Lookalike models are based on the assumption that user similarity plays an important role towards product selling and enhancing the existing advertising campaigns from a very large user base. Challenges associated to these models reside on the heterogeneity of the user base and its sparsity. In this work, we propose a novel framework that unifies the customers' different behaviors or features such as demographics, buying behaviors on different platforms, customer loyalty behaviors and build a lookalike model to improve customer targeting for Rakuten Group, Inc. Extensive experiments on real e-commerce and travel datasets demonstrate the effectiveness of our proposed lookalike model for user targeting task.

We present Move2Kube, a replatforming framework that automates the creation and transformation of DevOps artifacts of an application for deployment in a Cloud Native environment. Our contributions include a customizable transformer framework that allows for complete control over the artifacts being processed, and output generated. We provide case studies and open-source benchmark-based evidence comparing Move2Kube with similar state-of-the-art tools to demonstrate its effectiveness in terms of effort reduction, diverse utility, and highlight future lines of work. Move2Kube is being developed as an open-source community project and it is available at: https://move2kube.konveyor.io/

We present Move2Kube, a replatforming framework that automates the transformation of the deployment specification and development pipeline of an application from a non-Kubernetes platform to a Kubernetes-based one, minimizing changes to the application's functional implementation and architecture. Our contributions include: (1) a standardized intermediate representation to which diverse application deployment artifacts could be translated, (2) an extension framework for adding support for new source platforms, and target artifacts while allowing customization as per organizational standards. We provide initial evidence of its effectiveness in terms of effort reduction, and highlight the current research challenges and future lines of work. Move2Kube is being developed as an open source community project and it is available at https://move2kube.konveyor.io/

Registering altered domain names with the purpose of confusing users and conducting malicious activities is one of the most widespread types of attacks on the Web, conforming a family of techniques known as domain squatting. Detecting these domains is a difficult task, given the large a mount of combinations and the massive and heterogeneous nature of the Web. In this work, we propose a set of models to firstly learn the distributional regularities from detected squatted domains, and from that, automatically generate realistic modified domains. Our goal is to proactively guide the generation of squatted domains towards malicious domains that exists but have not been detected yet. We conducted an empirical study for both typo-squatting and combo-squatting generation approaches against strong baselines on real world data, showing their feasibility and providing insights to support for proactive defense in the context of cloud security.

In software development, bug localization is the process finding portions of source code associated to a submitted bug report. This task has been modeled as an information retrieval task at source code file, where the report is the query. In this work, we propose a model that, instead of working at file level, learns feature representations from source changes extracted from the project history at both syntactic and code change dependency perspectives to support bug localization.

We propose to study the generation of descriptions from source code changes by integrating the messages included on code commits and the intra-code documentation inside the source in the form of docstrings.Our hypothesis is that although both types of descriptions are not directly aligned in semantic terms -one explaining a change and the other the actual functionality of the code being modified-there could be certain common ground that is useful for the generation.To this end, we propose an architecture that uses the source codedocstring relationship to guide the description generation.We discuss the results of the approach comparing against a baseline based on a sequence-to-sequence model, using standard automatic natural language generation metrics as well as with a human study, thus offering a comprehensive view of the feasibility of the approach.

Given the heterogeneity of the data that can be extracted from the software development process, defect prediction techniques have focused on associating different sources of data with the introduction of faulty code, usually relying on handcrafted features. While these efforts have generated considerable progress over the years, little attention has been given to the fact that the performance of any predictive model depends heavily on the representation of the data used, and that different representations can lead to different results. We consider this a relevant problem, as it could be affecting directly the efforts towards generating safer software systems. Therefore, we propose to study the impact of the representation of the data in defect prediction models. To this end, we focus on the use of developer activity data, from which we structure dependency graphs. Then, instead of manually generating features, such as network metrics, we propose two models inspired by recent advances in representation learning which are able to automatically generate feature representations from graph data. These new representations are compared against manually crafted features for defect prediction in real world software projects. Our results show that automatically learned features are competitive, reaching increments in prediction performance up to 13%.

We propose an encoder-decoder neural architecture to model user session and intent using browsing and purchasing data from a large e-commerce company.