Thousands of data sources exist nowadays from which we can extract, transform and load data ranging stock prices, medical records, surveys, population census, and logged behaviors, among others. Also, there's a huge variety of fields in which we can apply these techniques and a wide range of useful applications inside each field, such as fraud detection, credit scoring and asset allocation in relation to the finance domain. But how much can I contribute with this knowledge to a company? A LOT! Just put yourself in the situation of a credit risk analyst at a bank. "Should I lend money to this client or should I reject his application? How much information should I request him or her without risking to lose the interest rate associated with the lending? Are his periodical payslips enough? Or should I also ask him credit records from other financial institutions to guarantee the repayment?".
Though banks don't create AI strategies, they are increasingly using artificial intelligence and machine learning in their day-to-day business. We frequently work with them on ideation workshops, PoC, and solution implementation. Santander Consumer Bank, for example, is running workshops and researching how to use machine learning to boost the sustainability of loan portfolios. Besides credit risk modeling, there is already an impressive range of use cases for AI in banking. It covers everything, from customer service to back-office operations.
TrackStar.ai, a company led by credit industry veterans that specializes in predictive credit technology, today announced the launch of a new proprietary, predictive API designed to help lending institutions determine consumer lending potential. By utilizing this first-of-its-kind API, lenders are able to make better decisions about qualifying current and prior loan applicants. The result is lower acquisition costs and churn, all while reducing lender's reliance on outside partnerships for leads. TrackStar's API is designed for enterprise level banking institutions and lenders to help them optimize the customer acquisition and retention process. TrackStar's predictive AI layer determines which negative credit items could be removed from a customer's credit history, allowing lenders to extend offers to customers who might normally get declined or not even considered as qualifying loan applicants.
GlobalData has revealed that the number of gig workers has increased in the world's largest economies, prompting lender curiosity about expanding their access to credit. Gig workers who previously struggled in the lending ecosystem due to their temporary, freelance jobs wanting steady pay cheques could now utilise artificial intelligence (AI) to convert them into creditworthy borrowers, by using alternative data. Kiran Raj, Principal Disruptive Tech Analyst at GlobalData, noted that traditional credit scoring models, such as FICO, are inherently flawed in accessing thin credit files due to their assessment of only a handful of standard data variables. Raj acknowledged that this leads to lenders reeling under pressure to make more inclusive credit decisions in real time. "This is where fintech start-ups have come into action with their AI credit scoring models almost instantly interpreting alternative data like historical payments, digital footprint and behavioural economics," Raj said.
As the Managing Director-Technology and Head of NY/Canada Business Unit at Synechron, Ravnit is currently responsible for leading multiple global client relationships, driving business development and sales, IT Strategy and consulting, execution and delivery, P&L and program management for strategic financial clients. In addition, a vital part of his role is providing thought leadership around the impact of emerging technologies (particularly AI/Machine Learning/RPA) on the financial industry. He is a key contributor to Synechron's Accelerator programs, leveraging emerging technologies to address key business challenges in the BFSI space. Ravnit has significant techno-functional hands-on experience as well as a proven track record for execution and delivery of IT Solutions in capital markets and wealth management functions across asset classes, lines of businesses and front-/mid-/back-office functions. Prior to Synechron, Ravnit was a Senior Developer at Polaris Consulting & Services Limited.
When observation in one class is higher than the observation in other classes then there exists a class imbalance. Example: To detect fraudulent credit card transactions. As you can see in the below graph fraudulent transaction is around 400 when compared with non-fraudulent transaction around 90000. Class Imbalance is a common problem in machine learning, especially in classification problems. Imbalance data can hamper our model accuracy big time.
If a ML system uses gender information in credit scoring, then gender information is probably relevant for credit scoring. We all know that women, for example, are more risk averse than men on average and that there are more men with very low IQ's; and more men take part in dangerous activities than can maim them. All those things contribute to credit risk. I looked at some actuarial motorcycle accident data from a Swedish insurance company a couple of years ago, and the accident rate of young men (18-25 maybe) was something like 40 times higher than women in the same age interval. Of course, EU law requires us to offer the same rate to men and women, so we have to ignore this; and thus the women pay more than they should if things were fair.
With plenty of post-recession anti-banking sentiment still lingering, it's common to see fintech and traditional banks framed in oppositional terms. There's some truth to that, especially with disruption-minded digital-only banks, but technological innovations have transformed banking of all stripes -- and nowhere is that clearer than with artificial intelligence. AI has impacted every banking "office" -- front, middle and back. That means even if you know nothing about the way your financial institution uses, say, complex machine learning to fend off money launderers or sift through mountains of data for fraud-related anomalies, you've probably at least interacted with its customer service chatbot, which runs on AI. Like fabric softener and football, banks -- or at least banks as physical spaces -- have been cited as yet another industry that's being killed by those murderous Millennials.
Which algorithms should be used to build a model that addresses and solves a classification problem? When it comes to classification, we have quite a handful of different algorithms to use unlike regression. To name some, Logistic Regression, K-Neighbors, SVC, Decision Tree and Random Forest are the top common and widely used algorithms to solve such problems. Here's a quick recap of what each algorithm does and how it distinguishes itself from the others: Let's see how they work with our dataset compared to one another: After importing the algorithms from sklearn, I created a dictionary which combines all algorithms into one place, so that it's easier to apply them on the data at once, without the need to manually iterate each individually. After applying the algorithms on both train and test sets, it seems that Logistic Regression doesn't work well for the dataset as the scores are relatively low (around 50%, which indicates that the model is not able to classify the target).
Mitsubishi UFJ Financial Group (MUFG) has partnered with Israeli fintech Liquidity Capital to create a joint venture (JV) to offer debt financing for Asia-Pacific start-ups. Named Mars Growth Capital and based in Singapore, the JV's fund has an initial capital commitment of $80 million and is "expected" to power up this year. MUFG likes to splash the cash in the Asian region – and hedge its bets – as it was one of the names making a recent $850 million investment in Grab. In this latest move today (7 August), the Japanese bank explains: "In Asia Pacific, the advancement of digitalisation and smart technologies in the corporate arena has not only contributed to the rapid growth of start-ups but also the emergence of a business model within the financial services sector that is increasingly reliant on data analysis and artificial intelligence (AI) technology." Liquidity Capital was founded in 2018 and uses a credit scoring model based on AI technology and real-time financial and accounting data from client bank accounts, accounting systems and CRM information captured through its API to forecast future earnings and cash flow.