Fine-grained location prediction on smart phones can be used to improve app/system performance. Application scenarios include video quality adaptation as a function of the 5G network quality at predicted user locations, and augmented reality apps that speed up content rendering based on predicted user locations. Such use cases require prediction error in the same range as the GPS error, and no existing works on location prediction can achieve this level of accuracy. We propose Federated Meta-Location Learning (FMLL) on smart phones for fine-grained location prediction, based on GPSt races collected on the phones. FMLL has three components: a meta-location generation module, a prediction model, and a federated learning framework. The meta-location generation module represents the user location data as relative points in an abstract 2D space, which enables learning across different physical spaces. The model fuses Bidirectional Long Short-Term Memory (BiLSTM) and Convolutional Neural Networks (CNN), where BiLSTM learns the speed and direction of the mobile users, and CNN learns information such as user movement preferences. The framework runs on the phones of the users and also on a server that coordinates learning from all users in the system. FMLL uses federated learning to protect user privacy and reduce bandwidth consumption. Our experimental results, using a dataset with over 600,000 users, demonstrate that FMLL outperforms baseline models in terms of prediction accuracy. We also demonstrate that FMLL works well in conjunction with transfer learning, which enables model reusability. Finally, benchmark results on Android phones demonstrate FMLL’s feasibility in real life.

Corporations spend billions of dollars annually caring for customers across multiple contact channels. A customer journey is the complete sequence of contacts that a given customer has with a company across multiple channels of communication. While each contact is important and contains rich information, studying customer journeys provides a better context to understand customers' behavior in order to improve customer satisfaction and loyalty, and to reduce care costs. However, journey sequences have a complex format due to the heterogeneity of user behavior: they are variable-length, multi-attribute, and exhibit a large cardinality in categories (e.g. contact reasons). The question of how to characterize and learn representations of customer journeys has not been studied in the literature. We propose to learn journey embeddings using a sequence-to-sequence framework that converts each customer journey into a fixed-length latent embedding. In order to improve the disentanglement and distributional properties of embeddings, the model is further modified by incorporating a Wasserstein autoencoder inspired regularization on the distribution of embeddings. Experiments conducted on an enterprise-scale dataset demonstrate the effectiveness of the proposed model and reveal significant improvements due to the regularization in both distinguishing journey pattern characteristics and predicting future customer engagement.

Cellular traffic prediction enables operators to adapt to traffic demand in real-time for improving network resource utilization and user experience. To predict cellular traffic, previous studies either applied Recurrent Neural Networks (RNN) at individual base stations or adapted Convolutional Neural Networks (CNN) to work at grid-cells in a geographically defined grid. These solutions do not consider explicitly the effect of handover on the spatial characteristics of the traffic, which may lead to lower prediction accuracy. Furthermore, RNN solutions are slow to train, and CNN-grid solutions do not work for cells and are difficult to apply to base stations. This paper proposes a new prediction model, STGCN-HO, that uses the transition probability matrix of the handover graph to improve traffic prediction. STGCN-HO builds a stacked residual neural network structure incorporating graph convolutions and gated linear units to capture both spatial and temporal aspects of the traffic. Unlike RNN, STGCN-HO is fast to train and simultaneously predicts traffic demand for all base stations based on the information gathered from the whole graph. Unlike CNN-grid, STGCN-HO can make predictions not only for base stations, but also for cells within base stations. Experiments using data from a large cellular network operator demonstrate that our model outperforms existing solutions in terms of prediction accuracy.

Applying Machine Learning (ML) to business applications for automation usually faces difficulties when integrating diverse ML dependencies and services, mainly because of the lack of a common ML framework. In most cases, the ML models are developed for applications which are targeted for specific business domain use cases, leading to duplicated effort, and making reuse impossible. This paper presents Acumos, an open platform capable of packaging ML models into portable containerized microservices which can be easily shared via the platform's catalog, and can be integrated into various business applications. We present a case study of packaging sentiment analysis and classification ML models via the Acumos platform, permitting easy sharing with others. We demonstrate that the Acumos platform reduces the technical burden on application developers when applying machine learning models to their business applications. Furthermore, the platform allows the reuse of readily available ML microservices in various business domains.

With widespread adoption and growing sophistication of mobile devices, fraudsters have turned their attention from landlines and wired networks to cellular networks. While security threats to wireless data channels and applications have attracted the most attention, voice-related fraud activities also represent a serious threat to mobile users. In particular, we have seen increasing numbers of incidents where fraudsters deploy malicious apps, e.g., disguised as gaming apps to entice users to download; when invoked, these apps automatically - and without users' knowledge - dial certain (international) phone numbers which charge exorbitantly high fees. Fraudsters also frequently utilize social engineering (e.g., SMS or email spam, Facebook postings) to trick users into dialing these exorbitant fee-charging numbers.

Effective management of large-scale cellular data networks is critical to meet customer demands and expectations. Customer calls for technical support provide direct indication as to the problems customers encounter. In this paper, we study the customer tickets - free-text recordings and classifications by customer support agents - collected at a large cellular network provider, with two inter-related goals: i) to characterize and understand the major factors which lead to customers to call and seek support; and ii) to utilize such customer tickets to help identify potential network problems. For this purpose, we develop a novel statistical approach to model customer call rates which account for customer-side factors (e.g., user tenure and handset types) and geo-locations. We show that most calls are due to customer-side factors and can be well captured by the model. Furthermore, we also demonstrate that location-specific deviations from the model provide a good indicator of potential network-side issues.

Keyword-based searches on the World Wide Web are often of limited use, because they return too many uninteresting matches. We propose here a novel mechanism that permits the user to specify directory sets to restrict the space of documents searched, and, at the same time, increase the speed of the search. We view the Web as a single, huge hierarchy, reflected in the structure of the URLs. We refer to each subtree in this hierarchy as a directory, and group semantically related documents from multiple directories into a directory set. Starting from a collection of pre-defined directory sets, a user can dynamically generate new directory sets by using operators in a directory set algebra, and focus keywordbased searches to documents that belong to a (pre-defined or dynamically generated) directory set. We design algorithms for efficiently evaluating expressions in the directory set algebra, and describe a technique for tightly integrating directory sets into keyword-based search engines....

Presents a technique for building an index into a Huffman-coded file that permits efficient random access to the encoded data. The technique provides the ability to find the starting position of the jth symbol of the uncompressed file in an n-bit compressed file in O(log n) bit-examinations of the compressed file plus its index. Furthermore, the size of the index is o(n) bits. In other words, the ratio of the space occupied by the index to the space occupied by the data approaches zero as the length of the data file increases without bound.>

Data structures that represent static unlabeled trees and planar graphs are developed. The structures are more space efficient than conventional pointer-based representations, but (to within a constant factor) they are just as time efficient for traversal operations. For trees, the data structures described are asymptotically optimal: there is no other structure that encodes n-node trees with fewer bits per node, as N grows without bound. For planar graphs (and for all graphs of bounded page number), the data structure described uses linear space: it is within a constant factor of the most succinct representation.>