The closed feedback loop in recommender systems is a common setting that can lead to different types of biases. Several studies have dealt with these biases by designing methods to mitigate their effect on the recommendations. However, most existing studies do not consider the iterative behavior of the system where the closed feedback loop plays a crucial role in incorporating different biases into several parts of the recommendation steps. We present a theoretical framework to model the asymptotic evolution of the different components of a recommender system operating within a feedback loop setting, and derive theoretical bounds and convergence properties on quantifiable measures of the user discovery and blind spots. We also validate our theoretical findings empirically using a real-life dataset and empirically test the efficiency of a basic exploration strategy within our theoretical framework. Our findings lay the theoretical basis for quantifying the effect of feedback loops and for designing Artificial Intelligence and machine learning algorithms that explicitly incorporate the iterative nature of feedback loops in the machine learning and recommendation process.

As recommender systems send a massive amount of content to keep users engaged, users may experience fatigue which is contributed by 1) an overexposure to irrelevant content, 2) boredom from seeing too many similar recommendations. To address this problem, we consider an online learning setting where a platform learns a policy to recommend content that takes user fatigue into account. We propose an extension of the Dependent Click Model (DCM) to describe users' behavior. We stipulate that for each piece of content, its attractiveness to a user depends on its intrinsic relevance and a discount factor which measures how many similar contents have been shown. Users view the recommended content sequentially and click on the ones that they find attractive. Users may leave the platform at any time, and the probability of exiting is higher when they do not like the content. Based on user's feedback, the platform learns the relevance of the underlying content as well as the discounting effect due to content fatigue. We refer to this learning task as "fatigue-aware DCM Bandit" problem. We consider two learning scenarios depending on whether the discounting effect is known. For each scenario, we propose a learning algorithm which simultaneously explores and exploits, and characterize its regret bound.

Recommender systems play a fundamental role in web applications in filtering massive information and matching user interests. While many efforts have been devoted to developing more effective models in various scenarios, the exploration on the explainability of recommender systems is running behind. Explanations could help improve user experience and discover system defects. In this paper, after formally introducing the elements that are related to model explainability, we propose a novel explainable recommendation model through improving the transparency of the representation learning process. Specifically, to overcome the representation entangling problem in traditional models, we revise traditional graph convolution to discriminate information from different layers. Also, each representation vector is factorized into several segments, where each segment relates to one semantic aspect in data. Different from previous work, in our model, factor discovery and representation learning are simultaneously conducted, and we are able to handle extra attribute information and knowledge. In this way, the proposed model can learn interpretable and meaningful representations for users and items. Unlike traditional methods that need to make a trade-off between explainability and effectiveness, the performance of our proposed explainable model is not negatively affected after considering explainability. Finally, comprehensive experiments are conducted to validate the performance of our model as well as explanation faithfulness.

Recently, self-attention based models have achieved state-of-the-art performance in sequential recommendation task. Following the custom from language processing, most of these models rely on a simple positional embedding to exploit the sequential nature of the user's history. However, there are some limitations regarding the current approaches. First, sequential recommendation is different from language processing in that timestamp information is available. Previous models have not made good use of it to extract additional contextual information. Second, using a simple embedding scheme can lead to information bottleneck since the same embedding has to represent all possible contextual biases. Third, since previous models use the same positional embedding in each attention head, they can wastefully learn overlapping patterns. To address these limitations, we propose MEANTIME (MixturE of AtteNTIon mechanisms with Multi-temporal Embeddings) which employs multiple types of temporal embeddings designed to capture various patterns from the user's behavior sequence, and an attention structure that fully leverages such diversity. Experiments on real-world data show that our proposed method outperforms current state-of-the-art sequential recommendation methods, and we provide an extensive ablation study to analyze how the model gains from the diverse positional information.

Machine learning is becoming more important in our daily lives. But most of us probably never envisioned a day when it would be important in online dating or the beginning of new relationships. A growing number of video chat services are utilizing machine learning features in interesting ways. MarTech Series published an article last year on the growing relevance of machine learning in video conferencing. The same principles can be just as applicable to video chats with online dating services.

In the first part of this blog, we looked at how Artificial Intelligence (AI) has shifted to the supplier side of the retail eco-system, particularly in two areas -- price and product offering. In this post, we will explore how this has impacted the buyer's journey at almost every stage. As many of you know, the buyer's journey starts from the awareness stage, where he comes to learn about a product or brand, and then goes through the following steps: research, consideration, purchase, and retention; The second is that a company tries to capture its customers. Above all, history shows that people who have previously purchased from your company will be repeat customers if they are happy with the entire journey. AI E-commerce has retained the power to analyze vast ways of data and human behavior.

As Amazon continues its "off-to-college" savings event, Best Buy is offering a couple of Alexa speaker bundles that are great deals if you want the most bang for your buck. The latest among them is a bundle that includes a free Echo Show 5 and a Philips Hue smart light bulb when you buy an Echo Show for $180. Not only do you get those two freebies, but you're getting the Echo Show smart display for $50 off. Best Buy also cut the price of a bundle we covered earlier this month: now you can get an Echo Studio with a free Echo Show 5 and Philips Hue bulb for only $170. Best Buy doesn't advertise the freebies clearly, but you can see the full details of the bundle by clicking the "free items with purchase" link underneath the price on each product page.

Video meet app Zoom on Wednesday announced that it will now be available on smart home displays including Amazon Echo Show, Portal from Facebook and Google Nest Hub Max. Zoom on Portal is expected to be available publicly in September and will arrive on Echo Show and Google Nest Hub Max by the end of the year. "We're excited to bring Zoom to these popular devices. It's more apparent than ever that people are looking for easy-to-use displays for their video communications needs, both professionally and personally," said Oded Gal, Chief Product Officer at Zoom. As a part of Zoom for Home, Zoom users will be able to extend integrated calendar and HD video and audio for Zoom Meetings on these smart displays.

It is expected that innovations such as progressive web apps, artificial intelligence, and augmented/virtual reality will continue to evolve in 2020. Every industry needs some sort of online platform to create a reputation for its business. There are over 1.5 billion websites, including over 200 million popular websites, according to Internet Live Statistics. Yet figures keep on increasing. Through the years the industry has evolved with emerging trends and technologies. To remain ahead of the market, businesses need to concentrate on rising patterns, strategies and solutions to custom site creation.

Multi-room audio specialist Sonos is back with the Arc, the firm's first Dolby Atmos-enabled soundbar that totally transforms your TV's sound. It is a single box of tricks that combines a smart speaker, wifi music sound system and home cinema kit in one, but like most soundbars of this type it can be dogged by audio-picture syncing issues when used with TV set top boxes – more on that later. The Arc looks deceptively simple. It is a sleek, one metre-long cylinder that is surprisingly compact considering there are eight separate woofers, three tweeters and a collection of electronics all hidden behind the matt metal mesh. Four of the woofers face you directly through the front of the Arc.