Customer Choice Models Versus Machine Learning PDF Download
Are you looking for read ebook online? Search for your book and save it on your Kindle device, PC, phones or tablets. Download Customer Choice Models Versus Machine Learning PDF full book. Access full book title Customer Choice Models Versus Machine Learning by Jacob Feldman. Download full books in PDF and EPUB format.
Author: Jacob Feldman
Publisher:
ISBN:
Category :
Languages : en
Pages : 50
Get Book Here
Book Description
We compare the performance of two approaches for finding the optimal set of products to display to customers landing on Alibaba's two online marketplaces, Tmall and Taobao. Both approaches were placed online simultaneously and tested on real customers for one week. The first approach we test is Alibaba's current practice. This procedure embeds thousands of product and customer features within a sophisticated machine learning algorithm that is used to estimate the purchase probabilities of each product for the customer at hand. The products with the largest expected revenue (revenue * predicted purchase probability) are then made available for purchase. The downside of this approach is that it does not incorporate customer substitution patterns; the estimates of the purchase probabilities are independent of the set of products that eventually are displayed. Our second approach uses a featurized multinomial logit (MNL) model to predict purchase probabilities for each arriving customer. In this way we use less sophisticated machinery to estimate purchase probabilities, but we employ a model that was built to capture customer purchasing behavior and, more specifically, substitution patterns. We use historical sales data to fit the MNL model and then, for each arriving customer, we solve the cardinality-constrained assortment optimization problem under the MNL model online to find the optimal set of products to display. Our experiments show that despite the lower prediction power of our MNL-based approach, it generates significantly higher revenue per visit compared to the current machine learning algorithm with the same set of features. We also conduct various heterogeneous-treatment-effect analyses to demonstrate that the current MNL approach performs best for sellers whose customers generally only make a single purchase.
Author: Jacob Feldman
Publisher:
ISBN:
Category :
Languages : en
Pages : 50
Get Book Here
Book Description
We compare the performance of two approaches for finding the optimal set of products to display to customers landing on Alibaba's two online marketplaces, Tmall and Taobao. Both approaches were placed online simultaneously and tested on real customers for one week. The first approach we test is Alibaba's current practice. This procedure embeds thousands of product and customer features within a sophisticated machine learning algorithm that is used to estimate the purchase probabilities of each product for the customer at hand. The products with the largest expected revenue (revenue * predicted purchase probability) are then made available for purchase. The downside of this approach is that it does not incorporate customer substitution patterns; the estimates of the purchase probabilities are independent of the set of products that eventually are displayed. Our second approach uses a featurized multinomial logit (MNL) model to predict purchase probabilities for each arriving customer. In this way we use less sophisticated machinery to estimate purchase probabilities, but we employ a model that was built to capture customer purchasing behavior and, more specifically, substitution patterns. We use historical sales data to fit the MNL model and then, for each arriving customer, we solve the cardinality-constrained assortment optimization problem under the MNL model online to find the optimal set of products to display. Our experiments show that despite the lower prediction power of our MNL-based approach, it generates significantly higher revenue per visit compared to the current machine learning algorithm with the same set of features. We also conduct various heterogeneous-treatment-effect analyses to demonstrate that the current MNL approach performs best for sellers whose customers generally only make a single purchase.
Author: Steven Struhl
Publisher: Kogan Page Publishers
ISBN: 0749479566
Category : Business & Economics
Languages : en
Pages : 273
Get Book Here
Book Description
The ability to predict consumer choice is a fundamental aspect to success for any business. In the context of artificial intelligence marketing, there are a wide array of predictive analytic techniques available to achieve this purpose, each with its own unique advantages and disadvantages. Artificial Intelligence Marketing and Predicting Consumer Choice serves to integrate these widely disparate approaches, and show the strengths, weaknesses, and best applications of each. It provides a bridge between the person who must apply or learn these problem-solving methods and the community of experts who do the actual analysis. It is also a practical and accessible guide to the many remarkable advances that have been recently made in this fascinating field. Online resources: bonus chapters on AI, ensembles and neural nets, and finishing experiments, plus single and multiple product simulators.
Author: Zhenkang Peng
Publisher:
ISBN:
Category :
Languages : en
Pages : 0
Get Book Here
Book Description
In revenue management, the customer discrete choice model is essential to describe customer purchase behavior. The multinomial logit (MNL) model is a classical random utility-based choice model that assumes that the consumer can purchase only one product from a set of substitute products. The revenue maximization problem of choosing the assortment under the MNL model must balance the cannibalization effect and nonpurchase probability. On the other hand, a large number of recommendation algorithms used in e-commerce, such as the DeepFM model with high prediction accuracy, tend to ignore the substitution effect among products. In this paper, we investigate whether and how better prediction accuracy transforms into better decisions for assortment planning. To answer this question, we compare MNL, DeepFM and a variant of DeepFM with the assortment information, called DeepFM-a. Instead utilizing the costly field experiment, we first use a real dataset of a flight browsing log and transaction records to train a machine learning model called Transformer, which has better prediction accuracy than MNL, DeepFM and DeepFM-a. Then, we utilize the trained Transformer model as a simulator to generate a synthetic dataset for consumer browsing and purchasing behavior. After training the MNL, DeepFM and DeepFM-a models, assortment decisions are given for simulated product pools with the three models. Then, the simulator is used to evaluate the revenue for each assortment from different choice models. Such a procedure utilizing the simulator can lessen the issue of validating decision models that change the observed data in the real world. Our findings are that a choice model with better prediction power may not yield higher revenue. When the outside option is less attractive, the MNL model provides comparable prediction power with much higher revenue. Fewer training data points reduce both prediction power and revenue for all three choice models. However, fewer features reduced the prediction power for all three choice models, but the assortment decision prescribed by DeepFM could increase the revenue.
