From Theory to Practice: Advances in Natural Language Processing for Financial Applications

Abstract

This thesis investigates the potential of Natural Language Processing (NLP) in the financial sector, with a specific emphasis on its accessibility and effectiveness for individual users and small companies operating with limited resources. It explores how NLP techniques can be developed and utilized to interpret financial discourse, offering insights into current capabilities and performance benchmarks achievable without extensive resources.

The research begins with an overview of fundamental NLP concepts, emphasizing their relevance in financial contexts. It then transitions into a practical guide, demonstrating how users with limited technical and financial resources can implement NLP solutions. This guide covers essential steps from data acquisition to analysis, showcasing scalable methods and tools.

The core of this thesis addresses the main research question: "How can NLP applications in finance be developed by an individual or a small company, and what level of performance is achievable without high-end resources?" Through this investigation, the thesis aims to demystify NLP applications in finance, making them accessible and practical for a wider range of users and organizations.