No abstract

In the recent years, data science methods have been developed considerably and have consequently found their way into many business processes in banking and finance. One example is the review and approval process of credit applications where they are employed with the aim to reduce rare but costly credit defaults in portfolios of loans. But there are challenges. Since defaults are rare events, it is—even with machine learning (ML) techniques—difficult to improve prediction accuracy and improvements are often marginal. Furthermore, while from an event prediction point of view, a non-default is the same as a default, from an economic point of view much more relevant to the end user it is not due to the high asymmetry in cost. Last, there are regulatory constraints when it comes to the adoption of advanced ML, hence the call for explainable artificial intelligence (XAI) issued by regulatory bodies like FINMA and BaFin. In our study, we will address these challenges. In particular, based on an exemplary use case, we show how ML methods can be adapted to the specific needs of credit assessment and how, in the case of strongly asymmetric costs of wrong forecasts, it makes sense to optimize not for accuracy but for an economic target function. We showcase this for two simple and ad hoc explainable ML algorithms, finding that in the case of credit approval, surprisingly high rejection rates contribute to maximizing profit.

Financial trading has been widely analyzed for decades with market participants and academics always looking for advanced methods to improve trading performance. Deep reinforcement learning (DRL), a recently reinvigorated method with significant success in multiple domains, still has to show its benefit in the financial markets. We use a deep Q-network (DQN) to design long-short trading strategies for futures contracts. The state space consists of volatility-normalized daily returns, with buying or selling being the reinforcement learning action and the total reward defined as the cumulative profits from our actions. Our trading strategy is trained and tested both on real and simulated price series and we compare the results with an index benchmark. We analyze how training based on a combination of artificial data and actual price series can be successfully deployed in real markets. The trained reinforcement learning agent is applied to trading the E-mini S&P 500 continuous futures contract. Our results in this study are preliminary and need further improvement.

The central research question to answer in this study is whether the AI methodology of Self-Play can be applied to financial markets. In typical use-cases of Self-Play, two AI agents play against each other in a particular game, e.g., chess or Go. By repeatedly playing the game, they learn its rules as well as possible winning strategies. When considering financial markets, however, we usually have one player—the trader—that does not face one individual adversary but competes against a vast universe of other market participants. Furthermore, the optimal behaviour in financial markets is not described via a winning strategy, but via the objective of maximising profits while managing risks appropriately. Lastly, data issues cause additional challenges, since, in finance, they are quite often incomplete, noisy and difficult to obtain. We will show that academic research using Self-Play has mostly not focused on finance, and if it has, it was usually restricted to stock markets, not considering the large FX, commodities and bond markets. Despite those challenges, we see enormous potential of applying self-play concepts and algorithms to financial markets and economic forecasts.

Artificial Intelligence (AI) is one of the most sought-after innovations in the financial industry. However, with its growing popularity, there also is the call for AI-based models to be understandable and transparent. However, understandably explaining the inner mechanism of the algorithms and their interpretation is entirely audience-dependent. The established literature fails to match the increasing number of explainable AI (XAI) methods with the different stakeholders’ explainability needs. This study addresses this gap by exploring how various stakeholders within the Swiss financial industry view explainability in their respective contexts. Based on a series of interviews with practitioners within the financial industry, we provide an in-depth review and discussion of their view on the potential and limitation of current XAI techniques needed to address the different requirements for explanations.