The banking industry, as with most industries, always deals with large data and detailed demography. Credit risk is one of the major financial challenges the banking industry is facing nowadays. Credit risk rating and the underwriting process is a hard and tedious routine which often requires a lot of information to be processed and scored by human labor. As McKinsey Global Institute described it in its 2018 survey titled AI adoption advances, but foundational barriers remain, ”Artificial intelligence is rapidly taking hold across global business and risk management is one of the functions from which organizations are deriving the most significant benefits.”
Develandoo AI Innovation Lab has recently developed a new banking product called Protogen AI. Armen Ghambaryan, lead Data Scientist of Develandoo and Chief Technical Officer of Protogen AI, describes how it works, the core idea of the product and the uniqueness of its solution.
Armen has been developing analytical systems based on state-of-the-art machine learning models for central banks. He holds a PhD degree in Economics. He sees a big promise in Protogen AI as it aims to unlock the full potential of financial data by building fast, accurate and interpretable predictive systems.
What is Protogen AI?
Protogen is a financial credit risk scoring system built on state-of-the-art machine learning techniques. The system aims at predicting the probability of customers defaulting with high accuracy and speed as well as providing post prediction analysis tools for the interpretation of the system’s workings. It takes into account social and open banking data to build credit history patterns including, a sentiment model for evaluating real-time customer relation status. It does this by having a recommender system that offers relevant cross and upsells suggestions, and it can be extended with behavioral models based on customer’s actions in real time.
How does it work?
It is split into 3 parts. Two satellite models that analyze the historical data corresponding to the client, and the main model that takes into account both predictions of satellites and the current application data of the client.
Why Protogen? What’s the essence of the solution?
Protogen is using modern machine learning algorithms that sequentially learn from their mistakes. For financial data that generally contains a lot of missing values and outliers, this is the best approach since, from one side advanced data imputation techniques are being used, from the other side the model can handle unbalanced datasets, which is a common case for credit default risk related data.
What are Protogen’s benefits?
With Protogen customers can obtain credit risk scores with higher accuracy and in a matter of seconds, compared to current state-of-the-art approaches. It also treats the model as something other than a black box, since Protogen provides model interpretation tool that helps customers understand its workings on the backend.
To know more about our latest AI product, visit here.
- Artificial Intelligence