynamic pricing strategies. Furthermore, the method led to a significant increase in profit and revenue in a real-world evaluation.
Citations
More filters
TL;DR: A three-stage framework for strategic marketing planning, incorporating multiple artificial intelligence (AI) benefits: mechanical AI for automating repetitive marketing functions and activities, thinking AI for processing data to arrive at decisions, and feeling AI for analyzing interactions and human emotions is developed.
Abstract: The authors develop a three-stage framework for strategic marketing planning, incorporating multiple artificial intelligence (AI) benefits: mechanical AI for automating repetitive marketing functions and activities, thinking AI for processing data to arrive at decisions, and feeling AI for analyzing interactions and human emotions. This framework lays out the ways that AI can be used for marketing research, strategy (segmentation, targeting, and positioning, STP), and actions. At the marketing research stage, mechanical AI can be used for data collection, thinking AI for market analysis, and feeling AI for customer understanding. At the marketing strategy (STP) stage, mechanical AI can be used for segmentation (segment recognition), thinking AI for targeting (segment recommendation), and feeling AI for positioning (segment resonance). At the marketing action stage, mechanical AI can be used for standardization, thinking AI for personalization, and feeling AI for relationalization. We apply this framework to various areas of marketing, organized by marketing 4Ps/4Cs, to illustrate the strategic use of AI.
254 citations
Cites background from "Optimal pricing in e-commerce based..."
...Bauer and Jannach (2018) show that a machine-learning framework based on Bayesian inference can optimize online pricing even when data are updated frequently, and are sparse and noisy....
[...]
...It is achieved by bringing together diverse AI literatures on algorithms (e.g., Bauer and Jannach 2018; Davis and Marcus 2015), psychology (e.g., Lee et al. 2018; Leung et al. 2018), societal effects (e.g., Autor and Dorn 2013; Frey and Osborne 2017), and managerial implications (e.g., Huang et al.…...
[...]
...…prices with incomplete price information (Misra et al. 2019) • Machine learning based on Bayesian inference optimize online pricing with sparse and noisy data (Bauer and Jannach 2018) • Consumers’ private information for price personalization (Montes et al. 2019) • Interpersonal likeability would…...
[...]
28 Jan 2021
TL;DR: A comprehensive review of AI in marketing is offered using bibliometric, conceptual and intellectual network analysis of extant literature published between 1982 and 2020 to identify the scientific actors' performance like most relevant authors and most relevant sources.
Abstract: Disruptive technologies such as the internet of things, big data analytics, blockchain, and artificial intelligence have changed the ways businesses operate. Of all the disruptive technologies, artificial intelligence (AI) is the latest technological disruptor and holds immense marketing transformation potential. Practitioners worldwide are trying to figure out the best fit AI solutions for their marketing functions. However, a systematic literature review can highlight the importance of artificial intelligence (AI) in marketing and chart future research directions. The present study aims to offer a comprehensive review of AI in marketing using bibliometric, conceptual and intellectual network analysis of extant literature published between 1982 and 2020. A comprehensive review of one thousand five hundred and eighty papers helped to identify the scientific actors' performance like most relevant authors and most relevant sources. Furthermore, co-citation and co-occurrence analysis offered the conceptual and intellectual network. Data clustering using the Louvain algorithm helped identify research sub-themes and future research directions to expand AI in marketing.
143 citations
TL;DR: A market survey in Taiwan developing a data mining analytics including clustering analysis and association rules based on a snowflake schema database design is investigated, determining the role of mobile payment is determined in terms of new retail payment mechanism that promotes a better consumer purchase experience in an online to offline business environment.
37 citations
01 Nov 2020
TL;DR: In this paper, an in-depth review of 86 empirical studies at the firm level was conducted to uncover various reasons for the emergence of the Solow Paradox, debates its following reversal marked by the occurrence of excess returns and deduces a model of factors influencing the returns on IT investments.
Abstract: New developments in the fields of artificial intelligence or robotics are receiving considerable attention from businesses, as they promise astonishing gains in process efficiency—sparking a surge of corporate investments in new, digital technologies. Yet, firms did not become per se more productive, as labor productivity growth in various industrial nations has decelerated in recent years. The fact that the adoption of innovative technologies is not accompanied by productivity increases has already been observed during the dawn of the computer age and became known as Solow’s Paradox. Thus, this paper takes stock of what is known about the Solow Paradox, before incorporating the findings into the debate of the current productivity slowdown. Based on an in-depth review of 86 empirical studies at the firm level, this paper uncovers various reasons for the emergence of the Solow Paradox, debates its following reversal marked by the occurrence of excess returns and deduces a model of factors influencing the returns on IT investments. Based on these insights, four overarching explanations of the modern productivity paradox namely adjustment delays, measurement issues, exaggerated expectations and mismanagement are discussed, whereby mismanagement emerges as a currently neglected, but focal issue.
29 citations
TL;DR: In this article, a classification framework that connects the information system (IS) discipline to contemporary AI practices has been proposed, and 103 documents on AI published by 25 leading technology companies ranked in the 2019 list of Fortune 500 companies.
