Many interesting problems in the Internet industry can be framed as a two-sided marketplace problem. Examples include search applications and recommender systems showing people, jobs, movies, products, restaurants, etc. Incorporating fairness while building such systems is crucial and can have deep social and economic impact (applications include job recommendations, recruiters searching for candidates, etc.). In this paper, we propose a definition and develop an end-to-end framework for achieving fairness while building such machine learning systems at scale. We extend prior work [29] to develop an optimization framework that can tackle fairness constraints from both the source and destination sides of the marketplace, as well as dynamic aspects of the problem. The framework is flexible enough to adapt to different definitions of fairness and can be implemented in very large-scale settings. We perform simulations to show the efficacy of our approach.

Google Maps is working on a new feature that will show you how to reach the nearest public transport connection, according to new leaked screenshots. The new Maps filter will let users choose what mode of transportation they will be using at the very beginning of their daily commute, the screenshots show. Once rolled out, the feature will allow commuters to work out their preferred route to various transport connections, such as the train station, when they return to the workplace after the coronavirus pandemic. The screenshots also reveal an option to get more accurate Uber fares using data from Google Maps and a slightly new design for the Maps interface. 'Google Maps is working on route options with "Connections to Public Transit", such as car and transit, bicycle and transit, auto rickshaw, ride service [and] motorcycle and transit,' said Jane Wong, a Hong Kong-based hacker, tech blogger and software engineer, who leaked the screenshots.

There is no doubt that the artificial intelligence (AI) phenomenon will have a profound impact on businesses large and small this year; that part is easy to predict. What impact it will have, and whether this is a good or a bad thing, is harder to tell. Let's start with the basics of AI. In their PwC briefing, Chris Curran and Anand Rao explained it this way: "In our broad definition, AI is a collective term for computer systems that can sense their environment, think, learn, and take action in response to what they're sensing and their objectives. Forms of AI in use today include, among others, digital assistants, chatbots, and machine learning. Helping people to perform tasks faster and better. Helping people to make better decisions. Automating decision making processes without human intervention."

Tiktok has revealed greater insight into how its recommendation algorithm works in a new blog post. The algorithm uses a number of factors to base its suggestions of 15-second clips. Theses include user interactions, such as the videos a user likes or shares, accounts they follow, and comments posted as well as video information such as sounds and hashtags. Tiktok will use your device and language settings to "make sure the system is optimised for performance" but receive lower weight compared to the other metrics "since users don't actively express these as preferences." Many of TikTok's algorithm influences will be familiar; similar features are offered by other social media sites such as Twitter and YouTube upon setting up a new account.

I lead the Search Experience team at Walmart and I am writing my first story on search and recommendation engines.

While the debates rage on over whether or not anyone needs 8K, the new line of Denon receivers are ready for higher resolution video when and if you decide to make an upgrade. Perhaps more importantly, they also support HDMI 2.1, including features like auto low latency mode (ALLM), variable refresh rate (VRR), passthrough of 4K video at up to 120 frames per second and quick frame transport (QFT) that reduces input lag. These features are especially key if you're planning to get the Xbox Series X or PlayStation 5 when those consoles ship this fall. All four of the new X-Series receivers include one 8K input and they support quick media switching (QMS), which should eliminate blank screens when you switch between content that uses different refresh rates. They also support Roon music management that pulls in metadata for your various media files, and voice control with Amazon Alexa, Google Assistant, Siri and Josh.ai.

Apple pioneered the voice revolution in 2011 with the introduction of Siri in its iPhone 4s. Today, you tell your iPhone 11, "Hey Siri, Play Bruce Springsteen by Spotify," and it responds, "I can't talk to Spotify, but you can use Apple music instead," politely displaying options on the screena as shown in the figure here. Or, you tell one of your five Amazon Echo devices at home, "Alexa, add pumpkin pie to my Target shopping list,"b then "order AA Duracell batteries," and it adds pumpkin pie and Amazon Basics batteries to your Amazon shopping cart, ignoring your request to shop at Target and be loyal to Duracell. You are the consumer, but your choices have been ignored. Or, consider you are a brand manager.

The May 2020 update has arrived, and one noticeable change is Microsoft Cortana. If you were used to asking the virtual assistant questions, it may be time to switch to another assistant. Microsoft's decided to revamp Cortana into a productivity tool, eliminating many of the features you might have been used to. The big question – is Cortana still worth using for the average user? Even though some users absolutely love Microsoft Cortana, she never really caught on quite like Amazon Alexa, Google Assistant, and Siri. Instead of investing more time and money into trying to compete, Microsoft made the choice to turn Cortana into a system application versus the whole system integration the assistant once had.

The word "deep" in "deep learning" refers to the number of layers through which the data is transformed. Deep models are able to extract better features than shallow models and hence, extra layers help in learning the features effectively.

Recommendation is a prevalent application of machine learning that affects many users; therefore, it is important for recommender models to be accurate and interpretable. In this work, we propose a method to both interpret and augment the predictions of black-box recommender systems. In particular, we propose to interpret feature interactions from a source recommender model and explicitly encode these interactions in a target recommender model, where both source and target models are black-boxes. By not assuming the structure of the recommender system, our approach can be used in general settings. In our experiments, we focus on a prominent use of machine learning recommendation: ad-click prediction. We found that our interaction interpretations are both informative and predictive, e.g., significantly outperforming existing recommender models. What's more, the same approach to interpret interactions can provide new insights into domains even beyond recommendation, such as text and image classification.