A new global Fintech index and its application to optimum policy generation based on reinforcement learning

The merger of technological applications with finance has taken its place in the literature as Financial Technology (Fintech) starting from the 1990s, although it has become more frequent especially after the 2008 Global Financial Crisis (GFC). Fintech, as the name suggests, is the fusion of finance and technology. It is known that technology has always affected the finance industry and changed the way it works. For example, the introduction of Autometed Teller Machine (ATM), money transfer systems and the increase in productivity emerged with these developments in the financial sector have been inevitable. The question is, what makes the current Fintech revolution different from other periods? First, the testing and introduction of new technologies into financial markets has never been so rapid before. Another important point is that the impact of today's development is not only on the financial markets, but also on the economy as a whole, as new start-ups and large technology companies create competition outside the financial sector with the financial products they develop, creating an exogenous effect on the entire economy. Today's Fintech concept has transcended the financial market and has become the focus of entrepreneurs from different sectors. For this reason, the impact of Fintech on the economies and growth of countries is a topic that needs to be researched more than ever. With all this, Fintech promotes participation in financial markets around the world, enabling millions of people and businesses to participate in the global economy. Access to financial services is critical for global development as it facilitates investment in health, education and business. Concordantly, within the scope of this thesis, it is aimed to create a composite indicator representing Fintech development of countries by using the prominent determinants of it and to provide guidance to policy makers by revealing the policies recommended to be followed in order to come to the forefront in this field on a country-specific basis. In this direction, firstly, a composite indicator was created by detecting the determinants of Fintech and then, using the indicator scores, policy recommendations were made for each country with the help of Reinforcement Learning (RL). Keywords: Fintech, Composite Indicator, Reinforcement Learning, Determinants of Fintech, Global Fintech Index (GFI)