It's a situation familiar to anyone who's ever communicated with a voice assistant on a smart device. You pose a request: "Hey Voice Assistant, tell me a story about Georgia Tech." More often than not, you get a related response – "Georgia Tech is located in Atlanta, Georgia. Would you like me to provide you with directions?" – but one with slightly unnatural language and only limited information. Despite the enormous strides made in artificial intelligence to develop systems that can answer simple questions and requests, the kinds of natural conversational language humans have with each other when giving more complex directions or telling stories has thus far been out of reach.

Financial services and technology vendors make for uneasy bedfellows. While tech has formed banking's bedrock since the Big Bang deregulation of the 1980s, in the last decade financial services (FS) organisations have seen the new "masters of the universe" steadily – almost stealthily – encroach on their patch. Established tech vendors and new start-ups have introduced a range of financial services from money transfer apps to mobile payments, crowdfunding to share trading and investments. These new services are perfectly suited to a generation who have grown up with smartphones and expect instant access to digital services, combined simplicity and a great user experience. While over the last few years there has been an exponential increase in the structured data that is collected and used, the inclusion of unstructured data sets, pictures, images and videos along with structured data has been increasingly important in driving both strategic and operational business decisions.

An effective content recommendation on social media platforms should be able to benefit both creators to earn fair compensation and consumers to enjoy really relevant, interesting, and personalized content. In this paper, we propose a model to implement the liquid democracy principle for the content recommendation system. It uses a personalized recommendation model based on reputation ranking system to encourage personal interests driven recommendation. Moreover, the personalization factors to an end users' higher-order friends on the social network (initial input Twitter channels in our case study) to improve the accuracy and diversity of recommendation results. This paper analyzes the dataset based on cryptocurrency news on Twitter to find the opinion leader using the liquid rank reputation system. This paper deals with the tier-2 implementation of a liquid rank in a content recommendation model. This model can be also used as an additional layer in the other recommendation systems. The paper proposes the implementation, challenges, and future scope of the liquid rank reputation model.

Due to its deep learning and independent decision-making capabilities, applications of AI in different business areas are seeing a steady rise in ubiquity in some industries. The concept of artificial intelligence or machines that aim to emulate human thinking is undergoing vigorous research and is a topic that is increasingly being associated with the Internet of things. An AI enabled IoT system extends the functionality and value of an organization's offering, without the need for committing additional resources to achieve the increased value. This is exemplified by under Armour(UA) and IBM's collaboration on the UA Record app, which is an AI-based personal fitness coaching system, that uses a variety of sensor data to suggest highly personalized, context-relevant fitness activities to users. Such applications of AI are going to be more commonplace in the future as they are already having a significant impact on many industries.

Amazon wants Alexa owners to buy more things. That's the clear impetus behind the new Alexa feature announced today at Amazon's Accelerate conference, called Customers Ask Alexa, which lets brands submit answers to common questions like "How can I remove pet hair from my carpet?" and "How to eliminate odor from soil stains?" Previously, Alexa supplied generic tips from the web and other sources in response to such queries. But Customers Ask Alexa basically turns answers into sponsored product spots. "Brands registered with Amazon Brand Registry will see the new Customers Ask Alexa feature in Seller Central, where they can easily discover and answer frequently asked customer questions using self-service tools," Amazon explains in a blog post.

Beamforming-capable antenna arrays overcome the high free-space path loss at higher carrier frequencies. However, the beams must be properly aligned to ensure that the highest power is radiated towards (and received by) the user equipment (UE). While there are methods that improve upon an exhaustive search for optimal beams by some form of hierarchical search, they can be prone to return only locally optimal solutions with small beam gains. Other approaches address this problem by exploiting contextual information, e.g., the position of the UE or information from neighboring base stations (BS), but the burden of computing and communicating this additional information can be high. Methods based on machine learning so far suffer from the accompanying training, performance monitoring and deployment complexity that hinders their application at scale. This paper proposes a novel method for solving the initial beam-discovery problem. It is scalable, and easy to tune and to implement. Our algorithm is based on a recommender system that associates groups (i.e., UEs) and preferences (i.e., beams from a codebook) based on a training data set. Whenever a new UE needs to be served our algorithm returns the best beams in this user cluster. Our simulation results demonstrate the efficiency and robustness of our approach, not only in single BS setups but also in setups that require a coordination among several BSs. Our method consistently outperforms standard baseline algorithms in the given task.

Out-of-Domain (OOD) detection is a key component in a task-oriented dialog system, which aims to identify whether a query falls outside the predefined supported intent set. Previous softmax-based detection algorithms are proved to be overconfident for OOD samples. In this paper, we analyze overconfident OOD comes from distribution uncertainty due to the mismatch between the training and test distributions, which makes the model can't confidently make predictions thus probably causing abnormal softmax scores. We propose a Bayesian OOD detection framework to calibrate distribution uncertainty using Monte-Carlo Dropout. Our method is flexible and easily pluggable into existing softmax-based baselines and gains 33.33\% OOD F1 improvements with increasing only 0.41\% inference time compared to MSP. Further analyses show the effectiveness of Bayesian learning for OOD detection.

Sequential recommender systems have shown effective suggestions by capturing users' interest drift. There have been two groups of existing sequential models: user- and item-centric models. The user-centric models capture personalized interest drift based on each user's sequential consumption history, but do not explicitly consider whether users' interest in items sustains beyond the training time, i.e., interest sustainability. On the other hand, the item-centric models consider whether users' general interest sustains after the training time, but it is not personalized. In this work, we propose a recommender system taking advantages of the models in both categories. Our proposed model captures personalized interest sustainability, indicating whether each user's interest in items will sustain beyond the training time or not. We first formulate a task that requires to predict which items each user will consume in the recent period of the training time based on users' consumption history. We then propose simple yet effective schemes to augment users' sparse consumption history. Extensive experiments show that the proposed model outperforms 10 baseline models on 11 real-world datasets. The codes are available at https://github.com/dmhyun/PERIS.

Iterative machine learning algorithms used to power recommender systems often change people's preferences by trying to learn them. Further a recommender can better predict what a user will do by making its users more predictable. Some preference changes on the part of the user are self-induced and desired whether the recommender caused them or not. This paper proposes that solutions to preference manipulation in recommender systems must take into account certain meta-preferences (preferences over another preference) in order to respect the autonomy of the user and not be manipulative.

Aqara, a leading provider of smart home products, introduced its Radiator Thermostat E1 to automate hydronic radiators including wall-mounted radiators, towel warmers and even warm floors, making the heating systems smarter for improved energy efficiency and comfort. This radiator thermostat supports most radiator valves with its M30*1.5mm The Aqara Radiator Thermostat E1 is now available on European Amazon stores (France, Germany, Italy, Spain, UK), as well as via selective Aqara retailers in Europe. Based on the Zigbee 3.0 protocol, the Thermostat is expected to support the future-proofing Matter standard via an OTA update of the compatible, Zigbee 3.0-based Aqara hub. The device is also compatible with major ecosystems and voice assistants such as HomeKit/Siri, Alexa, Google Home/Google Assistant, IFTTT, Home Assistant and more.