Artificial intelligence solutions for financial data analysis

In the chat that took place last Friday at the ABANCA Seguros Auditorium in A Coruña, I explained how we use natural language processing (NLP) and machine learning (ML) techniques in our different projects to analyze large amounts of data and generate valuable information. for a wide variety of financial services.

Table of Contents

As always, I wanted to value the 8 years that we have been working for top-level entities, such as Banco Santander, EVO Banco, Bankinter, NN, among others. The use of ML techniques has allowed us to be leaders in the categorization of transactional data in Spain and there are already 3 published research papers, in addition to having collaborated with the AttlanTiC group from the University of Vigo.

Óscar Barba

Co-founder, CTO of Coinscrap Finance and SenseiZero

Artificial intelligence: history and current situation

The day’s agenda began with a tour of the trajectory of AI to the present day. We were able to learn about the R&D cycle of this technology: expectations, investment, scientific research and, finally, sectoral developments and applied results. And it is that, since the Darmouth Conference in 1956 –where the scientist John McCarthy used the term for the first time– we have discovered a multitude of applications and, currently, the need for a regulation that controls its legal and social repercussions is imposed.

Google trends IA

Google queries on the subject “artificial intelligence” continue an unstoppable escalation and the media flood us with all kinds of news about it. It is important to highlight that Spain’s strategy in terms of its application refers to its enormous potential for transformation from a technological and economic point of view. To close this part of the talk, I analyzed the Artificial Intelligence Index Report 2022 from Stanford University. As can be seen in the link, academic interest and private investment have skyrocketed in recent years.

New call-to-action

Data: The origin of everything

Data-Driven Companies (DDC) use artificial intelligence (AI) to make the most of data. AI processes large volumes of data, discovers hidden patterns and provides information for decision making. These companies automate tasks, improve the customer experience, and gain a competitive advantage in today’s marketplace. The combination of DDC and AI drives business success by making data-driven decisions and adapting to a dynamic business environment.

But… How can you discover which data is the most interesting for your entity? It has been shown that the collection of information about the process of creating products and services, the improvement of the different points of contact with the user and the personal data of the end customer are the most useful for banks and insurers. To understand it, what the AI does with them is: understand them, interpret them, reason about them and learn for future interactions.

The reality is that the current state of artificial intelligence has been fostered by Big Data. People and machines carry out daily activities that leave a digital trace that can be analyzed. This data is so massive and complex that it requires non-traditional computer applications to decipher it. And all this translates to the financial sector with natural language processing applications that understand human language and correctly respond to questions posed by users.

Here is an article on how banks are already applying artificial intelligence.

Use cases

We currently perform a contextual analysis that allows us to establish sentiment indicators. We automatically tag each news item with topics that include entities, relevant public figures, and event categories. Thousands of entities, people, geographic locations, products, and services can be recognized. Our personalized categorization also allows you to discover events that may influence the price of a share. These are some of the applications of natural language processing (NLP) by banks:

  • Analysis of market sentiment on the stock market.
  • PBC and AML automation from digital sources.
  • Classification and analysis of documents.
  • Unstructured feedback categorization.
  • Automatic generation of responses (intelligent chatbots).

In addition, NLP can help in the process of investing in the stock market in several ways. On the one hand, it makes it possible to analyze large amounts of data from the media and social networks to understand how investors and the general public perceive a company or sector. It also automatically extracts relevant information from news and financial documents. Detect and follow relevant events, news that could have a significant impact on the financial markets and automatically notify investors.

It is able to analyze trends to understand market preferences, allowing investors to make informed decisions about which stocks to buy or sell.

Artificial intelligence in the future

The media do not stop echoing prohibitions by companies and countries to use Chat GPT. The legal framework proposed by the EU, still under study, includes four levels of risk: unacceptable, high, limited and minimal. Several of these levels will require rigorous testing, documentation of data quality, and human oversight.

“To be truly successful, AI deployment must be done responsibly. That is why
lawyers and technologists must operate as strategic allies for the business.”

Eva Garcia San Luis. Partner of KPMG Lighthouse in Spain.

Given a future that is as promising as it is uncertain, collaboration between the legal departments of the entities and the IT areas of the FinTechs is necessary. In this way we can guarantee that we are building a truly responsible, traceable and reliable AI for society.

New call-to-action

About the Autor

Óscar Barba is co-founder and CTO of Coinscrap Finance and SenseiZero. He is an expert Scrum Manager with more than 6 years of experience in the collection and semantic analysis of data in the financial sector, classification of bank transactions, deep learning applied to stock market sentiment analysis systems and the measurement of the carbon footprint associated with transactional data. 

With extensive experience in the banking and insurance sector, Óscar is finishing his PhD in Information Technology right now. He is an Engineer and Master in Computer Engineering from the University of Vigo and Master in Electronic Commerce from the University of Salamanca. In addition, Scrum Manager and Project Management Certificate from the CNTG, SOA Architecture and Web Services Certificate from the University of Salamanca and more.

Sign up for our newsletter and get our top stories delivered straight to your inbox