Predictive analytics systems are currently one of the most important areas of research and development within the Artificial Intelligence domain and particularly in Machine Learning. One of the "holy grails" of predictive analytics is the research and development of the "perfect" recommendation system. In our paper we propose an advanced pipeline model for the multi-task objective of determining product complementarity, similarity and sales prediction using deep neural models applied to big-data sequential transaction systems. Our highly parallelized hybrid pipeline consists of both unsupervised and supervised models, used for the objectives of generating semantic product embeddings and predicting sales, respectively. Our experimentation and benchmarking have been done using very large pharma-industry retailer Big Data stream.

Apple has once again summoned the media to its Cupertino, California headquarters. Monday's festivities are expected to be a star-studded sneak peak of a new $9.99 monthly entertainment subscription service, offering series and movies from the likes of Steven Spielberg, Oprah Winfrey and Brie Larson. The place to find the service is expected to be on the Apple TV app, which is available for the set-top box and on iOS devices like the iPhone and iPad. Reporters are eager to hear how Apple plans on expanding its base to TVs and other set-top boxes like Roku and Amazon Fire TV Stick. Additionally, Apple is expected to unveil a "Netflix of magazines," that will offer publications like the Wall Street Journal and People for $9.99 monthly.

You know, the first one you see when you turn on the Apple TV set-top box, which alerts you to the latest movies available for rent, TV shows to purchase and the like? Apple sees a bigger future for the app, as a launchpad for a new entertainment service, and a place where folks can subscribe to other subscription services, like HBO and Showtime. This week the company unveiled a new line of iMac computers and iPads, as well as an update to its popular AirPods bluetooth earbuds, to clear the deck and get all the focus on entertainment. Is Apple about to challenge the leaders in streaming? Monday, Apple is expected to sneak peek a new $9.99 monthly entertainment subscription service, offering series and movies from the likes of Steven Spielberg, Oprah Winfrey and Brie Larson.

Smart ceiling fans--models with wireless remote controls and digital-assistant compatibility--are a relatively new thing. But you can still control a legacy fan if you replace your in-wall switch with something like Lutron's Caséta Fan Control. It's not an inexpensive option, especially if you don't already have a Caséta bridge connected to your router, but it is a very good one. The Caséta bridge isn't required if you have no intention of integrating this fan controller into your broader smart home system, but most TechHive readers will. Lutron's Clear Connect Wireless technology is at the heart of the Caséta product line, and it's a robust competitor to the broader Z-Wave and ZigBee ecosystems.

It's cheaper and easier than ever to add some smarts to your home, and today you can make two of your dumb devices smarter for the lowest price we've ever seen. B&H Photo Video is selling the TP-Link HS107 Wi-Fi dual-outlet smart plug for $25Remove non-product link with the on-page coupon today, down from a list price of $35. The coupon applies $10 off for each plug that you buy, so you can get multiple at this price. This smart plug comes with two individually controlled outlets, so you'll be able to plug in and control two devices at once. Using the connected Kasa app, you'll be able to turn devices off and on or create schedules from anywhere using your mobile device.

Your message has been sent. There was an error emailing this page. Vacuuming is one of the most loathed household chores. While it doesn't come with the ick factor of cleaning the toilet or the tedium of dusting, pushing and dragging a noisy, cumbersome vacuum is its own kind of torture. No wonder most of us only break it out the bare-minimum-recommended once a week.

Apple's AirPods have been staggeringly successful. Although at first some found them strange-looking or were convinced they would fall out of their ears, they quickly became the in-ear wireless headphone to aspire to. Rarely in the two years and three months since launch has demand eased off. As a result, the look has gone from curious to acceptable to – dare I say it – iconic. Now, the second-generation AirPods have been announced, I talked to Greg Joswiak, Apple's Vice President of Product Marketing and Kate Bergeron, Vice President of Hardware Engineering about the new arrivals.

The recommender system is an important form of intelligent application, which assists users to alleviate from information redundancy. Among the metrics used to evaluate a recommender system, the metric of conversion has become more and more important. The majority of existing recommender systems perform poorly on the metric of conversion due to its extremely sparse feedback signal. To tackle this challenge, we propose a deep hierarchical reinforcement learning based recommendation framework, which consists of two components, i.e., high-level agent and low-level agent. The high-level agent catches long-term sparse conversion signals, and automatically sets abstract goals for low-level agent, while the low-level agent follows the abstract goals and interacts with real-time environment. To solve the inherent problem in hierarchical reinforcement learning, we propose a novel deep hierarchical reinforcement learning algorithm via multi-goals abstraction (HRL-MG). Our proposed algorithm contains three characteristics: 1) the high-level agent generates multiple goals to guide the low-level agent in different stages, which reduces the difficulty of approaching high-level goals; 2) different goals share the same state encoder parameters, which increases the update frequency of the high-level agent and thus accelerates the convergence of our proposed algorithm; 3) an appreciate benefit assignment function is designed to allocate rewards in each goal so as to coordinate different goals in a consistent direction. We evaluate our proposed algorithm based on a real-world e-commerce dataset and validate its effectiveness.

With some new and improved features. The second generation of AirPods have finally arrived. Following a hardware update cycle that saw new iPads on Monday and refreshed iMacs on Tuesday, Apple released the long-awaited update to AirPods Wednesday. Keeping the same name and largely same design as the original AirPods first released in 2016, the new earbuds start at $199 and come with a new wireless charging case, the ability to wirelessly summon Siri and Apple's new H1 chip which promises to add an extra hour of talk time. The wireless charging case, which has a little light on the front to indicate when it is charging, uses the same Qi-standard found on recent iPhones and Android devices.

For most people who talk to our technology -- whether it's Amazon's Alexa, Apple Siri or the Google Assistant -- the voice that talks back sounds female. Some people do choose to hear a male voice. Now, researchers have unveiled a new gender-neutral option: Q. "One of our big goals with Q was to contribute to a global conversation about gender, and about gender and technology and ethics, and how to be inclusive for people that identify in all sorts of different ways," says Julie Carpenter, an expert in human behavior and emerging technologies who worked on developing Project Q. The voice of Q was developed by a team of researchers, sound designers and linguists in conjunction with the organizers of Copenhagen Pride week, technology leaders in an initiative called Equal AI and others. They first recorded dozens of voices of people -- those who identify as male, female, transgender or nonbinary.