With the advent of modern$4 \mathrm{G} / 5 \mathrm{G}$networks, mobile phone data collected by operators now includes detailed, servicespecific traffic information with high spatio-temporal resolution. In this paper, we explore the potential of such data for learning high-quality embeddings (representations) of urban regions. We propose a methodology that takes this data as input and employs a temporal convolutional network-based autoencoder, transformers, and learnable weighted sum models to extract key urban features. In the experimental evaluation, conducted using realworld datasets, we demonstrate that the embeddings generated by our methodology effectively capture urban characteristics. In particular, our embeddings are compared against those of a state-of-the-art multi-modal competitor across two downstream tasks, showing comparable quality. In general, our work highlights the potential and utility of service-specific mobile traffic data for urban research and the importance of making this data accessible to foster public innovation.

Mobility data analysis provides insights into human movement patterns, traffic flows, and urban planning strategies. Human dynamics analysis focuses on tracking people to investigate how individuals and groups behave, interact, and evolve. Various mobility data sources, such as GPS, mobile phone records, social media, and transportation logs, are often semantically enriched and used for these analyses. This results in the generation of new, complex datasets that require effective summarization methods to reduce data volume while preserving relevant information. In this work, we aim to demonstrate the effective use of summarized semantic trajectories in analyzing human mobility behaviours. We offer empirical evidence from a case study, showing how this type of trajectory helps in understanding human mobility, especially in distinguishing between routine and non-routine behaviours. Experimental results show that the analysis results are comparable with the results obtained in the original (non summarized) dataset.

The proliferation of tracking sensors in today's devices has led to the generation of high-frequency, high-volume streams of mobility data capturing the movements of various objects. These movement data can be enriched with semantic contextual information, such as activities, events, user preferences, and more, generating semantically enriched trajectories. Creating and managing these types of trajectories presents challenges due to the massive data volume and the heterogeneous, complex semantic dimensions. To address these issues, we introduce a novel approach, MAT-Sum, which uses a location-centric enrichment perspective to summarize massive volumes of mobility data while preserving essential semantic information. Our approach enriches geographical areas with semantic aspects to provide the underlying context for trajectories, enabling effective data reduction through trajectory summarization. In the experimental evaluation, we show that MAT-Sum effectively minimizes trajectory volume while retaining a good level of semantic quality, thus presenting a viable solution to the relevant issue of managing massive mobility data.

A wide range of core information retrieval (IR) tasks, such as searching, ranking, and filtering, to name a few, have seen tremendous improvements thanks to machine learning (ML) and artificial intelligence (AI). The traditional centralized approach to training AI/ML models is still predominant: large volumes of data generated by end users must be transferred from their origins and shared with remote locations for processing. However, this centralized paradigm suffers from significant privacy issues and does not take full advantage of the computing power of client devices like modern smartphones. A possible answer to this need is provided by federated learning (FL), which enables collaborative training of predictive models among a set of cooperating edge devices without disclosing any private local data. Unfortunately, FL is still far from being fully exploited in the IR ecosystem.

The notion of multiple aspect trajectory (MAT) has been recently introduced in the literature to represent movement data that is heavily semantically enriched with dimensions (aspects) representing various types of semantic information (e.g., stops, moves, weather, traffic, events, and points of interest). Aspects may be large in number, heterogeneous, or structurally complex. Although there is a growing volume of literature addressing the modelling and analysis of multiple aspect tra-jectories, the community suffers from a general lack of publicly available datasets. This is due to privacy concerns that make it difficult to publish such type of data, and to the lack of tools that are capable of linking raw spatio-temporal data to different types of semantic contextual data. In this work we aim to address this last issue by presenting MAT-BUILDER, a system that not only supports users during the whole semantic enrichment process, but also allows the use of a variety of external data sources. Furthermore, MAT-BUILDER has been designed with modularity and extensibility in mind, thus enabling practitioners to easily add new functionalities to the system and set up their own semantic enrichment process. The demonstration scenario, which will be showcased during the demo session, highlights how MAT-BUILDER's main features allow users to easily generate multiple aspect trajectories, hence benefiting the mobility data analysis community.

Telecommunications operators (telcos) traditional sources of income, voice and SMS, are shrinking due to customers using over-the-top (OTT) applications such as WhatsApp or Viber. In this challenging environment it is critical for telcos to maintain or grow their market share, by providing users with as good an experience as possible on their network. But the task of extracting customer insights from the vast amounts of data collected by telcos is growing in complexity and scale everey day. How can we measure and predict the quality of a user's experience on a telco network in real-time? That is the problem that we address in this paper. We present an approach to capture, in (near) real-time, the mobile customer experience in order to assess which conditions lead the user to place a call to a telco's customer care center. To this end, we follow a supervised learning approach for prediction and train our Restricted Random Forest model using, as a proxy for bad experience, the observed customer transactions in the telco data feed before the user places a call to a customer care center. We evaluate our approach using a rich dataset provided by a major African telecommunication's company and a novel big data architecture for both the training and scoring of predictive models. Our empirical study shows our solution to be effective at predicting user experience by inferring if a customer will place a call based on his current context. These promising results open new possibilities for improved customer service, which will help telcos to reduce churn rates and improve customer experience, both factors that directly impact their revenue growth.

