No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
The Prediction Lover's Handbook
Abstract
When picking assessment tools to inform better decisions about future paths, executives are faced with a wide variety of options - some of which are well established, while others are in early stages of development. The authors provide an insider's guide to prediction and recommendation techniques and technologies. They cover prediction tools including attributized Bayesian analysis, biological responses analysis, cluster analysis, collaborative filtering, content-based filtering/decision trees, neural network analysis, prediction (or opinion) markets, regression analysis, social network-based recommendations and textual analytics. With each potential tool, they briefly describe the technique, who uses it and for what purpose, its strengths and weaknesses, and its future prospects as a prediction tool. Finally, the authors offer up an indication of the best time in the decision process to begin using the tool. Copyright © Massachusetts Institute of Technology, 2009. All rights reserved.
... In particular, Amazon was one of the pioneers in the use of collaborative filtering in the late 1990s. 21 Collaborative filtering consists in creating patterns of consumption to give shopping recommendations. However, the method has many limitations: it cannot determine if the product was bought for the consumer's personal use or for someone else, and it does not allow to confidently predict the products consumers will buy next and the reasons they like this product. ...
... However, the method has many limitations: it cannot determine if the product was bought for the consumer's personal use or for someone else, and it does not allow to confidently predict the products consumers will buy next and the reasons they like this product. Surveys are often used in collaboration with social networks 21,22 to identify the degree of acceptation or satisfaction. For example, after buying a product on Amazon, customers usually receive an e-mail asking to grade the product and give a review. ...
A new collaborative consumer-centric decision-making platform to support the design of innovative products is presented and applied to in-flight entertainment systems. Based on a six-step methodology, it allows designers to dynamically and exhaustively decompose their problem and generate all feasible concepts. Automatically removing unfeasible concepts decreases the overall execution time by a factor of 103, while maintaining consistency and exhaustiveness. An automatically generated survey is combined with a quantitative multiple-objective option evaluation. This supports decision-making via rapid trade-off visualization and systematic rankings based on requirement prioritization. Finally, a robustness analysis allows designers to take into account requirements’ uncertainty.
Experts share their views on the growing importance of business analytics and big data for modern business organizations. Information processing has become increasingly more powerful and flexible, with faster and higher-capacity storage and networks. Globalization and other competitive factors have exerted strong pressures to improve efficiencies and effectiveness, and to strengthen business and customer relationships. Each successive stage of this competition requires more data and more analysis to support strategic, managerial, and operational decision-making. This competition is driving the need for more and better analytics technology, which helps to make competition even more intense. This cycle results in a confluence of competitive imperatives and technological advancements that interact in a unique way.
ResearchGate has not been able to resolve any references for this publication.