Search and recommendation systems, such as search engines, recruiting tools, online marketplaces, news, and social media, output ranked lists of content, products, and sometimes, people. Credit ratings, standardized tests, risk assessments output only a score, but are also used implicitly for ranking. Bias in such ranking systems, especially among the top ranks, can worsen social and economic inequalities, polarize opinions, and reinforce stereotypes. On the other hand, a bias correction for minority groups can cause more harm if perceived as favoring group-fair outcomes over meritocracy. In this paper, we study a trade-off between individual fairness and group fairness in ranking. We define individual fairness based on how close the predicted rank of each item is to its true rank, and prove a lower bound on the trade-off achievable for simultaneous individual and group fairness in ranking. We give a fair ranking algorithm that takes any given ranking and outputs another ranking with simultaneous individual and group fairness guarantees comparable to the lower bound we prove. Our algorithm can be used to both pre-process training data as well as post-process the output of existing ranking algorithms. Our experimental results show that our algorithm performs better than the state-of-the-art fair learning to rank and fair post-processing baselines.

A Chatbot is a pure magic. AI-powered virtual assistants are the future of the tech industry that opened the door for all companies to interact with their users. The Chatbot is not a new concept. Although they have been technically using since the 1950s, virtual bots are hottest in the technology and digital marketing world. Many popular brands such as Uber, Pizza Hut implemented them to reach more customers efficiently. As a survey of 2018, 38% of Americans would use Chatbots to interact with a company or brand.

Google has a new Assistant routine that will remind you of the passage of time as you continue to work from home. The workday routine will prompt you to get up and move, go for a walk, grab a glass of water and other normal human being activities at various points throughout the day, just in case, you know, you were beginning to atrophy at your desk while seasons changed outside your window. The new feature rolls out this week and comes pre-configured with suggested actions at specific times, though you can customize these yourself. So instead of (or in addition to) "start preparing dinner" at 5pm, you might set a reminder to "Take a shower, you stink" at 7pm, too. Assistant will serve these reminders through your smart display or speaker, and will also regularly share the time with you throughout the day.

Google Assistant already knows how to slowly brighten a smart light to simulate the sunrise, as well as how to gradually dim your smart lights at bedtime. The catch, however, was that it was only able to perform the trick with Philips Hue smart lights, but that's changing starting today. Besides the Assistant's improved "Gentle Sleep and Wake" functionality, Google is also rolling out a new pre-made routine designed to ease the strain of your workday. We'll cover the new Workday routine in a moment. First, Google just announced that over the next few days, it will start rolling out an update that allows Google Assistant to slowly brighten or dim all smart lights, not just those from Philips Hue.

Amazon Prime Day, previously postponed due to the coronavirus pandemic, is now scheduled for Oct. 13-14, and Amazon just might compensate for the three month-long postponement with even better deals and lower prices. The new date was revealed in internal Amazon emails sent to employees, who were also told not to take any vacation leaves Oct. 13-20. One memo said the company will officially confirm Oct. 13-14 in an announcement on Sunday, according to The Verge. "Stay tuned for more details on Prime Day," said an Amazon spokesperson, who also said customers can ask Alexa devices to keep them updated about Prime Day. Prime Days have normally been held July 15, the anniversary Amazon's founding anniversary.

NEWSUPDATE247 is an Entertainment and News website that publishes accurate, trusted and reliable news.

One year ago, I was visiting with the CEO of a financial services company, and she was telling me about its implementation of digital employees. "They do rote tasks, and they work on projects," she said. "In fact, we even assign them employee numbers!" I was aware of digitalizing routine, repetitive tasks for digital agents to perform, and of the work that was being done with robotic process automation (RPA)--but was surprised at the idea of a digital assistant that was a full-time employee in an organization. Now one year later, digital assistants are being taught to behave in even more human-like fashion so they can assume more responsibilities.

Contextual bandits provide an effective way to model the dynamic data problem in ML by leveraging online (incremental) learning to continuously adjust the predictions based on changing environment. We explore details on contextual bandits, an extension to the traditional reinforcement learning (RL) problem and build a novel algorithm to solve this problem using an array of action-based learners. We apply this approach to model an article recommendation system using an array of stochastic gradient descent (SGD) learners to make predictions on rewards based on actions taken. We then extend the approach to a publicly available MovieLens dataset and explore the findings. First, we make available a simplified simulated dataset showing varying user preferences over time and how this can be evaluated with static and dynamic learning algorithms. This dataset made available as part of this research is intentionally simulated with limited number of features and can be used to evaluate different problem-solving strategies. We will build a classifier using static dataset and evaluate its performance on this dataset. We show limitations of static learner due to fixed context at a point of time and how changing that context brings down the accuracy. Next we develop a novel algorithm for solving the contextual bandit problem. Similar to the linear bandits, this algorithm maps the reward as a function of context vector but uses an array of learners to capture variation between actions/arms. We develop a bandit algorithm using an array of stochastic gradient descent (SGD) learners, with separate learner per arm. Finally, we will apply this contextual bandit algorithm to predicting movie ratings over time by different users from the standard Movie Lens dataset and demonstrate the results.

Increasing users' positive interactions, such as purchases or clicks, is an important objective of recommender systems. Recommenders typically aim to select items that users will interact with. If the recommended items are purchased, an increase in sales is expected. However, the items could have been purchased even without recommendation. Thus, we want to recommend items that results in purchases caused by recommendation. This can be formulated as a ranking problem in terms of the causal effect. Despite its importance, this problem has not been well explored in the related research. It is challenging because the ground truth of causal effect is unobservable, and estimating the causal effect is prone to the bias arising from currently deployed recommenders. This paper proposes an unbiased learning framework for the causal effect of recommendation. Based on the inverse propensity scoring technique, the proposed framework first constructs unbiased estimators for ranking metrics. Then, it conducts empirical risk minimization on the estimators with propensity capping, which reduces variance under finite training samples. Based on the framework, we develop an unbiased learning method for the causal effect extension of a ranking metric. We theoretically analyze the unbiasedness of the proposed method and empirically demonstrate that the proposed method outperforms other biased learning methods in various settings.

Microsoft's Cortana-powered consumer speakers are dead. Long live...Cortana powered Teams speakers? During a Microsoft Ignite keynote by Jared Spataro, the vice president of Microsoft 365, Microsoft showed off a demonstration room powered by some of its latest hardware, including the 85-inch Surface Hub 2S, plus companion devices like Teams Rooms, which are third-party bundles of cameras and small displays for facilitating meetings. Microsoft's idea is that the Teams Rooms devices will manage the meetings, with voice assistance using Cortana, and capabilities like Teams casting and the Room remote app for facilitating conferences. One of the key capabilities of the Microsoft Teams software is its ability to listen to, record, and transcribe the conversation.