As more and more people shift their movie watching online, competition between movie viewing websites are getting more and more intense. Therefore, it has become incredibly important to accurately predict a given user's watching list to maximize the chances of keeping the user on the platform. Recent studies have suggested that the novelty-seeking propensity of users can impact their viewing behavior. In this paper, we aim to accurately model and describe this novelty-seeking trait across many users and timestamps driven by data, taking into consideration user forgetfulness. Compared to previous studies, we propose a more robust measure for novelty. Our model, termed Deep Forgetful Novelty-Seeking Model (DFNSM), leverages demographic information about users, genre information about movies, and novelty-seeking traits to predict the most likely next actions of a user. To evaluate the performance of our model, we conducted extensive experiments on a large movie rating dataset. The results reveal that DFNSM is very effective for movie recommendation.

In 2006, Netflix, which was then a DVD rental service, announced a data science competition for movie rating predictions. The company would offer a $1 million grand prize to the team that could improve their existing recommender system's prediction accuracy by 10%. The competition garnered much interest from researchers and engineers in both academia and industry. Within the first year of the competition, over 40,000 teams from more than 100 countries had entered the competition [1]. In June 2009, the prize was awarded to BellKor's Pragmatic Chaos, a team of AT&T engineers, who submitted the winning algorithm a few minutes earlier than the second-place team [2].

I wrote about recommender systems last week, but there is so much discussion around their effects right now in the mainstream tech press that they deserve a second issue. As a recap, I said that there were two things that made recommender systems super ineffective, and that YouTube, one of the premier companies tech using recommendations, suffers from both a lot of the first and a lot of the second. Recommender systems today have two huge problems that are leading companies (sometimes at enormous pressure from the public) to rethink how they're being used: technical bias, and business bias. The real problem is YouTube's business model. YouTube is THIRSTY for advertising money, at all times.

It will no longer keep audio recordings of Siri users by default, though it will retain automatically generated transcripts of the requests. Users will be able to opt in to sharing their recordings with Apple. "We hope that many people will choose to help Siri get better," the company said. Only Apple employees will be allowed to listen to those audio samples. The company had previously outsourced the work to contracting firms.

Facebook has teamed up with researchers at the Massachusetts Institute of Technology (MIT) to develop an artificial intelligence (AI) assistant for the world's most popular video game, Minecraft. This isn't an AI that will help you automatically build worlds, but rather one capable of multitasking and helping users with everyday tasks outside a gaming environment. Minecraft was chosen by the researchers because it's currently the most popular game in the world with more than 90-million people playing it every month and it has "infinite variety" yet simple predictable rules. Plus, there's a big opportunity for the AI assistant to learn inside'Minecraft' and help human players to acquire more knowledge outside the game. "The opportunities for an AI to learn are huge, Facebook is setting itself the task of designing the AI to self-improve, the researchers think the'Minecraft' environment is a perfect one to develop this kind of learning," said the report.

Bubbling enthusiasts for robots and artificial intelligence (AI) gush technical about how a new revolution is going to transform our lives. But it isn't clear whether the transformation is going to be favourable or unfavourable. What I read from the geeks is a mixture of two distinctly different visions: first, the idea that we all face a terrible future – involving poverty, loss of self-worth, or even annihilation – as our creation, the robots, take over; second, the idea that the revolution is going to enrich us all and free humanity from drudgery. As an economist, I share the second of these visions. I believe that the AI revolution is broadly a continuation of everything that has happened...

A significant barrier to progress in data-driven approaches to building dialog systems is the lack of high quality, goal-oriented conversational data. To help satisfy this elementary requirement, we introduce the initial release of the Taskmaster-1 dataset which includes 13,215 task-based dialogs comprising six domains. Two procedures were used to create this collection, each with unique advantages. The first involves a two-person, spoken "Wizard of Oz" (WOz) approach in which trained agents and crowdsourced workers interact to complete the task while the second is "self-dialog" in which crowdsourced workers write the entire dialog themselves. We do not restrict the workers to detailed scripts or to a small knowledge base and hence we observe that our dataset contains more realistic and diverse conversations in comparison to existing datasets. We offer several baseline models including state of the art neural seq2seq architectures with benchmark performance as well as qualitative human evaluations. Dialogs are labeled with API calls and arguments, a simple and cost effective approach which avoids the requirement of complex annotation schema. The layer of abstraction between the dialog model and the service provider API allows for a given model to interact with multiple services that provide similar functionally. Finally, the dataset will evoke interest in written vs. spoken language, discourse patterns, error handling and other linguistic phenomena related to dialog system research, development and design.

President Trump's personal assistant, Madeline Westerhout, resigned from the White House amid allegations she shared private information about the president to reporters. President Trump on Friday expressed disappointment over what he described as the "unfortunate" departure this week of his personal assistant Madeleine Westerhout over "hurtful" comments she made to reporters at a recent off-the-record gathering, saying Westerhout explained to him she was "drinking" at the time. "She told me she was very upset," Trump told reporters before boarding Marine One. She said she was drinking." On Thursday, it was reported that Westerhout abruptly left her job after it was determined she shared private information about the president and his family with reporters near Bedminster, N.J., where Trump was on vacation. According to Trump, "She was with reporters and everything she said was off the record." But some of her comments made their way back to the White House. "I think the press was very dishonest," he said. "Because it was supposed to be off the record." The president didn't cite what Westerhout said – but said her comments were a "little bit hurtful." "You don't say things like she said," she said. According to Politico, Westerhout shared intimate details about the president's family – including about daughters Ivanka and Tiffany -- during the dinner with reporters "Tiffany is great," Trump said Friday, in response to those reports. Westerhout served as a gatekeeper to the president, having a desk outside the Oval Office. Trump said: "She's a very good person.

Apple today announced some major changes to its controversial'Siri audio grading program' following criticism for employing humans to listen to audio recordings of users collected via its voice-controlled Siri personal assistant without their knowledge or consent. The move came a month after The Guardian reported that third-party contractors were regularly listening to private conversations of Apple users giving voice commands to Siri in a bid to improve the quality of its product's response. While the data received by the contractors were anonymized and not associated to Apple devices, the private conversations--which also includes private discussions between doctors and patients, business deals, seemingly criminal dealings, people having sex and so on--sometimes reveal identifiable details like a person's name or medical records. In response to the backlash Apple received after the report went public, the company initially responded by temporarily suspending the program earlier this month while it thoroughly reviewed its practices and policies. Now, Apple today revealed that the company intends to continue that program in the fall, but only after making three significant changes to it, as mentioned below: First, Apple will no longer retain audio recordings of Siri interactions by default.

You'd expect Microsoft's offices to be wired with some snappy technology. When it comes to booking a meeting room, Microsoft employees can tell an artificial intelligence-powered (AI) bot how many people need to sit down at what time and the bot will return ideas for the best spaces based on the headcount plus availability. The American software giant envisions that sort of AI making its way into medical exam rooms, PowerPoint slides and other companies' administrative offices over the next five years, says Ken Sun, general manager of Microsoft Taiwan where a lot of the research is being done. Artificial intelligence technology, better known as AI, refers to making machines react and process information, often based on giant data reserves, much as people do. "It's super exciting," Sun says in an interview.