Tapping technology to bring speed, accuracy to credit risk modelling

Bharath Vellore

WITH all the disruption stemming from Covid-19 over the past two years, how sound are credit risk models? This was one of the questions we sought to answer with a global research study that surveyed 100 industry decision makers across Asia Pacific. The results were more than a little unsettling – only 16 per cent of fintech and financial services organisations believe their credit risk models are accurate at least 76 per cent of the time. 

This state of great uncertainty in credit risk modelling is exposing the shortcomings of legacy approaches for credit risk decision-making that leverage limited data, workflow and automation – and often in separate systems, to boot. To really level-up decision-making, organisations need more data, more automation, more sophisticated processes, more forward-looking predictions, and greater speed-to-decisioning. To this end, they need artificial intelligence (AI), machine learning, and alternative data. The Singapore government recognises the importance of AI and has invested S$180 million into a national AI programme for the finance industry. In collaboration with the Monetary Authority of Singapore (MAS) and the National AI Office (NAIO) at the Smart Nation and Digital Government Office (SNDGO), the programme seeks to implement AI in the financial sector for the benefit of improved customer service and risk management. 

Our survey underscored the growing appetite for AI predictive analytics and machine learning, data integration, and the use of alternative data as the means to improve credit risk analysis. Real-time credit risk analysis was the respondents’ Number 1 planned investment area in 2022, as organisations work to resolve today’s “financial fault line” in credit risk modelling. 

Financial services executives see AI-enabled risk decision-making as the cornerstone to improvements in many areas, including fraud prevention (91 per cent), automating decisions across the credit lifecycle (75 per cent), improving cost savings and operational efficiency (68 per cent) and more competitive pricing (60 per cent) .

However, many companies struggle with mounting the resources needed to support their AI initiatives -- it can take a long time to develop and implement AI. It can be prohibitively expensive, with only 7 per cent of financial services organisations beginning to see a return on investment from AI initiatives within 120 days. PWC’s Uncovering the Ground Truth: AI in Indian Financial Services reports that lack of integration is posing a challenge for AI to be fully adopted. Financial institutions in India are still reliant on legacy systems and because of the increase in data and variety, they can’t quite maximise the use of AI applications.

Sixty-five per cent of decision makers in our survey indicated that they recognise the importance of alternative data in credit risk analysis for improved fraud detection. Additionally, 46 per cent recognise its importance in supporting financial inclusion. Alternative data offers another way for lenders to detect fraud before it happens and to evaluate individuals with a thin (or no) credit file by putting together a more holistic, comprehensive view of an individual’s credit risk.

For unbanked and underbanked consumers, AI gives organisations the opportunity to support those consumers’ financial journeys. In India, the growth of unbanked and underbanked customers has increased significantly. Fintech firms like ANVI have built a digital platform using AI to support customers with financial accessibility. Financial services organisations typically struggle to help these consumers because they don’t come with a history of data that can be used in traditional analysis methods. However, because AI can identify patterns in a wide variety of alternative and traditional data, it can power highly accurate analysis, even for no-file or thin-file consumers. This vastly benefits those who can’t be easily scored via traditional credit analysis methods, while also benefitting financial institutions by expanding their total addressable market.

By deploying AI and machine learning technologies, as well as embracing alternative data, organisations are on their way to improved agility and confidence in credit risk modelling. In doing so, they will be more prepared to react to changes moving forward, while also supporting critical industry imperatives such as fraud prevention and inclusive finance. 

As organisations come to terms with stark inequalities over credit risks, AI and machine learning offers the power to resolve these challenges and provide seamless experiences for internal and external stakeholders. The era of AI is here – just in time for organisations to exploit the technology and move forward with better credit risk analysis.  

The writer is general manager, APAC, at Provenir