LivePerson believes that artificial intelligence (AI) and automation are the foundation for transforming the conversational experience and customer service. This requires altering the way agents operate and the way brands interact with consumers. LivePerson is a leading conversational AI company that creates digital experiences that are curiously human. Conversational AI allows humans and machines to interact using natural language, including speech or text. Already consumer preference has shifted from calling to messaging in personal life.

Traditionally, when recommender systems are formalized as multi-armed bandits, the policy of the recommender system influences the rewards accrued, but not the length of interaction. However, in real-world systems, dissatisfied users may depart (and never come back). In this work, we propose a novel multi-armed bandit setup that captures such policy-dependent horizons. Our setup consists of a finite set of user types, and multiple arms with Bernoulli payoffs. Each (user type, arm) tuple corresponds to an (unknown) reward probability. Each user's type is initially unknown and can only be inferred through their response to recommendations. Moreover, if a user is dissatisfied with their recommendation, they might depart the system. We first address the case where all users share the same type, demonstrating that a recent UCB-based algorithm is optimal. We then move forward to the more challenging case, where users are divided among two types. While naive approaches cannot handle this setting, we provide an efficient learning algorithm that achieves $\tilde{O}(\sqrt{T})$ regret, where $T$ is the number of users.

This is a guest post co-authored by Taylor Names, Staff Machine Learning Engineer, Dev Gupta, Machine Learning Manager, and Argie Angeleas, Senior Product Manager at Ibotta. Ibotta is an American technology company that enables users with its desktop and mobile apps to earn cash back on in-store, mobile app, and online purchases with receipt submission, linked retailer loyalty accounts, payments, and purchase verification. Ibotta strives to recommend personalized promotions to better retain and engage its users. However, promotions and user preferences are constantly evolving. This ever-changing environment with many new users and new promotions is a typical cold start problem--there is no sufficient historical user and promotion interactions to draw any inferences from.

The Google Home app should soon be more convenient -- and familiar, if you're an Android user. Google is rolling out updates to Home for Android and iOS that should provide more powerful controls even as they remove some of the clutter. Most notably, you'll see simpler, Android 11-inspired smart home controls in the main view over the weeks ahead. You can tap devices to turn them on, use sliders to quickly dim lights or raise a speaker's volume and long-press if you need more control. As of this week, you'll find a settings section that lets you manage privacy controls, Assistant data and home activity within the Google Home app.

Virginie Do, Sam Corbett-Davies, Jamal Atif and Nicolas Usunier won the AAAI 2022 outstanding paper award for their work Online certification of preference-based fairness for personalized recommender systems. The award was presented at this year's virtual AAAI Conference on Artificial Intelligence. Here, Virginie Do tells us more about the implications of this research, the methodology, and their main findings. Our paper is about fairness in recommender systems, and more precisely about certifying that recommender systems treat their users fairly. We conducted this research in a context of increased interest in auditing for the fairness of recommender systems.

Cortana (Jen Taylor) is one of the first characters that comes to mind when you think of the Halo universe. With a live-action Halo series on the way on Paramount, we thought a guide to Cortana (without giving too much away for those who haven't made their way through all the games) was in order. Cortana serves as a guide and ally to the player throughout Halo gameplay, and in that sense and many others, she is essential to the Halo experience. Her mannerisms as an AI make for a sort of dry humor that makes her stand out among other recurring characters in the game. It will be interesting to see how this character, who fits so easily into the video game format, will be adapted to a live-action television series.

Many powerful machine learning algorithms—including PageRank (Pregel), recommendation engines (collaborative filtering), and text summarization and other NLP tasks—are based on graphs. And there are even more applications once you consider data pr...

On Monday evening, the Lapsus$ digital extortion gang published a series of increasingly shocking posts in its Telegram channel. First, the group dumped what it claims is extensive source code from Microsoft's Bing search engine, Bing Maps, and Cortana virtual assistant software. A potential breach of an organization as big and security-conscious as Microsoft would be significant in itself, but the group followed the post with something even more alarming: screenshots apparently taken on January 21 that seem to show Lapsus$ in control of an Okta administrative or "super user" account. Okta is a near-ubiquitous identity management platform used by thousands of large organizations that want to make it easy--and, crucially, secure--for their employees or partners to log in to multiple services without juggling a dozen passwords. Past breaches, like 2020's notorious Twitter meltdown, have stemmed from attackers taking over access to an administrative or support account that has the ability to modify customers' accounts.

Artificial intelligence, AI for short, is a newcomer in the digital marketing arena. And yet it has the power to create a true revolution in the field if businesses choose to embrace it. In this article we will examine how artificial intelligence could be applied to digital marketing, and why it's best to start adopting it sooner rather than later. Search engines are always evolving and adapting, and AI is the next frontier for the likes of Google, Bing, Yahoo and more. The old SEO game is dead.

Modern educational systems have not really evolved enough to meet the needs of modern students.21 No wonder, the percentage of dropouts from university studies is quite high (40% in the U.S. and 10% in Europe7,9). The university student profile has changed over the years. While yesterday's students were mainly full-time, today's students face challenges such as work commitments, family obligations, financial constraints, physical impairments, and learning models that do not adequately engage students or help them understand core concepts.11 One might think that this issue concerns only those who fail to complete their studies, but this is view is shortsighted. Today's educational system deficiencies will affect the welfare of tomorrow's society. To improve current learning models, academic institutions around the world agree that the time has come to improve the world of education, moving from a traditional approach--where learning is standardized and available only to those with access to educational buildings--to a new paradigm that enables students to personalize their educational pathway, so they can progress at their own pace.19,21