VIETNAM - Room 801 No.41, Street 41 Thao Dien Ward,


How Data Science is Used in Fintech

August 16, 2019



Financial Technologies well known as Fintech is defined as any technological innovation in financial services including widely available payment apps or more complex software applications such as artificial intelligence and big data. This industry has strongly developed in recent years with $17.4 billion investment received in 2016 only. Due to the requirement of flexible data management structures to facilitate future analytics, fintech companies depend heavily on machine learning, artificial intelligence, predictive analytics and data science. Here below are some examples where data science is applied in Fintech industries.





On the contrast of tradition human advisers, robo-advisors are automated investment services that uses algorithms based on information collected from client’s profile such as financial status, risk capacity and future financial goals in order to estimate expected return, risk tolerance and then provide financial advice which instruments and asset classes best suited for client’s needs and goals. Robo-advisors can efficiently provide advice to client without the conflict of interest or any behavioral biases as what found in traditional financial advisors. Moreover, this method is typically less expensive than human advisers so it is much more suitable for investors who just get started.



Risk Analysis


Credit card or credit scoring companies such as the BIG 3 including Standard & Poor’s (S&P), Moody’s and Fitch Group rely on data science and machine learning to provide instant data analysis on borrowers. They use logistic regression through large volumes of collected data from structured databases such as customer or transaction records to predict the risk of customers by score rating separating good borrowers from bad ones.


Fraud Detection


Traditionally, fraud identification in transaction has to be set manually along with the rules for flagging a fraudulent transaction. But today, thanks to big data and data analytics techniques, this process can be done automatically. Taking the credit card payment fraud detection as an example, the classification problem involves creating a models and technique that have enough intelligence in order to help us flag or predict fraud in future transaction based on vast amounts of online fraudulent transaction through the leverage of big data. Therefore, it can properly classify transactions as either legit or fraudulent based on transaction details such as amount, merchant, location or time.  





For further info, you can meet us, call us, message us or take a look at our website


Talk to you soon!



Created in 2017, DRIVE is a digital performance company providing clients with a data-driven business strategy, powered by skilled talents, reliable data, and scalable technology system. Certified on major analytics and conversion solutions such as Google Analytics, Salesforce, Tableau and Adobe Analytics, we combine our expertise to meet your business expectations.


Please reload

Our Recent Posts

Metabase vs Tableau

October 16, 2019

5 Marketing trends applied to dominate e-commerce market

September 12, 2019

Build vs. Buy: What is best for your project?

September 6, 2019

Please reload