Author: Kenneth Train
Publisher: Cambridge University Press
ISBN: 0521766559
Category : Business & Economics
Languages : en
Pages : 399
Get Book Here
Book Description
This book describes the new generation of discrete choice methods, focusing on the many advances that are made possible by simulation. Researchers use these statistical methods to examine the choices that consumers, households, firms, and other agents make. Each of the major models is covered: logit, generalized extreme value, or GEV (including nested and cross-nested logits), probit, and mixed logit, plus a variety of specifications that build on these basics. Simulation-assisted estimation procedures are investigated and compared, including maximum stimulated likelihood, method of simulated moments, and method of simulated scores. Procedures for drawing from densities are described, including variance reduction techniques such as anithetics and Halton draws. Recent advances in Bayesian procedures are explored, including the use of the Metropolis-Hastings algorithm and its variant Gibbs sampling. The second edition adds chapters on endogeneity and expectation-maximization (EM) algorithms. No other book incorporates all these fields, which have arisen in the past 25 years. The procedures are applicable in many fields, including energy, transportation, environmental studies, health, labor, and marketing.
Author: Christopher Gan
Publisher:
ISBN: 9781877176814
Category : Banks and banking
Languages : en
Pages : 19
Get Book Here
Book Description
Author: Robert W. Palmatier
Publisher: Bloomsbury Publishing
ISBN: 1350305286
Category : Business & Economics
Languages : en
Pages : 414
Get Book Here
Book Description
Marketing Strategy offers a unique and dynamic approach based on four underlying principles that underpin marketing today: All customers differ; All customers change; All competitors react; and All resources are limited. The structured framework of this acclaimed textbook allows marketers to develop effective and flexible strategies to deal with diverse marketing problems under varying circumstances. Uniquely integrating marketing analytics and data driven techniques with fundamental strategic pillars the book exemplifies a contemporary, evidence-based approach. This base toolkit will support students' decision-making processes and equip them for a world driven by big data. The second edition builds on the first's successful core foundation, with additional pedagogy and key updates. Research-based, action-oriented, and authored by world-leading experts, Marketing Strategy is the ideal resource for advanced undergraduate, MBA, and EMBA students of marketing, and executives looking to bring a more systematic approach to corporate marketing strategies. New to this Edition: - Revised and updated throughout to reflect new research and industry developments, including expanded coverage of digital marketing, influencer marketing and social media strategies - Enhanced pedagogy including new Worked Examples of Data Analytics Techniques and unsolved Analytics Driven Case Exercises, to offer students hands-on practice of data manipulation as well as classroom activities to stimulate peer-to-peer discussion - Expanded range of examples to cover over 250 diverse companies from 25 countries and most industry segments - Vibrant visual presentation with a new full colour design
Author: Christoph Molnar
Publisher: Lulu.com
ISBN: 0244768528
Category : Artificial intelligence
Languages : en
Pages : 320
Get Book Here
Book Description
This book is about making machine learning models and their decisions interpretable. After exploring the concepts of interpretability, you will learn about simple, interpretable models such as decision trees, decision rules and linear regression. Later chapters focus on general model-agnostic methods for interpreting black box models like feature importance and accumulated local effects and explaining individual predictions with Shapley values and LIME. All interpretation methods are explained in depth and discussed critically. How do they work under the hood? What are their strengths and weaknesses? How can their outputs be interpreted? This book will enable you to select and correctly apply the interpretation method that is most suitable for your machine learning project.
Author: Parag Kulkarni
Publisher: Springer Nature
ISBN: 9811940592
Category : Technology & Engineering
Languages : en
Pages : 254
Get Book Here
Book Description
This book presents thoughts and pathways to build revolutionary machine learning models with the new paradigm of machine learning to adapt behaviorism. It focuses on two aspects – one focuses on architecting a choice process to lead users on the certain choice path while the second focuses on developing machine learning models based on choice paradigm. This book is divided in three parts where part one deals with human choice and choice architecting models with stories of choice architects. Second part closely studies human choosing models and deliberates on developing machine learning models based on the human choice paradigm. Third part takes you further to look at machine learning based choice architecture. The proposed pioneering choice-based paradigm for machine learning presented in the book will help readers to develop products – help readers to solve problems in a more humanish way and to negotiate with uncertainty in a more graceful but in an objective way. It will help to create unprecedented value for business and society. Further, it will unveil a new paradigm for modern intelligent businesses to embark on the new journey; the journey of transition from shackled feature rich and choice poor systems to feature flexible and choice rich natural behaviors.
Author: Volodymyr Babich
Publisher: Springer Nature
ISBN: 3030757293
Category : Business & Economics
Languages : en
Pages : 304
Get Book Here
Book Description
This book examines the challenges and opportunities arising from an assortment of technologies as they relate to Operations Management and Finance. The book contains primers on operations, finance, and their interface. After that, each section contains chapters in the categories of theory, applications, case studies, and teaching resources. These technologies and business models include Big Data and Analytics, Artificial Intelligence, Machine Learning, Blockchain, IoT, 3D printing, sharing platforms, crowdfunding, and crowdsourcing. The balance between theory, applications, and teaching materials make this book an interesting read for academics and practitioners in operations and finance who are curious about the role of new technologies. The book is an attractive choice for PhD-level courses and for self-study.
Author: Stephane Hess
Publisher: Edward Elgar Publishing
ISBN: 1781003157
Category : Business & Economics
Languages : en
Pages : 721
Get Book Here
Book Description
The Handbook of Choice Modelling, composed of contributions from senior figures in the field, summarizes the essential analytical techniques and discusses the key current research issues. The book opens with Nobel Laureate Daniel McFadden calling for d
