Churn happens when a customer leaves a brand or stop using its services. Brands reduce their churn rates by identifying and retaining potential churners through customer retention campaigns. In this paper, we consider the problem of classifying micro-posts as churny or non-churny with respect to a given brand. Motivated by the recent success of recurrent neural networks (RNNs) in word representation, we propose to utilize RNNs to learn micro-post and churn indicator representations. We show that such representations improve the performance of churn detection in microblogs and lead to more accurate ranking of churny contents. Furthermore, in this researchwe show that state-of-the-art sentiment analysis approaches fail to identify churny contents. Experiments on Twitter data about three telco brands show the utility of our approach for this task.

In the past decade, social and information networks have become prevalent, and research on the network data has attracted much attention. Besides the link structure, network data are often equipped with the content information (i.e, node attributes) that is usually noisy and characterized by high dimensionality. As the curse of dimensionality could hamper the performance of many machine learning tasks on networks (e.g., community detection and link prediction), feature selection can be a useful technique for alleviating such issue. In this paper, we investigate the problem of unsupervised feature selection on networks. Most existing feature selection methods fail to incorporate the linkage information, and the state-of-the-art approaches usually rely on pseudo labels generated from clustering. Such cluster labels may be far from accurate and can mislead the feature selection process. To address these issues, we propose a generative point of view for unsupervised features selection on networks that can seamlessly exploit the linkage and content information in a more effective manner. We assume that the link structures and node content are generated from a succinct set of high-quality features, and we find these features through maximizing the likelihood of the generation process. Experimental results on three real-world datasets show that our approach can select more discriminative features than state-of-the-art methods.

We investigate the problem of repacking stations in the FCC's upcoming, multi-billion-dollar "incentive auction". Early efforts to solve this problem considered mixed-integer programming formulations, which we show are unable to reliably solve realistic, national-scale problem instances. We describe the result of a multi-year investigation of alternatives: a solver, SATFC, that has been adopted by the FCC for use in the incentive auction. SATFC is based on a SAT encoding paired with a wide range of techniques: constraint graph decomposition; novel caching mechanisms that allow for reuse of partial solutions from related, solved problems; algorithm configuration; algorithm portfolios; and the marriage of local-search and complete solver strategies. We show that our approach solves virtually all of a set of problems derived from auction simulations within the short time budget required in practice.

To whom correspondence should be addressed; Email: artitw@gmail.com Customer temporal behavioral data was represented as images in order to perform churn prediction by leveraging deep learning architectures prominent in image classification. Supervised learning was performed on labeled data of over 6 million customers using deep convolutional neural networks, which achieved an AUC of 0.743 on the test dataset using no more than 12 temporal features for each customer. Unsupervised learning was conducted using autoencoders to better understand the reasons for customer churn. Images that maximally activate the hidden units of an autoencoder trained with churned customers reveal ample opportunities for action to be taken to prevent churn among strong data, no voice users.

If you hadn't heard of the RoboHon before, it's all the basic smartphone functions reborn into a tiny robot body. It walks, it dances, and an embedded projector inside its head can display photos and video at a functional-enough 720p resolution. Sharp confirms that it does have LTE radios inside: this was a big question mark when the phone was first announced, and the company adds that it's already working on NTT Docomo, Japan's biggest phone carrier -- although its plans to couple with smaller MVNO carriers at this point, rather than announce a launch with a big phone network. This could be crucial in deciding whether the phone sells in Japan: carriers will advertise with their own money -- Sharp may have to do a lot of the heavy PR lifting itself. "Do you think RoboHon will sell?"

In just a few years, it will provide customer service in airports, hospitals, train stations and other facilities, speaking four languages so that it can even serve the masses of foreign tourists streaming into Japan. It is Hitachi's Emiew3 -- a smaller, faster and more agile competitor unveiled Friday. The new robot marks the third generation, and first commercially viable member, of a series that began with an experimental model in 2005. The company seeks to put it on the market in 2018. In a demonstration Friday, an Emiew3 prototype surveyed its surroundings and approached an actress playing a lost foreigner.

I recently had the opportunity to learn more about Inbenta, a provider of Natural Language Search technology for intelligent assistant and web self-service technologies. I spoke with global marketing director Julie Casson and Kelly Foster, linguist, to gain insight into a company I didn't know much about. Inbenta originated in Barcelona, and now has offices in the United States, France, Singapore, Brazil and the Netherlands. Casson and Foster are located at the office in Sunnyvale, California. Prior to our conversation, I knew that Inbenta offers intelligent assistant technology and an extremely innovative 3D avatar, called Victoria.

We have the expertise to help enterprises of all sizes take on their greatest challenges. Let us show you how our products and services can help you achieve your business goals.

Nasa has announced that it has found evidence of flowing water on Mars. Scientists have long speculated that Recurring Slope Lineae -- or dark patches -- on Mars were made up of briny water but the new findings prove that those patches are caused by liquid water, which it has established by finding hydrated salts. Several hundred camped outside the London store in Covent Garden. The 6s will have new features like a vastly improved camera and a pressure-sensitive "3D Touch" display

People who rely on satnav could be at risk of losing their ability to navigate, an expert has warned. Writing in the journal Nature, former president of the Royal Institute of Navigation Roger McKinlay argues that our reliance on GPS technology is misplaced and could be eroding our innate way-finding abilities. "If we do not cherish them, our natural navigation abilities will deteriorate as we rely ever more on smart devices," he wrote. McKinlay believes huge investment will be needed before navigation systems will be good enough to allow technologies such as autonomous vehicles to take off. In the meantime, he argues, we need better research into systems for navigation while children should be encouraged to learn how to find their way around by more traditional means.