1,720,974 research outputs found
Neither in the Programs Nor in the Data: Mining the Hidden Financial Knowledge with Knowledge Graphs and Reasoning
No full textVadalog is a logic-based reasoning language for modern AI solutions, in particular for Knowledge Graph (KG) systems. It is showing very effective applicability in the financial realm, with success stories in a vast range of scenarios, including: creditworthiness evaluation, analysis of company ownership and control, prevention of potential takeovers of strategic companies, prediction of hidden links between economic entities, detection of family businesses, smart anonymization of financial data, fraud detection and anti-money laundering. In this work, we first focus on the language itself, giving a self-contained and accessible introduction to Warded Datalog+/-, the formalism at the core of Vadalog, as well as to the Vadalog system, a state-of-the-art KG system. We show the essentials of logic-based reasoning in KGs and touch on recent advances where logical inference works in conjunction with the inductive methods of machine learning and data mining. Leveraging our experience with KGs in Banca d’Italia, we then focus on some relevant financial applications and explain how KGs enable the development of novel solutions, able to combine the knowledge mined from the data with the domain awareness of the business experts
Weaving enterprise knowledge graphs: The case of company ownership graphs∗
No full textMotivated by our experience in building the Enterprise Knowledge Graph of Italian companies for the Central Bank of Italy, in this paper we present an in-depth case analysis of company ownership graphs, graphs having company ownership as a central concept. In particular, we study and introduce three industrially relevant problems related to such graphs: company control, asset eligibility and detection of personal links. We formally characterize the problems and present Vada-Link, a framework based on state-of-the-art approaches for knowledge representation and reasoning. With our methodology and system, we solve the problems at hand in a scalable, model-independent and generalizable way. We illustrate the favourable architectural properties of Vada-Link and give experimental evaluation of the approach
Eliminating Harmful Joins in Warded Datalog+/−
No full textWe provide a rewriting technique of Warded Datalog+/− settings to sustain decidability and data tractability of reasoning tasks in the presence of existential quantification and recursion. To achieve this behaviour in practice, reasoners implement specialized strategies which exploit the theoretical bases of the language to control the effects of recursion, ensuring reasoning termination with small memory footprint. However, as a necessary condition for such exploitation, the setting is required to be in a “normalized form”, essentially without joins on variables affected by existential quantification. We present the Harmful Join Elimination, a normalization algorithm of Warded Datalog+/− that removes such “harmful” joins, supporting the tractability of the reasoning task as well as the full expressive power of the language. The algorithm is integrated in the Vadalog system, a Warded Datalog+/− -based reasoner that performs ontological reasoning in complex scenarios
iWarded: A Versatile Generator to Benchmark Warded Datalog plus /- Reasoning
No full textWarded Datalog+/- is a powerful member of the Datalog+/- family, which extends the logic language Datalog with existential quantification and provides full support for recursion. Such expressive power, paired with a promising trade-off with the offered data complexity, was the catalyst for the recent rise of the language as a relevant candidate for knowledge graph traversal and ontological reasoning applications. Despite the growing research and industrial interest towards Warded Datalog+/-, we observe a substantial lack of specific tools able to generate non-trivial settings and benchmark scenarios, essential to evaluate, analyze and compare reasoning systems over such tasks. In this paper, we aim at filling this gap by introducing iWarded, a versatile generator of Warded Datalog+/- benchmarks. Our system is able to efficiently create very large, complex, and realistic reasoning settings while providing extensive control over the theoretical underpinnings of the language. iWarded was developed and employed in the context of the Vadalog system, a state-of-the-art Warded Datalog+/-based reasoner
EXLEngine: executable schema mappings for statistical data processing
No full textData processing is the core of any statistical information system. Statisticians are interested in specifying transformations and manipulations of data at a high level, in terms of entities of statistical models such as time series. We illustrate here an experience at the Bank of Italy where (i) a language, EXL, has been defined for the declarative specification of statistical programs, (ii) an approach for the translation of EXL code into executables in various target systems has been developed, and (iii) a concrete implementation, EXLEngine, has been carried out. The approach leverages on schema mappings as an intermediate specification step, in order to facilitate the translation from EXL towards several target systems
- …
