Graph Databases and their application to financial problems

Abstract

Over the past 20 years, Artificial Intelligence (AI) techniques were developed and widely used in many fields. AI refers to intelligent systems with various levels of autonomy that can predict, recommend or make decisions about anthropocentric goals. These techniques are based on use of large amounts of alternative data and "big data" analyzes for training machine learning (ML) models that improve predictability and performance automatically. These technologies offer competitive advantages, improving efficiency, increasing productivity, and improving it quality of services and products. In this thesis, cases are examined use of graphs in the field of economy, such as monitoring customer experience, h compliance management, and data analysis to address financials crimes. The goal is the effective utilization of information from financial news, stored in a graph, for advanced searches and analyses. Finally, a graph implementation and evaluation, incl statistics and machine learning models for binary classification.