How are advances in artificial intelligence and machine learning changing credit risk assessment? That's a topic I'll be exploring in three presentations at FICO World 2018, April 16-19 in Miami Beach. These three presentations have a common thread: How FICO applies artificial intelligence and machine learning not as a "silver bullet" but carefully balanced with human domain expertise in the formulation of problems and models. FICO Scores are among the most scrutinized models in the world, so would you expect modern machine learning -- with its challenges around explainability -- to bring great benefits to FICO Score R&D and production? On Tuesday, April 17, 1:30-2:30, my colleague Ethan Dornhelm and I will show that machine learning offers tremendous efficiencies for research "in the lab".
This week, Silicon Valley-based Harvesting Inc launched an Artificial Intelligence (AI)-backed platform that uses satellite images of farms to gauge credit risk for banks that lend to farmers. The technology can be used to capture data on farms in the developing world as well as in mature markets like the US. Harvesting Inc generates "credit scorecards" using satellite imagery of farms and other data points, already in the works in the African market. "Think of us as someone who calculates the language of agriculture [into] the language of finance," Garg said. Garg told deBanked that because small farmers in emerging markets don't have credit cards, let alone smartphones, they have no credit history and their creditworthiness can't be evaluated through a traditional Western banking system.
Approaches to risk assessment and management are changing with the introduction of machine learning, but is finance ready for the changes? There has been a radical alteration in the nature of risk in many sectors, in that the biggest threat that many companies now face is from disruption of their business model by start-ups. This has meant that traditional approaches to risk--the appointment of a risk officer, and identification of individual risks to be mitigated--are no longer sufficient. Risk now requires a whole-company approach. In the financial services sector, however, 'risk assessment and management' still largely means assessing and managing individual credit risks.
Credit risk or credit default indicates the probability of non-repayment of bank financial services that have been given to the customers. Credit risk has always been an extensively studied area in bank lending decisions. Credit risk plays a crucial role for banks and financial institutions, especially for commercial banks and it is always difficult to interpret and manage. Due to the advancements in technology, banks have managed to reduce the costs, in order to develop robust and sophisticated systems and models to predict and manage credit risk. To predict the credit default, several methods have been created and proposed.
"AI is the most important issue shaping society," said veteran venture investor Ted Dintersmith. Our new paper on the implications of artificial intelligence concluded, "Code that learns will prove to be humankind's greatest invention." Concerned that the country wasn't mobilizing for the automation economy, Ted left his fund, and produced a movie, Most Likely to Succeed, to name the problem. He visited all 50 states hosting conversations about what's happening, what it means, and how to prepare. "If we don't address the problem, we'll have a lot of angry, alienated people on our hands.
Intelligent Mortgage Loan Approvals Imagine technology that pulls third-party data to verify applicant's identity, determines whether the bank can offer pre-approval on the basis of a partial application, estimates property value, creates document files for title validation and flood certificate searches, determines loan terms on the basis on risk scoring, develops a strategy to improve conversation, provides real-time text and voice support via chatbot. Imagine software that calculates mortgage risk based on wide range of loan-level characteristics at origination (credit score, loan-to-value ratio, product type and features), as well as a number of variables describing loan performance (e.g., number of times delinquent in past year), several time-varying factors that describe the economic conditions a borrower faces, including both local variables such as housing prices, average incomes, and foreclosure rates at the zip code level, as well as national-level variables such as mortgage rates. When uncharacteristic transactions occur, an alert is generated indicating the possibility of fraud. Credit Risk Management Imagine software that allows for more accurate, instant credit decisions by analyzing news and business networks. This system can also be used to improve Early Warning Systems (EWS) and to provide mitigation recommendations.
Companies can develop and test new products--for example, through digitally enabled simulations, 3D printed prototypes, or minimally viable products released in the actual marketplace--much faster and more cheaply than ever before. Plenty of digital disruptors began with a beta test, among them Airbnb, Spotify, and Zappos.
The release goes on, "NVIDIA DRIVE provides a holistic safety platform that includes process, technologies and simulation systems, as described below: (1) Process: Sets out the steps for establishing a pervasive safety methodology for the design, management and documentation of the self-driving system. These include NVIDIA-designed IP related to NVIDIA Xavier covering CPU and GPU processors, deep learning accelerator, image processing ISP, computer vision PVA, and video processors – all at the highest quality and safety standards. Included are lockstep processing and error-correcting code on memory and buses, with built-in testing capabilities. The ASIL-C NVIDIA DRIVE Xavier processor and ASIL-D rated safety microcontroller with appropriate safety logic can achieve the highest system ASIL-D rating."