Goto

Collaborating Authors

 Personal Assistant Systems


Building a Movie Recommendation Engine in Python using Scikit-Learn

#artificialintelligence

Wondered how Google comes up with movies that are similar to the ones you like? After reading this post you will be able to build one such recommendation system for yourself. Now you might be thinking "That's interesting. But, what are the differences between these recommendation engines?". Let me help you out with that.


Amazon Bets on an Empathetic Alexa

#artificialintelligence

At least once a week, often every day, I get an email from somebody who just says that the Echo has changed their lives,


What YouTube needs to do to clean up its thorny kid issues

USATODAY - Tech Top Stories

For years, YouTube, the world's most popular video network, has been battling issues with "bad actors" wreaking havoc with the system. The Google-owned property wants to be a safe haven for advertisers to reach young viewers, primarily, with its mix of original videos and a library with virtually anything ever recorded on video. Yet once again, YouTube found itself under scrutiny this week for more abuses. Seemingly innocent videos of young girls doing gymnastics were hijacked by adult viewers commenting with time stamps and links to child pornography videos elsewhere on the web. So after being outed by YouTuber Matt Watson expressing his rage and losing top advertisers like Disney, AT&T, Epic Games and others in response, YouTube said it would change its ways, and disable commenting on any video involving children.


Fairness in Recommendation Ranking through Pairwise Comparisons

arXiv.org Artificial Intelligence

Recommender systems are one of the most pervasive applications of machine learning in industry, with many services using them to match users to products or information. As such it is important to ask: what are the possible fairness risks, how can we quantify them, and how should we address them? In this paper we offer a set of novel metrics for evaluating algorithmic fairness concerns in recommender systems. In particular we show how measuring fairness based on pairwise comparisons from randomized experiments provides a tractable means to reason about fairness in rankings from recommender systems. Building on this metric, we offer a new regularizer to encourage improving this metric during model training and thus improve fairness in the resulting rankings. We apply this pairwise regularization to a large-scale, production recommender system and show that we are able to significantly improve the system's pairwise fairness.


JBL delays Link Bar release yet again

Engadget

If you pre-ordered JBL's $399 Link Bar last August, you could end up waiting almost a year for it to arrive -- or possibly longer. Pre-order customers were originally told the all-in-one soundbar, TV box and Google Assistant speaker would ship in October. That didn't happen, and last month, unknown delays pushed shipping to spring. After pre-order customers noticed another ship-date change, Android Police confirmed with JBL that "in-market availability is now planned for mid-to-late summer." The Link Bar first gained attention for its promise to combine several features into one sleek, convenient device.


Increase Customer Lifetime Value By Personalized Recommendation on eCommerce Store

#artificialintelligence

LTCV stands for lifetime customer value i.e. a customer's timeframe of association with the business. Maximizing #customer_lifetime_value is important with #personalized_recommendation so that customers can keep coming and shopping on your e-store. The widget can be added to the accounts page so that customer can easily opt for re-purchase. Another widget- "More of your Choice" includes the products similar to those that customer has already purchased. This also helps in understanding the preferences of your customer.


10 Digital Marketing Trends That Are Totally Transforming The Landscape This Year

#artificialintelligence

In 2017, the digital marketing landscape built itself around video ads, mobile optimization, big data, dedicated apps, SEO audits, high-quality content, and smart machines. As we approach the back half of 2018, let's take a look at the digital marketing trends that are having an influence on this year and beyond. I say AI, and you go'meh!'. Because Artificial Intelligence is already everywhere, right? Well, think on a grander scale. Assistant, Siri, customer service chatbots โ€“ you encounter AI on a regular basis.


The future of AI

#artificialintelligence

In the field of computer science and information technology, the term artificial intelligence (AI) refers to the ability to endow machines with an intelligence and problem-solving capability, an analytical reasoning independent of direct control from an external operator โ€“ similar to notions of intellect demonstrated by humans and other living beings. The dream of AI dates back many years โ€“ intelligent robots appear in the myths of many ancient civilisations, including Greek, Arabic, Egyptian and Chinese. Nowadays, the field of artificial intelligence is more vibrant than ever, and some believe we're on the threshold of discoveries that could change human society irreversibly โ€“ for better or for worse. Alexa, Siri and Cortana are obvious examples of the "march of AI" into our everyday lives, but AI is being added to technology all around us. It can be found in television, mobile phones, vacuum cleaners, navigation systems, GPS systems, lawnmowers, video games, chapati makers and cars, as well as services such as Netflix, Amazon, Pandora and Nest.


Cedars-Sinai puts Amazon Alexa in patient rooms as part of a pilot program

#artificialintelligence

Los Angeles medical center Cedars-Sinai is currently piloting a program that places Amazon Echos in more than 100 patient rooms. The smart speakers use Aiva, a voice assistant platform for healthcare, and is intended to help patients communicate with their caregivers. Letting patients use Alexa to perform basic tasks like changing TV channels also frees up nurses to perform medical care. Backed by Amazon's Alexa Fund and the Google Assistant Investment Program, Aiva also participated in the Cedars-Sina accelerator program for healthcare startups. The platform also works with Google Home.


'OK Google' will no longer fully unlock your phone

Engadget

Google has come up with a compromise to make its "OK Google" feature more secure. Rather than allow users to unlock their Android devices completely (a security risk), the Voice Match command will soon limit "OK Google" to open the Assistant interface on the lock screen. There, interactions will be limited to "personal results," things like Google Calendar, email, reminders and shopping lists. For Google's phone and tablet users, this is a both loss of functionality and a significant gain in terms of security. Previously, you could say something like, "OK Google, what's the weather today?" and your device would unlock your screen to open a weather app.