Abstract: The current evolution of artificial intelligence (AI) practices and applications is creating a disconnection between modern-day information system (IS) research and practices. The purpose of this study is to propose a classification framework that connects the IS discipline to contemporary AI practices.,We conducted a review of practitioner literature to derive our framework's key dimensions. We reviewed 103 documents on AI published by 25 leading technology companies ranked in the 2019 list of Fortune 500 companies. After that, we reviewed and classified 110 information system (IS) publications on AI using our proposed framework to demonstrate its ability to classify IS research on AI and reveal relevant research gaps.,Practitioners have adopted different definitional perspectives of AI (field of study, concept, ability, system), explaining the differences in the development, implementation and expectations from AI experienced today. All these perspectives suggest that perception, comprehension, action and learning are the four capabilities AI artifacts must possess. However, leading IS journals have mostly published research adopting the “AI as an ability” perspective of AI with limited theoretical and empirical studies on AI adoption, use and impact.,First, the framework is based on the perceptions of AI by a limited number of companies, although it includes all the companies leading current AI practices. Secondly, the IS literature reviewed is limited to a handful of journals. Thus, the conclusions may not be generalizable. However, they remain true for the articles reviewed, and they all come from well-respected IS journals.,This is the first study to consider the practitioner's AI perspective in designing a conceptual framework for AI research classification. The proposed framework and research agenda are used to show how IS could become a reference discipline in contemporary AI research.
21 citations
References
More filters
TL;DR: Chapter 11 includes more case studies in other areas, ranging from manufacturing to marketing research, and a detailed comparison with other diagnostic tools, such as logistic regression and tree-based methods.
Abstract: Chapter 11 includes more case studies in other areas, ranging from manufacturing to marketing research. Chapter 12 concludes the book with some commentary about the scienti c contributions of MTS. The Taguchi method for design of experiment has generated considerable controversy in the statistical community over the past few decades. The MTS/MTGS method seems to lead another source of discussions on the methodology it advocates (Montgomery 2003). As pointed out by Woodall et al. (2003), the MTS/MTGS methods are considered ad hoc in the sense that they have not been developed using any underlying statistical theory. Because the “normal” and “abnormal” groups form the basis of the theory, some sampling restrictions are fundamental to the applications. First, it is essential that the “normal” sample be uniform, unbiased, and/or complete so that a reliable measurement scale is obtained. Second, the selection of “abnormal” samples is crucial to the success of dimensionality reduction when OAs are used. For example, if each abnormal item is really unique in the medical example, then it is unclear how the statistical distance MD can be guaranteed to give a consistent diagnosis measure of severity on a continuous scale when the larger-the-better type S/N ratio is used. Multivariate diagnosis is not new to Technometrics readers and is now becoming increasingly more popular in statistical analysis and data mining for knowledge discovery. As a promising alternative that assumes no underlying data model, The Mahalanobis–Taguchi Strategy does not provide suf cient evidence of gains achieved by using the proposed method over existing tools. Readers may be very interested in a detailed comparison with other diagnostic tools, such as logistic regression and tree-based methods. Overall, although the idea of MTS/MTGS is intriguing, this book would be more valuable had it been written in a rigorous fashion as a technical reference. There is some lack of precision even in several mathematical notations. Perhaps a follow-up with additional theoretical justi cation and careful case studies would answer some of the lingering questions.
11,507 citations
Book•
01 Jan 1999TL;DR: This new edition contains five completely new chapters covering new developments and has sold 4300 copies worldwide of the first edition (1999).
Abstract: We have sold 4300 copies worldwide of the first edition (1999). This new edition contains five completely new chapters covering new developments.
6,884 citations
"Optimal pricing in e-commerce based..." refers methods in this paper
...For this purpose, we use a tailored variant of the basic Metropolis-Hastings Algorithm [33]....
[...]
Book•
01 Jan 1992
TL;DR: In this paper, the authors present a non-Edgeworth view of the Bootstrap and propose a method of importance sampling for estimating bias, variance, and skewness.
Abstract: 1: Principles of Bootstrap Methodology.- 2: Principles of Edgeworth Expansion.- 3: An Edgeworth View of the Bootstrap.- 4: Bootstrap Curve Estimation.- 5: Details of Mathematical Rigour.- Appendix I: Number and Sizes of Atoms of Nonparametric Bootstrap Distribution.- Appendix II: Monte Carlo Simulation.- II.1 Introduction.- II.2 Uniform Resampling.- II.3 Linear Approximation.- II.4 Centring Method.- II.5 Balanced Resampling.- II.6 Antithetic Resampling.- II.7 Importance Resampling.- II.7.1 Introduction.- II.7.2 Concept of Importance Resampling.- II.7.3 Importance Resampling for Approximating Bias, Variance, Skewness, etc..- II.7.4 Importance Resampling for a Distribution Function.- II.8 Quantile Estimation.- Appendix III: Confidence Pictures.- Appendix IV: A Non-Standard Example: Quantite Error Estimation.- IV. 1 Introduction.- IV.2 Definition of the Mean Squared Error Estimate.- IV.3 Convergence Rate of the Mean Squared Error Estimate.- IV.4 Edgeworth Expansions for the Studentized Bootstrap Quantile Estimate.- Appendix V: A Non-Edgeworth View of the Bootstrap.- References.- Author Index.
2,306 citations
Journal Article•
TL;DR: A brief introduction to the historical origins of quantitative research on pricing and demand estimation is provided, point to different subfields in the area of dynamic pricing, and an in-depth overview of the available literature on dynamic pricing and learning is provided.
Abstract: The topic of dynamic pricing and learning has received a considerable amount of attention in recent years, from different scientific communities. We survey these literature streams: we provide a brief introduction to the historical origins of quantitative research on pricing and demand estimation, point to different subfields in the area of dynamic pricing, and provide an in-depth overview of the available literature on dynamic pricing and learning. Our focus is on the operations research and management science literature, but we also discuss relevant contributions from marketing, economics, econometrics, and computer science. We discuss relations with methodologically related research areas, and identify directions for future research.
293 citations
Additional excerpts
...Generally, we further refer to [28] and [29] for an overview of pricing methods in the literature....
[...]