Banks have been in the business of deciding who is eligible for credit for centuries. But in the age of artificial intelligence (AI), machine learning (ML), and big data, digital technologies have the potential to transform credit allocation in positive as well as negative directions. Given the mix of possible societal ramifications, policymakers must consider what practices are and are not permissible and what legal and regulatory structures are necessary to protect consumers against unfair or discriminatory lending practices. In this paper, I review the history of credit and the risks of discriminatory practices. I discuss how AI alters the dynamics of credit denials and what policymakers and banking officials can do to safeguard consumer lending.
A recent research study shows that artificial intelligence is going to help financial institutions save $1 trillion in project cost savings. According to some stats by Accenture, AI will add $1.2 trillion in value to the financial industry by 2035. Download our free e-book to learn everything you need to know about chatbots for your business. Here are a few key aspects of the banking industry AI can improve. Even though financial institutions already use the latest technologies to make their jobs safer and simpler, their employees still need to handle loads of paperwork daily.
I previously worked on designing some problem sets for a PhD class. One of the assignments dealt with a simple classification problem using data that I took from a kaggle challenge trying to predict fraudulent credit card transactions. The goal of the problem is to predict the probability that a specific credit card transaction is fraudulent. One unforeseen issue with the data was that the unconditional probability that a single credit card transaction is fraudulent is very small. This type of data is known as rare events data, and is common in many areas such as disease detection, conflict prediction and, of course, fraud detection.
Discover how to build a custom credit decision engines, including business rules and machine learning, that can plugged in to your loan origination software. In this video, Product Manager James Marsh walks us through how to create a model to automatically decision and price student loan refinance offers, without writing code. The model uses application data, credit bureau data, and custom credit variables to automate lending decisions. Additionally, leveraging out of the box machine learning algorithms and historical data, the model predicts which offers each applicant is most likely to be interested in, allowing lenders to prioritize offers with higher conversion rates and close more deals. With Modelshop, teams with different levels of technical expertise can create up-selling and cross-selling opportunities by predicting new products that customers are likely to be interested in buying.
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. Read on to learn how else AI is transforming the way banks operate, from investment assistance and consumer lending to credit scoring, smart contracts and more.
Watchdogs ask EC to delay repo haircut floors. It should come as no surprise that credit card companies supplement their revenues by selling real-time access to consumer transaction data – albeit aggregated and anonymised – and even less of a surprise that enterprising hedge funds have found a way to monetise it. This week, Risk.net reported how scrutinising data from millions of credit card transactions allowed a quant team to infer whether a company's sales are on the up or trending lower – without the need to wait for quarterly sales reports to be published. The analysis was delivered through a machine learning implementation of the random forest technique in which multitudes of decision trees combine to produce predictions. In this case, the algorithm enabled the quant shop to get an early warning on the health of companies whose options it held.
Singapore's digital national trade platform has launched Tradeteq's AI-based credit scoring system to enable its users to better assess counterparty risk in trade deals. The system is being used to leverage various data sources to provide thorough credit reports for users of Singapore's Networked Trade Platform (NTP), including data on each company in the supply chain as well as each receivable. The NTP is a digital national trade information management system backed by the Singaporean government, which aims to make trade flowing through Singapore more efficient. Launched in September last year, the NTP brings the entire trade ecosystem to a single online location, digitising the trade processing process. It replaced two existing trade facilitation platforms in Singapore, TradeXchange and TradeNet.
Credit scoring models support loan approval decisions in the financial services industry. Lenders train these models on data from previously granted credit applications, where the borrowers' repayment behavior has been observed. This approach creates sample bias. The scoring model (i.e., classifier) is trained on accepted cases only. Applying the resulting model to screen credit applications from the population of all borrowers degrades model performance. Reject inference comprises techniques to overcome sampling bias through assigning labels to rejected cases. The paper makes two contributions. First, we propose a self-learning framework for reject inference. The framework is geared toward real-world credit scoring requirements through considering distinct training regimes for iterative labeling and model training. Second, we introduce a new measure to assess the effectiveness of reject inference strategies. Our measure leverages domain knowledge to avoid artificial labeling of rejected cases during strategy evaluation. We demonstrate this approach to offer a robust and operational assessment of reject inference strategies. Experiments on a real-world credit scoring data set confirm the superiority of the adjusted self-learning framework over regular self-learning and previous reject inference strategies. We also find strong evidence in favor of the proposed evaluation measure assessing reject inference strategies more reliably, raising the performance of the eventual credit scoring model.
Conversion of raw data into insights and knowledge requires substantial amounts of effort from data scientists. Despite breathtaking advances in Machine Learning (ML) and Artificial Intelligence (AI), data scientists still spend the majority of their effort in understanding and then preparing the raw data for ML/AI. The effort is often manual and ad hoc, and requires some level of domain knowledge. The complexity of the effort increases dramatically when data diversity, both in form and context, increases. In this paper, we introduce our solution, Augmented Data Science (ADS), towards addressing this "human bottleneck" in creating value from diverse datasets. ADS is a data-driven approach and relies on statistics and ML to extract insights from any data set in a domain-agnostic way to facilitate the data science process. Key features of ADS are the replacement of rudimentary data exploration and processing steps with automation and the augmentation of data scientist judgment with automatically-generated insights. We present building blocks of our end-to-end solution and provide a case study to exemplify its capabilities.
Powered by our patented machine learning and artificial intelligence technology, the Trust Science SIX SCORE platform combines traditional and alternative data with consent-based mobile and social data to deliver in depth and dynamic analytics models and scores like Credit Bureau 2.0 . Trust Science uses patented algorithms to analyze publicly available digital information. We collect data from social media, news sources, court data, web search, transactions and more. Using sophisticated mathematical models, we process this data to then determine the trustworthiness of individuals, business and organizations.