Applying AI in the financial sector
Artificial intelligence (AI) technology is increasingly widely applied globally and is truly bringing about core changes in a number of industries, including financial services. In this development trend, in Vietnam, the application of AI technology in the fields of asset management, risk management and financial consulting services is still very limited. In part 1 of this research article, the authors will provide a general analysis of the most popular AI trends and technologies used in asset management, risk management and financial consulting today.
Although AI is a vast field with many approaches developed over time, recent interest in AI has focused almost entirely on machine learning (ML) techniques, and this is also the most popular AI approach to date. Machine learning – ML is concerned with using data to gradually tune the parameters of statistical, probability, and other computational models.
Essentially, ML automates one or several stages of information processing to produce the final model for prediction or classification. Most ML applications in asset management, and even in management in general, are based on a few key techniques. The main characteristics of popular machine learning techniques used in the financial sector are shown here
The significant increase in Fintech businesses demonstrates the potential of applying technology to solve problems and issues in the financial sector. However, the growth of Fintech companies in the period 2015-2020 shows that growth mainly focuses on a few areas (payments, lending) and neglects some very potential and promising areas. important in the financial industry (investment, asset management, risk management). According to a report conducted by Fintechnews.sg on the Fintech sector in Vietnam, the payment, lending and blockchain sectors account for more than 60% of Fintech businesses.
Meanwhile, the number of Fintech businesses in the fields of asset management and credit assessment/rating accounts for less than 13% (Figure 2). Part of the reason may lie in the fact that the core technology required in the fields of asset management, risk management or financial investment requires complex technologies and requires a lot of costs in terms of both human resources and investment. material resources for development rather than technologies in the fields of payment or P2P lending.
AI techniques can be used to perform fundamental analysis that requires the combination of multiple sources of information, including the use of text analytics and to optimize attribution. assets in financial investment portfolios.
Compared to conventional portfolio optimization methods, AI techniques often provide better estimates of returns and variances.
These estimates can then be used to optimize traditional investment portfolios. Furthermore, AI can be used directly for asset allocation decisions to build portfolios that meet performance targets more closely than portfolios created using traditional methods.
Methods to build investment portfolios include: NLP, LASSO Regression, artificial neural network (ANN), SVM. Portfolio Optimization method: neural network (ANN) techniques can be trained to make asset allocation decisions under complex constraints that are often not easy to integrate into returns expectation – variance.
AI techniques also have applications in risk management, related to both market risk and credit risk. Market risk refers to the possibility of loss due to the influence of the general market, and credit (or counterparty) risk is the risk of a counterparty not fully fulfilling its contractual obligations
One application of AI in market risk management involves extracting information from text or image qualitative data sources. Or unsupervised AI methods can be used to detect anomalies in the forecast output of a risk model by evaluating all forecasts generated by the model and automatically identifies any anomalies.
Risk managers can also use supervised AI techniques to create benchmark forecasts to validate the model. Comparing model results and forecast benchmarks will reveal whether the risk model is generating predictions that are significantly different from those generated by AI.
AI techniques can also predict market volatility and financial crises, especially ANN and SVM, whose ability to capture nonlinear relationships gives them an advantage over automatic models. regression with conditional heteroscedasticity (GARCH). The two techniques ANN and SVM are also widely applied in credit risk management today.
Robot-advisors are computer programs that provide financial advice to assist individual investors in investment activities. Robo-advisors have been attracting significant attention recently because of their success in reducing barriers to entry for non-professional investors. Robo-advisors can integrate all kinds of AI applications into portfolio management, trading, and portfolio risk management.
By absorbing the success of AI in these areas, robo-advisors can not only create portfolios with better out-of-sample performance for investors but also can automatically rebalance your portfolio, automatically manage portfolio risk and minimize transaction costs.
Institutional investors can also benefit from the ability of robo-advisors to process a wide range of financial data. While reducing behavioral biases when making investment decisions is beneficial for all types of investors, amateur investors especially benefit from robo-advisory on aspects of improving portfolio performance, increasing diversification and reducing risk.
