Angela has been a PCMag reporter since January 2012. Prior to joining the team, she worked as a reporter for SC Magazine, covering everything related to hackers and computer security. Angela has also written for The Northern Valley Suburbanite in New Jersey, The Dominion Post in West Virginia, and the Uniontown-Herald Standard in Pennsylvania. She is a graduate of West Virginia University's Perely Isaac Reed School of Journalism.

This straightforward order to display pictures of delicious fried confections, spoken into a Google Pixel 2 smartphone with the Google Assistant, is the type of command that users have been executing in Alphabet Inc.'s GOOGL, 1.13% GOOG, 1.00% search engine for years. Behind the scenes, however, the response to this type of query now leverages an enormous amount of machine-learning technology that Google has spent years and billions of dollars developing, in hopes of being a leader in artificial intelligence. For that command to function, software produced by Alphabet-owned Google needed to deploy image content analysis systems, voice recognition and a host of other technologies that revolve around machine learning and AI, mostly pumped through high-tech data centers the company has built. It also decided to make the hardware that runs it, with an eye on pushing the abilities of its services to new places in 2018 and beyond. Since 2013, Alphabet has ramped up its infrastructure spending, pouring $57.36 billion into capital expenditures--roughly $10 billion a year.

If Alexa has replaced other popular web-based search engines in your household, you are not alone. In fact, I'm guessing many of today's children will grow up researching school papers via robots, rather than traditional computers. What is the business case for robot-based assistance? Turns out many companies have already found ways to use artificially intelligence (AI) to increase efficiency and accuracy in their daily workplaces in the form of robotic "personal assistants." I know what you're thinking: I want in on that action!

The chapters in this book examine the state of today's agent technology and point the way toward the exciting developments of the next millennium. Contributors include Donald A. Norman, Nicholas Negroponte, Brenda Laurel, Thomas Erickson, Ben Shneiderman, Thomas W. Malone, Pattie Maes, David C. Smith, Gene Ball, Guy A. Boy, Doug Riecken, Yoav Shoham, Tim Finin, Michael R. Genesereth, Craig A. Knoblock, Philip R. Cohen, Hector J. Levesque, and James E. White, among others. Held at San Francisco's W Hotel, the conference included work from researchers and practitioners who are developing novel user interface and interaction paradigms that incorporate advanced reasoning and modeling techniques. In the past few years, user interfaces have faced increasingly challenging tasks, larger numbers of users with a wide range of computer skills, and the widespread use of new platforms such as mobile devices. These trends have led to a need for advanced techniques for communication and collaboration, personalization and adaptation of behavior, agent-based assistance, integrated multimodal interfaces, and a variety of intelligent front ends for complex environments and tasks.

As such systems must crucially rely on an accurate and complete model of user preferences, the acquisition of this model becomes the central subject of this article. Many tools used today do not satisfactorily assist users to establish this model because they do not adequately focus on fundamental decision objectives, help them reveal hidden preferences, revise conflicting preferences, or explicitly reason about tradeoffs. As a result, users fail to find the outcomes that best satisfy their needs and preferences. In this article, we provide some analyses of common areas of design pitfalls and derive a set of design guidelines that assist the user in avoiding these problems in three important areas: user preference elicitation, preference revision, and explanation interfaces. For each area, we describe the state of the art of the developed techniques and discuss concrete scenarios where they have been applied and tested. However, automated decision systems cannot effectively search the space of possible solutions without an accurate model of a user's preferences. Preference acquisition is therefore a fundamental problem of growing importance. Without an adequate interaction model and system guidance, it is difficult for users to establish a complete and accurate model of their preferences. More specifically, we face the following difficulties: First, inadequate elicitation tools can easily mislead users to focus on means objectives rather than fundamental decision objectives and force them to state preferences in the wrong order. For example, a user who commits to the choice of minivans (means objective) for spacious baggage space (fundamental) is not focusing on the values and could risk missing alternatives offered by station wagons. In value-focus thinking, Keeney (1992) suggests that the specification and clarification of values should not be overtaken by the set of alternatives too rapidly. This theory has a direct implication on the order in which the system initially elicits user preferences. Second, users are not aware of all preferences until they see them violated. For example, a user does not think of stating a preference for the intermediate airport until a solution proposes an airplane change in a place the user dislikes. This observation sheds light on the interaction design guideline on how to help users discover their hidden preferences. Finally, preferences can be inconsistent.

If a school does not meet assessment goals for two consecutive years, by law the district must offer stu dents the opportunity to transfer to a school that is meet ing its goals. Making a choice with such potential impact on a child's future is clearly monumental, yet astonishingly few parents take advantage of the opportunity. Our research has shown that a significant part of the problem arises from issues in information access and information overload, par ticularly for low socioeconomic status families. Thus we have developed an online, content-based recommender sys tem, called SmartChoice. It provides parents with school rec ommendations for individual students based on parents' pref erences and students' needs, interests, abilities, and talents.

The process can result in massive amounts of noisy and semistructured data that must be analyzed and distilled in order to extract useful requirements. As a result, many human-intensive tasks in requirements elicitation, analysis, and management processes can be augmented and supported through the use of recommender system and machine-learning techniques. In this article we describe several areas in which recommendation technologies have been applied to the requirements engineering domain, namely stakeholder identification, domain analysis, requirements elicitation, and decision support across several requirements analysis and prioritization tasks. We also highlight ongoing challenges and opportunities for applying recommender systems in the requirements engineering domain. These activities engage various stakeholders in the task of identifying and producing an agreed-upon set of requirements that clearly specify the functionality, behavior, and constraints of the proposed system.

Marketers evaluate recommender systems not on their algorithms but on how well the vendor's expertise and interfaces will support achieving business goals. Driven by a business model that pays based on recommendation success, vendors guide clients through continuous optimization of recommendations. While recommender technology is mature, the solutions and market are still young. As a result, solutions are not fully integrated with other business systems and technology platforms. While the market is retail-focused today, interest and vendor offerings are rapidly expanding to other areas.

Dozens of vendors have built recommendation technologies and taken them to market in two waves, roughly aligning with the web 1.0 and 2.0 revolutions. Today recommender systems are found in a multitude of online services.

They provide a personalized view of such spaces, prioritizing items likely to be of interest to the user. The field, christened in 1995, has grown enormously in the variety of problems addressed and techniques employed, as well as in its practical applications. Recommender systems research has incorporated a wide variety of artificial intelligence techniques including machine learning, data mining, user modeling, case-based reasoning, and constraint satisfaction, among others. Personalized recommendations are an important part of many online e-commerce applications such as Amazon.com, This wealth of practical application experience has provided inspiration to researchers to extend the reach of recommender systems into new and challenging areas.