We present a method for learning a low-dimensional representation which is shared across a set of multiple related tasks. The method builds upon the wellknown 1-norm regularization problem using a new regularizer which controls the number of learned features common for all the tasks. We show that this problem is equivalent to a convex optimization problem and develop an iterative algorithm for solving it. The algorithm has a simple interpretation: it alternately performs a supervised and an unsupervised step, where in the latter step we learn commonacross-tasks representations and in the former step we learn task-specific functions using these representations. We report experiments on a simulated and a real data set which demonstrate that the proposed method dramatically improves the performance relative to learning each task independently. Our algorithm can also be used, as a special case, to simply select – not learn – a few common features across the tasks.

Summary. We present a method for learning sparse representations shared across multiple tasks. This method is a generalization of the well-known singletask 1-norm regularization. It is based on a novel non-convex regularizer which controls the number of learned features common across the tasks. We prove that the method is equivalent to solving a convex optimization problem for which there is an iterative algorithm which converges to an optimal solution. The algorithm has a simple interpretation: it alternately performs a supervised and an unsupervised step, where in the former step it learns task-specific functions and in the latter step it learns common-across-tasks sparse representations for these functions. We also provide an extension of the algorithm which learns sparse nonlinear representations using kernels. We report experiments on simulated and real data sets which demonstrate that the proposed method can both improve the performance relative to learning each task independently and lead to a few learned features common across related tasks. Our algorithm can also be used, as a special case, to simply select – not learn – a few common variables across the tasks 3.

Conjoint analysis is marketers’ favorite methodology for finding out how buyers make trade-offs among competing products and suppliers. Conjoint analysts develop and present descriptions of alternative products or services that are prepared from fractional factorial, experimental designs. They use various models to infer buyers’ partworths for attribute levels. and enter the partworths into buyer choice simulators to predict how buyers will choose among products and services. Easy-to-use software has been important for applying these models. Thousands of applications of conjoint analysis have been carried out over the past three decades.

Abstract not found

In Web-based services of dynamic content (such as news articles), recommender systems face the difficulty of timely identifying new items of high-quality and providing recommendations for new users. We propose a feature-based machine learning approach to personalized recommendation that is capable of handling the cold-start issue effectively. We maintain profiles of content of interest, in which temporal characteristics of the content, e.g. popularity and freshness, are updated in real-time manner. We also maintain profiles of users including demographic information and a summary of user activities within Yahoo! properties. Based on all features in user and content profiles, we develop predictive bilinear regression models to provide accurate personalized recommendations of new items for both existing and new users. This approach results in an offline model with light computational overhead compared with other recommender systems that require online re-training. The proposed framework is general and flexible for other personalized tasks. The superior performance of our approach is verified on a large-scale data set collected from the Today-Module on Yahoo! Front Page, with comparison against six competitive approaches.

Summary. Given multiple prediction problems such as regression and classification, we are interested in a joint inference framework which can effectively borrow information among tasks to improve the prediction accuracy, especially when the number of training examples per problem is small. In this paper we propose a probabilistic framework which can support a set of latent variable models for different multi-task learning scenarios. We show that the framework is a generalization of standard learning methods for single prediction problems and it can effectively model the shared structure among different prediction tasks. Furthermore, we present efficient algorithms for the empirical Bayes method as well as point estimation. Our experiments on both simulated datasets and real world classification datasets show the effectiveness of the proposed models in two evaluation settings: standard multi-task learning setting and transfer learning setting. Key words: multi-task learning, latent variable models, hierarchical Bayesian models, model selection, transfer learning 1

: An exciting development in modeling has been the ability to estimate reliable individual-level parameters for choice models. Individual partworths derived from these parameters have been very useful in segmentation, identifying extreme individuals, and in creating appropriate choice simulators. In marketing, hierarchical Bayes models have taken the lead in combining information about the aggregate distribution of tastes with the individual's choices to arrive at a conditional estimate of the individual's parameters. In economics, the same behavioral model has been derived from a classical rather than a Bayesian perspective. That is, instead of Gibbs sampling, the method of maximum simulated likelihood provides estimates of both the aggregate and the individual parameters. This paper explores the similarities and differences between classical and Bayesian methods and shows that they result in virtually equivalent conditional estimates of partworths for customers. Thus, the choice betw...

Knowledge about a product’s willingness-to-pay on behalf of its (potential) customers plays a crucial role in many areas of marketing management like pricing decisions or new product development. Numerous approaches to measure willingness-to-pay with differential conceptual foundations and methodological implications have been presented in the relevant literature so far. This article provides the reader with a systematic overview of the relevant literature on these competing approaches and associated schools of thought, recognizes their respective merits and discusses obstacles and issues regarding their adoption to measuring willingness-to-pay. Because of its practical relevance, special focus will be put on indirect surveying techniques and, in particular, conjoint-based applications will be discussed in more detail. The strengths and limitations of the individual approaches are discussed and evaluated from a managerial point of view. Keywords: Willingness-to-pay, pricing, surveying techniques, conjoint measurement.

Conjoint analysis is one of the most important tools to support product development, pricing and positioning decisions in management practice. For this purpose various models have been developed. It is widely accepted that models that take consumer heterogeneity into account, outperform aggregate models in terms of hold-out tasks. The aim of our study is to investigate empirically whether predictions of choice-based conjoint models which incorporate heterogeneity can successfully be generalized to a whole market. To date no studies exist that examine the real world performance of choice-based conjoint models by use of aggregate scanner panel data. Our analysis is based on four commercial choice-based conjoint pricing studies including a total of 43 stock keeping units (SKU) and the corresponding weekly scanning data for approximately two years. An aggregate model serves as a benchmark for the performance of two models that take heterogeneity into account, hierarchical Bayes and latent class. Our empirical analysis demonstrates that, in contrast to the performance using hold-out tasks, the real world performance of hierarchical Bayes and latent class is similar to the performance of the aggregate model. Our results indicate that heterogeneity cannot be generalized to a whole market and suggest that aggregate models are sufficient to predict market shares. Keywords: Pricing Research, Choice Based Conjoint Analysis, Hierarchical Bayes, Latent Class, Heterogeneity 1

Abstract not found