In this paper we address the use of mobile phone location data to build urban sensing applications. In the past decade, several research works have proposed the use of different types of location data from the telecommunication network to characterise people mobility in the city. Thus, several applications to infer urban dynamics where proposed. However, different papers have used different types of mobile phone location data, making it is difficult to understand whether a particular dataset provided by a telecom operator is indeed effective for a specific urban sensing application. In this paper we address this issue by comparing the quality of the insights extracted from different types of mobile phone location data, with specific reference to two urban sensing applications: people count by location, and people flow between locations. Experiments executed on a real dataset provided by a telecom operator in Belgium show the advantages of using network-driven mobile phone location data (collected regardless on whether people are using their phone) compared to the widely used Call Detail Records.

In this paper, we present a personal journey advisor application for helping people to navigate the city using the available bike-sharing system. For a given origin and destination, the application suggests the best pair of stations to be used to take and return a city-bike, in order to minimize the overall walking and biking travel time as well as maximizing the probability to find available bikes at the first station and returning slots at the second one. To solve the journey advisor optimization problem, we modeled real mobile bikers' behavior in terms of travel time, and used the predicted availability at every bike station to choose the pair of stations which maximizes a measure of optimality. To develop the application, we built a spatio-temporal prediction system able to estimate the number of available bikes for each station in short and long term, outperforming already developed solutions. The prediction system is based on an underlying spatial interaction network among the bike stations, and takes into account the temporal patterns included in the data. The City ride application was tested with real data from the Dublin bike-sharing system.

In this paper we introduce a methodology for extracting mobility profiles of individuals from raw digital traces (in particular, GPS traces), and study criteria to match individuals based on profiles. We instantiate the profile matching problem to a specific application context, namely proactive car pooling services, and therefore develop a matching criterion that satisfies various basic constraints obtained from the background knowledge of the application domain. In order to evaluate the impact and robustness of the methods introduced, two experiments are reported, which were performed on a massive dataset containing GPS traces of private cars: (i) the impact of the car pooling application based on profile matching is measured, in terms of percentage shareable traffic; (ii) the approach is adapted to coarser-grained mobility data sources that are nowadays commonly available from telecom operators. In addition the ensuing loss in precision and coverage of profile matches is measured.

In the past few years there has been an increasing interest in the analysis of process logs. Several proposed techniques, such as workflow mining, are aimed at automatically deriving the underlying workflow models. However, current approaches only pay little attention on an important piece of information contained in process logs: the timestamps, which are used to define a sequential ordering of the performed tasks. In this work we try to overcome these limitations by explicitly including time in the extracted knowledge, thus making the temporal information a first-class citizen of the analysis process. This makes it possible to discern between apparently identical process executions that are performed with different transition times between consecutive tasks.

The pervasiveness of mobile devices and location based services is leading to an increasing volume of mobility data.This side eect provides the opportunity for innovative methods that analyse the behaviors of movements. In this paper we propose WhereNext, which is a method aimed at predicting with a certain level of accuracy the next location of a moving object. The prediction uses previously extracted movement patterns named Trajectory Patterns, which are a concise representation of behaviors of moving objects as sequences of regions frequently visited with a typical travel time. A decision tree, named T-pattern Tree, is built and evaluated with a formal training and test process. The tree is learned from the Trajectory Patterns that hold a certain area and it may be used as a predictor of the next location of a new trajectory finding the best matching path in the tree. Three dierent best matching methods to classify a new moving object are proposed and their impact on the quality of prediction is studied extensively. Using Trajectory Patterns as predictive rules has the following implications: (I) the learning depends on the movement of all available objects in a certain area instead of on the individual history of an object; (II) the prediction tree intrinsically contains the spatio-temporal properties that have emerged from the data and this allows us to define matching methods that striclty depend on the properties of such movements. In addition, we propose a set of other measures, that evaluate a priori the predictive power of a set of Trajectory Patterns. This measures were tuned on a real life case study. Finally, an exhaustive set of experiments and results on the real dataset are presented.

The increasing pervasiveness of location-acquisition technologies (GPS, GSM networks, etc.) is leading to the collection of large spatio-temporal datasets and to the opportunity of discovering usable knowledge about movement behaviour, which fosters novel applications and services. In this paper, we move towards this direction and develop an extension of the sequential pattern mining paradigm that analyzes the trajectories of moving objects. We introduce trajectory patterns as concise descriptions of frequent behaviours, in terms of both space (i.e., the regions of space visited during movements) and time (i.e., the duration of movements). In this setting, we provide a general formal statement of the novel mining problem and then study several different instantiations of different complexity. The various approaches are then empirically evaluated over real data and synthetic benchmarks, comparing their strengths and weaknesses.