Risk and data science specialist Jaywing, has launched Archetype, a new risk technology product that uses Artificial Intelligence (AI), machine learning and deep neural nets to help lenders generate transparent statistical models and predict almost any outcome on almost any data set.
Archetype uses true AI to generate more powerful models, significantly reducing the time and effort needed to create them. It affords lenders the opportunity to fully redevelop models the moment they begin to deteriorate, without incurring the resource costs typically associated with model redevelopment. Archetype also overcomes transparency concerns that have until now hindered the use of AI in credit scoring.
Archetype uses deep neural networks, an advanced predictive modelling methodology and an intuitive user interface to create models that will radically improve the interpretability and predictability of the AI-driven scoring process. Archetype’s AI processing engine uses insights from deep within the data to generate its models, using techniques that far outstrip the capability of standard modelling tools. This typically drives up predictive power, resulting in greater risk or fraud detection at a lower cost, given the same data inputs.
Organisations looking to make their first steps into AI-based modelling can make use of Archetype supported by Jaywing’s consultants, or sign up to use the product themselves through an easily-accessible web-based interface.
The potential for the application of Archetype goes beyond risk and fraud detection as it can be used to model almost any outcome on almost any data set, whether that’s in credit risk, collections, fraud or marketing propensity.
Ben O’Brien, Managing Director, Jaywing said: “We’ve been able to capitalise on almost twenty years of risk, financial services and data science heritage to create an enhanced AI solution for the financial services sector. The development of Archetype, on the back of advances in processing power and algorithmic improvements, solves one of the issues that was preventing the mass adoption of AI in credit scoring: how to build models that can be understood and agreed by the business, whilst maximising their predictive power. Initial comparative tests of Archetype against an already strong fraud model have shown an uplift in the order of 10 points. With Archetype, lenders can harness the potential of machine learning and AI to drastically reduce manual model development, mitigate risks, improve their speed to market with new models and squeeze vastly more insight from data. We are very excited about the potential for Archetype to transform all aspects of risk and fraud.”
Rob Shaw, CEO, Jaywing adds: “Jaywing has already set the standard in risk and data science in our industry and we are excited about the next stage in our ambitious strategy. We have now brought new algorithmic and expert knowledge on machine learning and AI to further optimise risk management, regulations and operational control while freeing resource to focus on other value-adding tasks.
“As the sophistication of Artificial Intelligence and machine learning, and the availability of data grows, it’s critical that lenders are supported by people with the right data skills. This combination of new technology and expertise will be key to how the lending landscape evolves over the next five years.”