Cross-Domain Collaborative Filtering (CDCF) provides a way to alleviate data sparsity and cold-start problems present in recommendation systems by exploiting the knowledge from related domains. Existing CDCF models are either based on matrix factorization or deep neural networks. Either of the techniques in isolation may result in suboptimal performance for the prediction task. Also, most of the existing models face challenges particularly in handling diversity between domains and learning complex non-linear relationships that exist amongst entities (users/items) within and across domains. In this work, we propose an end-to-end neural network model -- NeuCDCF, to address these challenges in a cross-domain setting. More importantly, NeuCDCF follows a wide and deep framework and it learns the representations combinedly from both matrix factorization and deep neural networks. We perform experiments on four real-world datasets and demonstrate that our model performs better than state-of-the-art CDCF models.

Unsupervised domain adaptation for classification tasks has achieved great progress in leveraging the knowledge in a labeled (source) domain to improve the task performance in an unlabeled (target) domain by mitigating the effect of distribution discrepancy. However, most existing methods can only handle unsupervised closed set domain adaptation (UCSDA), where the source and target domains share the same label set. In this paper, we target a more challenging but realistic setting: unsupervised open set domain adaptation (UOSDA), where the target domain has unknown classes that the source domain does not have. This study is the first to give the generalization bound of open set domain adaptation through theoretically investigating the risk of the target classifier on the unknown classes. The proposed generalization bound for open set domain adaptation has a special term, namely open set difference, which reflects the risk of the target classifier on unknown classes. According to this generalization bound, we propose a novel and theoretically guided unsupervised open set domain adaptation method: Distribution Alignment with Open Difference (DAOD), which is based on the structural risk minimization principle and open set difference regularization. The experiments on several benchmark datasets show the superior performance of the proposed UOSDA method compared with the state-of-the-art methods in the literature.

Recent progress in AutoML has lead to state-of-the-art methods (e.g., AutoSKLearn) that can be readily used by non-experts to approach any supervised learning problem. Whereas these methods are quite effective, they are still limited in the sense that they work for tabular (matrix formatted) data only. This paper describes one step forward in trying to automate the design of supervised learning methods in the context of text mining. We introduce a meta learning methodology for automatically obtaining a representation for text mining tasks starting from raw text. We report experiments considering 60 different textual representations and more than 80 text mining datasets associated to a wide variety of tasks. Experimental results show the proposed methodology is a promising solution to obtain highly effective off the shell text classification pipelines.

Personalized Route Recommendation (PRR) aims to generate user-specific route suggestions in response to users' route queries. Early studies cast the PRR task as a pathfinding problem on graphs, and adopt adapted search algorithms by integrating heuristic strategies. Although these methods are effective to some extent, they require setting the cost functions with heuristics. In addition, it is difficult to utilize useful context information in the search procedure. To address these issues, we propose using neural networks to automatically learn the cost functions of a classic heuristic algorithm, namely A* algorithm, for the PRR task. Our model consists of two components. First, we employ attention-based Recurrent Neural Networks (RNN) to model the cost from the source to the candidate location by incorporating useful context information. Instead of learning a single cost value, the RNN component is able to learn a time-varying vectorized representation for the moving state of a user. Second, we propose to use a value network for estimating the cost from a candidate location to the destination. For capturing structural characteristics, the value network is built on top of improved graph attention networks by incorporating the moving state of a user and other context information. The two components are integrated in a principled way for deriving a more accurate cost of a candidate location. Extensive experiment results on three real-world datasets have shown the effectiveness and robustness of the proposed model.

In order for robots and other artificial agents to efficiently learn to perform useful tasks defined by an end user, they must understand not only the goals of those tasks, but also the structure and dynamics of that user's environment. While existing work has looked at how the goals of a task can be inferred from a human teacher, the agent is often left to learn about the environment on its own. To address this limitation, we develop an algorithm, Behavior Aware Modeling (BAM), which incorporates a teacher's knowledge into a model of the transition dynamics of an agent's environment. We evaluate BAM both in simulation and with real human teachers, learning from a combination of task demonstrations and evaluative feedback, and show that it can outperform approaches which do not explicitly consider this source of dynamics knowledge.

A main driver behind the digitization of industry and society is the belief that data-driven model building and decision making can contribute to higher degrees of automation and more informed decisions. Building such models from data often involves the application of some form of machine learning. Thus, there is an ever growing demand in work force with the necessary skill set to do so. This demand has given rise to a new research topic concerned with fitting machine learning models fully automatically - AutoML. This paper gives an overview of the state of the art in AutoML with a focus on practical applicability in a business context, and provides recent benchmark results on the most important AutoML algorithms.

On 20 July 1969, before an estimated television audience of 650 million, a lunar module named Eagle touched down on the moon's Sea of Tranquility. The tension of the landing and the images of astronauts in futuristic spacesuits striding over the moon's barren surface, Earth reflected in their oversized visors, would prove wildly influential to artists, writers and film-makers. Also watching were the soon-to-be proponents of another technological field populated by brilliant young geeks: computer games. It is perhaps no coincidence that during the early 1960s, when Nasa was working with the Massachusetts Institute of Technology's Instrumentation Lab to develop the guidance and control systems for Apollo spacecraft, elsewhere on campus a programmer named Steve Russell was working with a small team to create one of the first true video game experiences. Inspired by the space race, and using the same DEC PDP-1 model of mainframe computer that generated spacecraft telemetry data for Nasa's Mariner programme, Russell wrote Spacewar!, a simple combat game in which two players controlled starships with limited fuel, duelling around the gravitational well of a nearby star.

To perform a better assessment of the value that is brought through analytics, we asked respondents exactly what they used the data and analytics in their organisation for. A compelling 98% of all respondents believed that analytics did play a role in their organisation. Its deployment, however, varied from case to case. When asked about the role that analytics played in their system, 39% of respondents believed that analytics was used for making both tactical and strategic decisions across the organisation.

Artificial Intelligence enables marketers to understand sales cycles better, correlating their strategies and spending to sales results. AI-driven insights are also helping to break down data silos so marketing and sales can collaborate more on deals. Marketing is more analytics and quant-driven than ever before with the best CMOs knowing which metrics and KPIs to track and why they fluctuate. The bottom line is that machine learning and AI are the technologies CMOs and their teams need to excel today. The best CMOs balance the quant-intensive nature of running marketing with qualitative factors that make a company's brand and customer experience unique.

In 2017, work-related injuries cost insurance companies an estimated $161 billion. And of course the impact on workers' health and safety goes beyond the numbers. That's why many worksites require protective gear such as helmets, vests, gloves, and masks. But enforcing these policies can be a challenge. It's not always practical to keep staff on hand to monitor workers.