Route recommendation is significant in navigation service. Two major challenges for route recommendation are route representation and user representation. Different from items that can be identified by unique IDs in traditional recommendation, routes are combinations of links (i.e., a road segment and its following action like turning left) and the number of combinations could be close to infinite. Besides, the representation of a route changes under different scenarios. These facts result in severe sparsity of routes, which increases the difficulty of route representation. Moreover, link attribute deficiencies and errors affect preciseness of route representation. Because of the sparsity of routes, the interaction data between users and routes are also sparse. This makes it not easy to acquire user representation from historical user-item interactions as traditional recommendations do. To address these issues, we propose a novel learning framework R4. In R4, we design a sparse & dense network to obtain representations of routes. The sparse unit learns link ID embeddings and aggregates them to represent a route, which captures implicit route characteristics and subsequently alleviates problems caused by link attribute deficiencies and errors. The dense unit extracts implicit local features of routes from link attributes. For user representation, we utilize a series of historical navigation to extract user preference. R4 achieves remarkable performance in both offline and online experiments.

Machine learning has developed a variety of tools for learning and representing high-dimensional distributions with structure. Recent years have also seen big advances in designing multi-item mechanisms. Akin to overfitting, however, these mechanisms can be extremely sensitive to the Bayesian prior that they target, which becomes problematic when that prior is only approximately known. We consider a multi-item mechanism design problem where the bidders' value distributions can be approximated by a topic model. Our solution builds on a recent robustification framework by Brustle et al., which disentangles the statistical challenge of estimating a multi-dimensional prior from the task of designing a good mechanism for it, robustifying the performance of the latter against the estimation error of the former. We provide an extension of the framework that allows us to exploit the expressive power of topic models to reduce the effective dimensionality of the mechanism design problem.

The world, as we see it, is digitizing itself from its peripheral edges to its very core as technology evolves leap by leap. And in this technologically advanced world, concepts such as'artificial intelligence,' 'machine learning,' or'data science' are no longer a figment of the imagination of sci-fi authors like Asimov but a reality that is very much here. The new-age tech is now paving its way to not only establishing itself subtly and not-so-subtly in our everyday lives but also leading the world to its fourth industrial revolution. The amount of data generated by both humans and machines far outpaces humans' ability to absorb, interpret, and make complex decisions based on that data. But a chunk of unstructured data is meaningless until it is converted to generate valuable, meaningful information.

Artificial intelligence (AI) has made important strides in transforming business practices and processes across a wide range of sectors, by helping organisations streamline operations, manage risk and reduce costs. This is especially true when it comes to critical activities such as marketing, customer service and sales, which have been identified by Forbes as the top three areas that AI can enhance business growth. Thanks to AI, we are now seeing a proliferation of digital assistants, also known as predictive chatbots. These are application programs that not only understand natural language voice commands, but can also simulate a conversation with users and complete tasks on their behalf. Using AI and machine learning, combined with a user's history, preferences, and other information, they can respond to difficult questions, make recommendations, and even start conversations.

It's a modern age conundrum: for years, customers have engaged with ChatBots to resolve a whole range of queries, only to be left frustrated and dissatisfied by the experience While these solutions are adept at automating the customer service process and cutting costs, their limited functionality means they have generated little value wider business context – until now. A new generation of technologies has been developed to not only service customers more effectively, but also to optimize human resource management and employee enablement. Even now that Conversational AI (CAI) technologies have arrived on the scene to take user experience (UX) to the next level, the truth is, that many individuals will still mistake them for run-of-the-mill Bots. The result of this is that some organizations might invest in the wrong technologies, or else dismiss next-gen solutions that could boost their efficiency. Beyond just offering first-line support to customers and colleagues, or the conversational acumen of home assistants like Alexa or Siri, newer CAI technologies are capable of fielding a much more complex range of queries, which will no doubt be a great service to organizations in the remote climate.

Support agents that help users in their daily lives need to take into account not only the user's characteristics, but also the social situation of the user. Existing work on including social context uses some type of situation cue as an input to information processing techniques in order to assess the expected behavior of the user. However, research shows that it is important to also determine the meaning of a situation, a step which we refer to as social situation comprehension. We propose using psychological characteristics of situations, which have been proposed in social science for ascribing meaning to situations, as the basis for social situation comprehension. Using data from user studies, we evaluate this proposal from two perspectives. First, from a technical perspective, we show that psychological characteristics of situations can be used as input to predict the priority of social situations, and that psychological characteristics of situations can be predicted from the features of a social situation. Second, we investigate the role of the comprehension step in human-machine meaning making. We show that psychological characteristics can be successfully used as a basis for explanations given to users about the decisions of an agenda management personal assistant agent.

THE INSTITUTE Artificial intelligence is transforming the financial services industry. The technology is being used to determine creditworthiness, identify money laundering, and detect fraud. AI also is helping to personalize services and recommend new offerings by developing a better understanding of customers. Chatbots and other AI assistants have made it easier for clients to get answers to their questions, 24/7. Although confidence in financial institutions is high, according to the Banking Exchange, that's not the case with AI.

The problem of low-rank matrix completion with heterogeneous and sub-exponential (as opposed to homogeneous and Gaussian) noise is particularly relevant to a number of applications in modern commerce. Examples include panel sales data and data collected from web-commerce systems such as recommendation engines. An important unresolved question for this problem is characterizing the distribution of estimated matrix entries under common low-rank estimators. Such a characterization is essential to any application that requires quantification of uncertainty in these estimates and has heretofore only been available under the assumption of homogenous Gaussian noise. Here we characterize the distribution of estimated matrix entries when the observation noise is heterogeneous sub-exponential and provide, as an application, explicit formulas for this distribution when observed entries are Poisson or Binary distributed.

At I/O 2021, Google reiterated its commitment to Matter with a handful of smart home-related Nest and Android updates. If you need a refresher, Matter was known as Project CHIP, or Connected Home over IP, before a rebranding this past May. It's a pact between some of the biggest companies in tech, including Google, Amazon and Apple, that aims to bring standardization to the fragmented smart home space. When it launches in the first half of 2022, it will support a variety of voice assistants and networking protocols, including Alexa, Google Assistant, Siri as well as WiFi, Thread and Bluetooth LE. At its simplest, the promise of Matter is that you'll be able to buy a new device and it will simply work with your existing smart home setup.

Artificial intelligence (AI) is transforming the landscape of 21st century marketing. Long gone are the days of throwing spaghetti on the wall and shooting in the dark to acquire new customers and to regain their business. With the amount of data growing exponentially on a daily basis, AI can help businesses scale their marketing efforts and leverage the data for actionable insights leading to greater ROI. Look up the term "marketing" and you'll find something that mentions actions or activities involving a business or company, promoting or selling products or services. Is that something that you or your company does?