Some mission critical systems, e.g., fraud detection, require accurate, real-time metrics over long time sliding windows on applications that demand high throughput and low latencies. As these applications need to run "forever" and cope with large, spiky data loads, they further require to be run in a distributed setting. We are unaware of any streaming system that provides all those properties. Instead, existing systems take large simplifications, such as implementing sliding windows as a fixed set of overlapping windows, jeopardizing metric accuracy (violating regulatory rules) or latency (breaching service agreements). In this paper, we propose Railgun, a fault-tolerant, elastic, and distributed streaming system supporting real-time sliding windows for scenarios requiring high loads and millisecond-level latencies. We benchmarked an initial prototype of Railgun using real data, showing significant lower latency than Flink and low memory usage independent of window size. Further, we show that Railgun scales nearly linearly, respecting our msec-level latencies at high percentiles (<250ms @ 99.9%) even under a load of 1 million events per second.

Payment card fraud causes multibillion dollar losses for banks and merchants worldwide, often fueling complex criminal activities. To address this, many real-time fraud detection systems use tree-based models, demanding complex feature engineering systems to efficiently enrich transactions with historical data while complying with millisecond-level latencies. In this work, we do not require those expensive features by using recurrent neural networks and treating payments as an interleaved sequence, where the history of each card is an unbounded, irregular sub-sequence. We present a complete RNN framework to detect fraud in real-time, proposing an efficient ML pipeline from preprocessing to deployment. We show that these feature-free, multi-sequence RNNs outperform state-of-the-art models saving millions of dollars in fraud detection and using fewer computational resources.

External Transaction Logic ( ETR ) is an extension of logic programming useful to reason about the behaviour of agents that have to operate in a transactional way, in a two-fold environment: an internal knowledge base defining the agent's internal knowledge and rules of behaviour, and an external world where it executes actions and interacts with other entities. Actions performed by the agent in the external world may fail, e.g. because their preconditions are not met, or because they violate some norm of the external environment. The failure to execute some action should lead, in the internal knowledge base, to its complete rollback, following the standard ACID transaction model used e.g. in databases. Since it is impossible to rollback external actions performed in the outside world, external consistency must be achieved by executing compensating operations (or repairs) that revert the effects of the initial executed actions. In ETR , repairs are stated explicitly in the program. With it, every performed external action is explicitly associated with its corresponding compensation or repair. Such user-defined repairs provide no guarantee to revert the effects of the original action. In this article, we define how ETR can be extended to automatically calculate compensations in case of failure. For this, we start by explaining how the semantics of Action Languages can be used to model the external domain of ETR , and how we can use it to reason about the reversals of actions.

Abstract Ontologies and rules are usually loosely coupled in knowledge representation formalisms. In fact, ontologies use open-world reasoning, while the leading semantics for rules use non-monotonic, closed-world reasoning. One exception is the tightly coupled framework of Minimal Knowledge and Negation as Failure (MKNF), which allows statements about individuals to be jointly derived via entailment from ontology and inferences from rules. Nonetheless, the practical usefulness of MKNF has not always been clear, although recent work has formalized a general resolution-based method for querying MKNF when rules are taken to have the well-founded semantics, and the ontology is modeled by a general oracle. That work leaves open what algorithms should be used to relate the entailments of the ontology and the inferences of rules. In this paper we provide such algorithms, and describe the implementation of a query-driven system, CDF-Rules, for hybrid knowledge bases combining both (non-monotonic) rules under the well-founded semantics and a (monotonic) ontology, represented by the Coherent Description Framework Type-1 ( $\mathcal{ALCQ}$ ) theory.