Credit


How machine learning can help banks rate credit risk - AI News

#artificialintelligence

Credit risk is one of the major financial challenges that exist in the banking system. Yet, so far many lenders have been slow to fully utilise the predictive power of digitising risk. This is despite a recent report from McKinsey showing that machine learning may reduce credit losses by up to 10 per cent, with over half of risk managers expecting credit decision times to fall by 25 to 50 per cent. Traditional scorecards often make it easier to explain how a customer was scored to the customer and regulators alike. Traditional models tend to focus on borrowers' financials, categorising customers based on demographics, payment history, and other macroeconomic considerations.


Machine-learning algorithms are the future of credit scoring Billtrust

#artificialintelligence

In order to create credit scores that provide utility and value, Credit2b's scores are on a scale of 0-100, with each point on this scale representing the probability of a positive outcome for the score. Therefore, a score of 80 simply means that there is an 80% probability that the company will pay on time for example. Other ratings agency scores are described in either tiers or bands that often cause confusion for credit practitioners who need to make important decisions quickly. With the tiered approach, two very similar companies may be scored in separate bands with completely different interpretations due to the randomness of the bands, and the simplicity of their data analysis algorithms. Machine-learning solutions deal with continuum, and give our customers information they can process and use quickly.


Machine learning – will the credit risk industry adopt or die?

#artificialintelligence

Missing a lucrative opportunity can cost you dearly. Just ask the'almost investors' of Amazon. Back in the mid-90s, Jeff Bezos, the founder of the retail behemoth, approached family, friends and others for a $50,000 investment in his idea for an online book shop. Those that could who believed in the idea invested. Those that couldn't, according to Bezos, to this day find it painful to talk about anything Amazon related.The lesson to be learnt?


Artificial intelligence for real-world regulatory hurdles

#artificialintelligence

Perhaps you'll see this one coming like an angry regulator pacing up to the door. But if you wonder what federal mandates, a motorcycle, a baby boomer hairdresser and a blown business opportunity might have in common, read on. Our story of regulatory woe on the go begins with 60-year-old Geri Michael of Vero Beach, Florida. The hairdresser decided it was high time to treat herself to a Honda motorcycle. Her checklist was looking pretty good, too.


Profitable Bandits

arXiv.org Machine Learning

Originally motivated by default risk management applications, this paper investigates a novel problem, referred to as the profitable bandit problem here. At each step, an agent chooses a subset of the K possible actions. For each action chosen, she then receives the sum of a random number of rewards. Her objective is to maximize her cumulated earnings. We adapt and study three well-known strategies in this purpose, that were proved to be most efficient in other settings: kl-UCB, Bayes-UCB and Thompson Sampling. For each of them, we prove a finite time regret bound which, together with a lower bound we obtain as well, establishes asymptotic optimality. Our goal is also to compare these three strategies from a theoretical and empirical perspective both at the same time. We give simple, self-contained proofs that emphasize their similarities, as well as their differences. While both Bayesian strategies are automatically adapted to the geometry of information, the numerical experiments carried out show a slight advantage for Thompson Sampling in practice.


Controversy, thy name is Europe: Open credit scores, data-driven counter-forensics, and the regulation debate

ZDNet

Europe's SXSW: The analogy may give an idea of what Berlin's re:publica is to someone who has never attended. Berlin's re:publica started out in 2007, with 700 bloggers in attendance, and it has been growing ever since. Last week, in Berlin, there were more than 10.000 people attending a program spanning three days, 15 themes, and 18 stages. With speakers ranging from the likes of Microsoft and Google to government officials to counter-culture activists, re:publica is a mixed bag. Data, its use and misuse, was a recurring theme, and we picked some of the topics that spurred debate.


How Your Data Fingerprint Will Become As Important As Your Credit Score

#artificialintelligence

It's not just about the skills one carries with him. It's also about the data he carries with him too. Big data and artificial intelligence (AI) will make it so. Every dollar we earn, borrow, spend and save every day counts. The tracking of this goes on whether we're aware of it or not.


Fintech players rely on AI to build credit scores for disbursal of loans

#artificialintelligence

The burgeoning online lending segment in India is also giving rise to a new kind of challenge on sourcing credit score data. To solve this problem, several fintech companies are using Artificial Intelligence (AI) and Machine Learning (ML) to create alternate lending data score for more than 80 per cent of the Indian population who have no credit scores. From the place where people live to the restaurants they visit to their digital footprints on social media, ML captures it all. Mohan Yadav, a 25-year-old software professional in Mumbai, was denied a ₹25,000 personal loan by his bank since he had no credit history. After a quick search online, he applied for a loan from Cashe, a Mumbai-based fintech company that offers personal loans to salaried professionals who have just entered the workforce.


Fintech players rely on AI to build credit scores for disbursal of loans – Tech Check News

#artificialintelligence

The lack of credit details has led to the emergence of analytics start-ups that are working on ways to develop alternate data-based lending programs to offer personal loans Now, customers with no prior credit score can easily get loans Priyanka Pani The burgeoning online lending segment in India is also giving rise to a new kind of challenge on sourcing credit score data. To solve this problem, several fintech companies are using Artificial Intelligence (AI) and Machine Learning (ML) to create alternate lending data score for more than 80 per cent of the Indian population who have no credit scores. From the place where people live to the restaurants they visit to their digital footprints on social media, ML captures it all. Live data Mohan Yadav, a 25-year-old software professional in Mumbai, was denied a ₹25,000 personal loan by his bank since he had no credit history.


Credit risk prediction in an imbalanced social lending environment

arXiv.org Machine Learning

Credit risk prediction is an effective way of evaluating whether a potential borrower will repay a loan, particularly in peer-to-peer lending where class imbalance problems are prevalent. However, few credit risk prediction models for social lending consider imbalanced data and, further, the best resampling technique to use with imbalanced data is still controversial. In an attempt to address these problems, this paper presents an empirical comparison of various combinations of classifiers and resampling techniques within a novel risk assessment methodology that incorporates imbalanced data. The credit predictions from each combination are evaluated with a G-mean measure to avoid bias towards the majority class, which has not been considered in similar studies. The results reveal that combining random forest and random under-sampling may be an effective strategy for calculating the credit risk associated with loan applicants in social lending markets.