Artificial Intelligence (AI) and Machine Learning (ML) techniques are creating waves within the financial services landscape. The banking industry, which relies heavily on the use of data, is increasingly starting to adopt these techniques and has started to leverage their powerful capabilities.
From chatbots to fraud detection, the banking sector is using AI and ML not only to automate processes and streamline operations for both the front and back offices, but also to enhance the overall customer experience. AI and ML tools, with their advanced prediction techniques and capabilities to utilize large volumes of data, are increasingly being used in Risk Management for quicker and more efficient credit, investment and business related decision making. The transformative power of this technology has been outlined below with respect to applications, key benefits and use cases:
Applications and key benefits
Artificial intelligence is being increasingly recognized across industries for its potential to significantly transform the day-to-day activities of a business. In risk management, AI/ML has become synonymous with improving efficiency and productivity while reducing costs. This has been possible due to the technologies’ ability to handle and analyze large volumes of unstructured data at faster speeds with considerably lower degrees of human intervention. The technology has also enabled banks and financial institutions to lower operational, regulatory, and compliance costs while simultaneously providing banks with accurate credit decision making capabilities.
AI/ML solutions are therefore able to generate large amounts of timely, accurate data, allowing financial institutions to build competence around customer intelligence, enabling the successful implementation of strategies and lowering potential losses.
AI/ML powered risk management solutions can also be used for model risk management (back-testing and model validation) and stress testing, as required by global prudential regulators, and may have the following key benefits:
a) Superior forecasting accuracy:
Traditional regression models do not adequately capture non-linear relationships between the macro economy and the financials of a company, especially in the event of a stressed scenario. Machine learning offers improved forecasting accuracy due to models’ ability to capture nonlinear effects between scenario variables and risk factors.
b) Optimized variable selection process
Feature/variable extraction processes take up a significant amount of time for risk models used for internal decision-making purposes. ML algorithms augmented with Big Data analytics platforms can process huge volumes of data and extract multiple variables. A rich feature set with a wide coverage of risk factors can lead to robust, data-driven risk models for stress testing.
c) Richer data segmentation
Appropriate granularity and segmentation are critical to deal with changing portfolio composition. ML algorithms enable superior segmentation and consider many attributes of segment data. By using unsupervised ML algorithms, combining both distance and density based approaches for clustering becomes a possibility, resulting in higher modelling accuracy and explanatory power.
Use cases
a) Credit risk modelling
Banks traditionally use traditional credit risk models to predict categorical, continuous or binary outcome variables (default/non default), as ML models are difficult to interpret and are not easily verifiable for regulatory purposes. Nevertheless, they can still be used to optimize parameters and improve the variable selection process in existing regulatory models.
AI based decision tree techniques can result in easily traceable and logical decision rules despite having non linear characters. Unsupervised learning techniques can be used to explore the data for traditional credit risk modelling while classification methods such as support vector machines can predict key credit risk characteristics such as PD or LGD for loans.
Financial services firms are also increasingly hiring external consultants who use deep learning methods to develop their revenue forecasting models under stress scenarios.
b) Fraud detection
Banks have been using machine learning methodologies for credit card portfolios for years, with credit card transactions presenting banks with a rich source of data on which to process and train unsupervised learning algorithms on. These algorithms have historically been highly accurate in predicting credit card fraud due to models’ availability to develop, train and validate huge volumes of data.
Credit card payment systems are embedded with workflow engines that monitor card transactions to assess the likelihood of fraud. The rich transaction history available for credit card portfolios present banks with the ability to distinguish between specific features present in fraudulent and non fraudulent transactions.
c) Trader behavior
Technologies such as natural language processing and text mining are increasingly being used to monitor trader activity for rogue trading, insider trading and market manipulation.
By analyzing email traffic and calendar related data, check in/check out times, and call times combined with trading portfolio data, systems are able to predict the probability of trader misconduct, saving millions in reputational and market risk for financial institutions.
