The most common way to listen to recorded music nowadays is via streaming platforms which provide access to tens of millions of tracks. To assist users in effectively browsing these large catalogs, the integration of Music Recommender Systems (MRSs) has become essential. Current real-world MRSs are often quite complex and optimized for recommendation accuracy. They combine several building blocks based on collaborative filtering and content-based recommendation. This complexity can hinder the ability to explain recommendations to end users, which is particularly important for recommendations perceived as unexpected or inappropriate.

Recommender systems play an important role in helping people find information and make decisions in today's increasingly digitalized societies. However, the wide adoption of such machine learning applications also causes concerns in terms of data privacy. These concerns are addressed by the recent "General Data Protection Regulation" (GDPR) in Europe, which requires companies to delete personal user data upon request when users enforce their "right to be forgotten". Many researchers argue that this deletion obligation does not only apply to the data stored in primary data stores such as relational databases but also requires an update of machine learning models whose training set included the personal data to delete. We explore this direction in the context of a sequential recommendation task called Next Basket Recommendation (NBR), where the goal is to recommend a set of items based on a user's purchase history. We design efficient algorithms for incrementally and decrementally updating a state-of-the-art next basket recommendation model in response to additions and deletions of user baskets and items. Furthermore, we discuss an efficient, data-parallel implementation of our method in the Spark Structured Streaming system. We evaluate our implementation on a variety of real-world datasets, where we investigate the impact of our update techniques on several ranking metrics and measure the time to perform model updates. Our results show that our method provides constant update time efficiency with respect to an additional user basket in the incremental case, and linear efficiency in the decremental case where we delete existing baskets. With modest computational resources, we are able to update models with a latency of around 0.2~milliseconds regardless of the history size in the incremental case, and less than one millisecond in the decremental case.

Tinder is charging people over 30 up to 48 per cent more for its premium service, an investigation has revealed. Which? said its findings suggest possible discrimination and a potential breach of UK law by the popular dating app. The consumer group also initially accused Tinder of hiking prices for young gay and lesbian users aged 18-29, but has since backtracked on this. A statement from Which? said: 'Having initially chosen not to provide further information, Tinder has since revealed that it offers discounts to users aged 28 and under in the UK.' It added that the dating app'claimed that by including 29-year-olds in our analysis of the relationship between price with age and sexual orientation, "the results would be skewed to make it appear that LGBTQAI members paid more based upon orientation, when in fact, it was based upon age".' Which? said that in light of the new information, it has'no evidence that sexual orientation impacts pricing for young Tinder users'. Tinder had previously said it was'categorically untrue' that its pricing structure discriminates by sexual preference.

You can now get Google Assistant to stop talking with just one word: "Stop." That's it -- you don't even have to say "Hey, Google" before that. The official Google Twitter account has announced the small but necessary quality-of-life improvement for the company's speakers and smart displays. It sometimes takes a while (and several repeated attempts) to get Assistant's attention with a "Hey, Google" if it suddenly goes off without you wanting it to or if you absolutely have to cut it off mid-spiel. This new feature solves that problem.

Here's a fun thought experiment; picture the amount of personal data you think tech companies keep on you. Now, realize it's actually way more than that (hmm, maybe this isn't that fun). Even as privacy and security become more talked about in consumer tech, the companies behind our favorite products are collecting more and more of our data. Well, if you want to know the information, say, Amazon has on you, there is a way to find out. To be clear, data collection is far from an Amazon-specific problem; it's pretty much par for the course when it comes to tech companies.

The amount of time we spend doing repetitive work is mind-boggling, with manual computer tasks and data entry taking up a good portion of an office worker's day. A recent survey indicates that people estimate they waste five hours each week on tasks that should be automated. According to McKinsey, the number is even higher, with at least one-third of job activities deemed automatable in about 60% of occupations. Whether it's data collection, approvals, or updates, many tasks don't require creativity or intuition, essential attributes that serve to increase job satisfaction. Instead, the monotony of the work lowers satisfaction, leading to lower productivity and other inefficiencies.

A previous version of this paper, entitled "Personalized Recommendation of PoIs to People with Autism," was published in the Proceedings of the 28th ACM Conference on User Modeling, Adaptation and Personalization (Genoa, Italy, 2020), 163–172.

Recommender systems are among the most pervasive machine learning applications on the Internet. Social media, audio and video streaming, news, and e-commerce are all heavily driven by the data-intensive personalization they enable, leveraging information drawn from the behavior of large user bases to offer a myriad of recommendation services. Point of Interest (PoI) recommendation is the task of recommending locations (business, cultural sites, natural areas) for a user to visit. This is a well-established sub-field within recommender systems, and as a domain of application, it provides a good introduction to the challenges of applying personalized recommendation in practical contexts. An effective PoI recommender must consider a user's interests and preferences, as in any personalized system, but also practical aspects of travel: weather, congestion, hours of operation, seasonality, to name a few.

At a Glance: So far we have gone through the pre-processing pipeline of the Criteo Dataset using the standard NVTabular toolkit present inside Merlin SDKs. This was a part of the ETL processing and it is present under Part 1. Followed by this, in Part 2, we have gone through the training procedures using the HugeCTR architecture. We have explored 4 standard state-of-the-art architectures using HugeCTR training toolkits inside Merlin. In this section, we are going to explore the inference implementation which is the final deployment process using the Triton Inference Server. Nvidia's Merlin contains 3 crucial components.

The most common way to listen to recorded music nowadays is via streaming platforms which provide access to tens of millions of tracks. To assist users in effectively browsing these large catalogs, the integration of Music Recommender Systems (MRSs) has become essential. Current real-world MRSs are often quite complex and optimized for recommendation accuracy. They combine several building blocks based on collaborative filtering and content-based recommendation. This complexity can hinder the ability to explain recommendations to end users, which is particularly important for recommendations perceived as unexpected or inappropriate. While pure recommendation performance often correlates with user satisfaction, explainability has a positive impact on other factors such as trust and forgiveness, which are ultimately essential to maintain user loyalty. In this article, we discuss how explainability can be addressed in the context of MRSs. We provide perspectives on how explainability could improve music recommendation algorithms and enhance user experience. First, we review common dimensions and goals of recommenders' explainability and in general of eXplainable Artificial Intelligence (XAI), and elaborate on the extent to which these apply -- or need to be adapted -- to the specific characteristics of music consumption and recommendation. Then, we show how explainability components can be integrated within a MRS and in what form explanations can be provided. Since the evaluation of explanation quality is decoupled from pure accuracy-based evaluation criteria, we also discuss requirements and strategies for evaluating explanations of music recommendations. Finally, we describe the current challenges for introducing explainability within a large-scale industrial music recommender system and provide research perspectives.