Periodic Reporting for period 1 - FinNet (Backreaction of Financial Networks: Risk Estimation and Asset-Management)
Berichtszeitraum: 2018-09-01 bis 2020-08-31
The financial market is deeply interconnected. Events, news or data shape the expectations of market participants. This influences their behaviour and may trigger in- or divestment decisions, consequently impacting market prices.
A positive surprise in sales volumes for a company’s key product (like Apple and its iPhone) can, for example, push its stock price up, while a missed target could be the reason for a price drop. From this perspective, asset prices carry important information about how market participants perceive and assess each individual asset as a part of the financial market.
However, a sector crisis would probably impact the price of various stocks, not just one. In the same way, the good performance of one company is able to also increase the market valuation of other companies, which are part of its supply chain. This collective behaviour shows effective interconnectivity between the financial actors or products.
Understanding and monitoring the financial interconnectivity is therefore crucial for evaluating risks in the financial market.
Investors, regulators and policymakers have risk at the foundation of their decision-making process. A misplaced understanding of financial risks can bring to disastrous scenarios such as the crisis of 2008, whose consequences had an impact on the entire world's economy and society.
This project aims to utilize and develop cutting-edge technologies in data science and machine learning together with quantitative modelling to improve risk assessment and the decision-making process. Networks can mathematically represent and model the interconnectivity between actors, and when applied to the financial market, their dynamics unveils changes in the risk contribution of each node.
The project allowed the introduction of a new framework that combines Explainable AI methods with traditional methods for testing investment strategies. The framework is able to improve transparency and understanding of the investment risks and performances. Furthermore, the project introduced and studied new network-based strategies that can provide more stable and reliable investment performances. The project could enhance awareness among academics and practitioners about the opportunity of using cutting-edge AI technologies in the finance industry, reinforcing the use of such tools in financial institutions such as in the project host.
A positive surprise in sales volumes for a company’s key product (like Apple and its iPhone) can, for example, push its stock price up, while a missed target could be the reason for a price drop. From this perspective, asset prices carry important information about how market participants perceive and assess each individual asset as a part of the financial market.
However, a sector crisis would probably impact the price of various stocks, not just one. In the same way, the good performance of one company is able to also increase the market valuation of other companies, which are part of its supply chain. This collective behaviour shows effective interconnectivity between the financial actors or products.
Understanding and monitoring the financial interconnectivity is therefore crucial for evaluating risks in the financial market.
Investors, regulators and policymakers have risk at the foundation of their decision-making process. A misplaced understanding of financial risks can bring to disastrous scenarios such as the crisis of 2008, whose consequences had an impact on the entire world's economy and society.
This project aims to utilize and develop cutting-edge technologies in data science and machine learning together with quantitative modelling to improve risk assessment and the decision-making process. Networks can mathematically represent and model the interconnectivity between actors, and when applied to the financial market, their dynamics unveils changes in the risk contribution of each node.
The project allowed the introduction of a new framework that combines Explainable AI methods with traditional methods for testing investment strategies. The framework is able to improve transparency and understanding of the investment risks and performances. Furthermore, the project introduced and studied new network-based strategies that can provide more stable and reliable investment performances. The project could enhance awareness among academics and practitioners about the opportunity of using cutting-edge AI technologies in the finance industry, reinforcing the use of such tools in financial institutions such as in the project host.
The project focused mainly on studying datasets consisting of prices or values of financial instruments over time. Futures markets have been one key source of financial data, as these instruments are exchange-listed products in many cases offering high liquidity, which is a precondition for the implementability of risk management techniques in practice. Futures provide a unified framework that allows extracting the connectivity and the relations between the entities in a portfolio covering commodities, fixed income, equities and forex and, in general, have the ability of mapping a vast part of the world’s economic activity. Networks can be constructed by looking at correlations among price changes of different futures or assets. In this project, we investigated the dynamics of the networks. We tested investment strategies (cross-asset risk premia) inspired by or that are able to exploit the network models.
In recent years, research in data science and machine learning introduced Machine Learning (ML) Explanations: models constructed to explain learning algorithms outcomes. The explanations can help, for example, to fulfil fairness requirements when dealing with human/machine interactions or decision making.
To assess the quality of investment strategies, which is a fundamental part of the research in asset management, we introduced a new way to study their performances. The standard method of testing an investment strategy is by evaluating its performance retrospectively by using historical data (backtesting). Using synthetic or bootstrap data, one can enrich this analysis and simulate the strategy behaviour in different scenarios and data configurations, obtaining a statistical distribution of strategy performances. By leveraging the power of ML explanations, we constructed a pipeline that can test the strategy in multiple scenarios and connect back the performance to features of the historical data that produced it. The ML explanations provide insights to understand the behaviour of complex strategies: what are the actually relevant features and how do they impact the performance. Performance can be e.g. returns, volatility or a risk-adjusted measure whose behaviour can be very non-linear or path-dependent.
