[Paper Review] NLP in FinTech Applications: Past, Present and Future

Chung-Chi Chen, Hen‐Hsen Huang+1 more|arXiv (Cornell University)|May 4, 2020

FinTech, Crowdfunding, Digital Finance34 references18 citations

TL;DR

This paper surveys the evolution of NLP in FinTech, focusing on KYC, KYP, and SYC applications using both formal and informal textual data. It proposes a framework for dynamic product feature updates from risk and prospect perspectives and outlines future research directions in open finance and NLP-driven financial innovation.

ABSTRACT

Financial Technology (FinTech) is one of the worldwide rapidly-rising topics in the past five years according to the statistics of FinTech from Google Trends. In this position paper, we focus on the researches applying natural language processing (NLP) technologies in the finance domain. Our goal is to indicate the position we are now and provide the blueprint for future researches. We go through the application scenarios from three aspects including Know Your Customer (KYC), Know Your Product (KYP), and Satisfy Your Customer (SYC). Both formal documents and informal textual data are analyzed to understand corporate customers and personal customers. Furthermore, we talk over how to dynamically update the features of products from the prospect and the risk points of view. Finally, we discuss satisfying the customers in both B2C and C2C business models. After summarizing the past and the recent challenges, we highlight several promising future research directions in the trend of FinTech and the open finance tendency.

Motivation & Objective

• To analyze the role of NLP in financial technology (FinTech) across key application domains such as KYC, KYP, and SYC.
• To examine how both structured documents and unstructured textual data are leveraged to understand corporate and personal customers.
• To propose a dynamic approach for updating product features based on risk and prospect evaluation.
• To explore customer satisfaction strategies in B2C and C2C FinTech business models using NLP.
• To identify and outline promising future research directions in NLP for FinTech amid the rise of open finance.

Proposed method

• Systematic review of NLP applications in FinTech, focusing on three pillars: Know Your Customer (KYC), Know Your Product (KYP), and Satisfy Your Customer (SYC).
• Integration of formal financial documents and informal textual data (e.g., social media, customer reviews) for customer profiling.
• Dynamic feature updating of financial products using NLP to assess risk and prospective value over time.
• Application of NLP techniques to extract sentiment, intent, and risk indicators from unstructured text in B2C and C2C contexts.
• Use of contextual embeddings and sequence modeling to improve understanding of financial narratives and customer behavior.
• Framework design for aligning NLP-driven insights with regulatory and business objectives in open finance ecosystems.

Experimental results

Research questions

• RQ1 How has NLP been applied in KYC processes to improve customer onboarding and compliance?
• RQ2 In what ways can NLP extract actionable insights from unstructured data to support KYP and product risk assessment?
• RQ3 How can NLP enhance customer satisfaction in both B2C and C2C FinTech models through personalized services?
• RQ4 What are the key technical and regulatory challenges in dynamically updating financial product features using NLP?
• RQ5 What future research directions are most promising for NLP in the context of open finance and real-time financial data processing?

Key findings

• NLP has significantly enhanced KYC processes by enabling automated extraction of customer identity and risk data from diverse textual sources.
• Informal textual data such as customer reviews and social media content provide valuable signals for understanding customer sentiment and behavior.
• Dynamic product feature updates using NLP allow financial institutions to adapt to changing market conditions and risk profiles in real time.
• The integration of NLP in KYP enables more accurate and timely assessment of product suitability and risk exposure.
• Future research should focus on explainable NLP models, regulatory compliance, and interoperability in open finance ecosystems.
• The paper identifies a growing need for NLP systems that balance personalization with data privacy and security in FinTech applications.