Our pipeline and results obtained by using it to investigate two prominent risk parity strategies – “equal risk contribution” and the network-inspired “hierarchical risk parity” – have been accepted for publication in the Journal of Financial Data Science.
In the project, we also introduced novel network-based diversification strategies that are able to go beyond linearity and long-only positions.
Moreover, two other papers have been published concerning the use of ML explanations in finance, in these cases in credit risk, and how networks can provide non-local and global insights into the ML model.
The project content and results have been disseminated also in workshops, conferences and events reaching researchers, investors, the general public and, thanks also to the synergy with the h2020 FIN-TECH project, financial supervisors and policy-makers.
In recent years, research in data science and machine learning introduced Machine Learning (ML) Explanations: models constructed to explain learning algorithms outcomes. The explanations can help, for example, to fulfil fairness requirements when dealing with human/machine interactions or decision making.
To assess the quality of investment strategies, which is a fundamental part of the research in asset management, we introduced a new way to study their performances. The standard method of testing an investment strategy is by evaluating its performance retrospectively by using historical data (backtesting). Using synthetic or bootstrap data, one can enrich this analysis and simulate the strategy behaviour in different scenarios and data configurations, obtaining a statistical distribution of strategy performances. By leveraging the power of ML explanations, we constructed a pipeline that can test the strategy in multiple scenarios and connect back the performance to features of the historical data that produced it. The ML explanations provide insights to understand the behaviour of complex strategies: what are the actually relevant features and how do they impact the performance. Performance can be e.g. returns, volatility or a risk-adjusted measure whose behaviour can be very non-linear or path-dependent.
Our pipeline and results obtained by using it to investigate two prominent risk parity strategies – “equal risk contribution” and the network-inspired “hierarchical risk parity” – have been accepted for publication in the Journal of Financial Data Science.
In the project, we also introduced novel network-based diversification strategies that are able to go beyond linearity and long-only positions.
Moreover, two other papers have been published concerning the use of ML explanations in finance, in these cases in credit risk, and how networks can provide non-local and global insights into the ML model.
The project content and results have been disseminated also in workshops, conferences and events reaching researchers, investors, the general public and, thanks also to the synergy with the h2020 FIN-TECH project, financial supervisors and policy-makers.
The project introduced a new tool for investors, regulators and policymakers to better understand or even control the risk and the performance of strategies employed by the finance industry.
From a broader perspective, the project showed the possibility to use cutting-edge technologies developed in the AI field in finance, not just for prediction tasks but as monitoring tools for risk assessment in the automatic decision-making process. AI is usually seen as a source of new risks in finance. In this project, we show instead that AI can also provide new tools for investigating risks in complex decision-making processes otherwise difficult or impossible to tackle. The framework introduced in the project can become the new standard for risk assessment and would bring more transparency in the financial industry, leading to the possibility of discovering critical scenarios in advance. In this way, risk managers and regulators can take action to prevent possible losses or even economic crashes that may build up or suddenly appear due to initially hidden risks.
Moreover, during the project, we constructed network-based allocation approaches that can help to improve the diversifying nature of existing investment styles. Networks are an effective and reliable model for the interconnectedness of the financial market. For this reason, the key element. While acknowledging that the future remains unpredictable, these new approaches can lead to portfolios that are more stable, reliable and diversified. Furthermore, they may help to sharpen the understanding of risk within a system. All of this can for example help to improve the robustness of savings and retirement product performances, which make use of these risk-based concepts. A more stable market, with more risk-aware participants, more secure instruments can help Finance to be an opportunity for the society while preventing it from being the source of further risks for the world's economy.
From a broader perspective, the project showed the possibility to use cutting-edge technologies developed in the AI field in finance, not just for prediction tasks but as monitoring tools for risk assessment in the automatic decision-making process. AI is usually seen as a source of new risks in finance. In this project, we show instead that AI can also provide new tools for investigating risks in complex decision-making processes otherwise difficult or impossible to tackle. The framework introduced in the project can become the new standard for risk assessment and would bring more transparency in the financial industry, leading to the possibility of discovering critical scenarios in advance. In this way, risk managers and regulators can take action to prevent possible losses or even economic crashes that may build up or suddenly appear due to initially hidden risks.
Moreover, during the project, we constructed network-based allocation approaches that can help to improve the diversifying nature of existing investment styles. Networks are an effective and reliable model for the interconnectedness of the financial market. For this reason, the key element. While acknowledging that the future remains unpredictable, these new approaches can lead to portfolios that are more stable, reliable and diversified. Furthermore, they may help to sharpen the understanding of risk within a system. All of this can for example help to improve the robustness of savings and retirement product performances, which make use of these risk-based concepts. A more stable market, with more risk-aware participants, more secure instruments can help Finance to be an opportunity for the society while preventing it from being the source of further risks for the world's economy.