Quantum Machine Learning for Credit Scoring
Nikolaos Schetakis (ALMA Sistemi Srl) , Davit Aghamalyan (A*STAR) , Michael Boguslavsky (Tradeteq), Agieszka Rees (Tradeteq), Marc Rakotomalala (SKBI), Paul Robert Griffin (SMU) | Jul 2022 |
In this paper we explore the use of quantum machine learning (QML) applied to credit scoring for small and medium size businesses (SMEs). A quantum/classical hybrid approach has been used for two years of experimentation with several models, activation functions, epochs, other parameters. Results are shown from the best model, using two quantum classifiers and a classical neural network, applied to data for companies in Singapore. We observe significantly more efficient training for the quantum models over the classical models for comparable prediction performance. Practical issues are also explored including a quadratic computational slow down with the number of qubits and a linear slow down with the number of blocks of classifiers using classical simulators. Running the models on real quantum computers is discussed including the number of times a circuit has to be executed. Surprisingly, a degradation in the accuracy was observed as the number of qubits was increased beyond 12 qubits and also with the addition of extra classifier blocks in the quantum model. Overall, we see great promise in this first in-depth exploration of the use of hybrid QML in credit scoring.
Commodity Return Predictability: Evidence from Implied Variance, Skewness and their Risk Premia
Marinela Adriana Finta (SKBI) and José Renato Haas Ornelas (Banco Central do Brasil) | Apr 2022 |
This paper investigates the role of realized and implied moments and their risk premia (variance and skewness) for commodities’ future returns. We estimate these moments from high frequency and commodity futures option data that results in forward-looking measures. Risk premia are computed as the difference between implied and realized moments. We highlight, from a cross-sectional and time-series perspective, the strong positive relation between commodity returns and implied skewness. Moreover, we emphasize the high performance of skewness risk premium. Additionally, we show that their portfolios exhibit the best risk-return tradeoff. Most of our results are robust to other factors such as the momentum and roll yield.
Forthcoming in Journal of International Financial Markets, Institutions and Money.
Bank Competition amid Digital Disruption: Implications for Financial Inclusion
Erica Xuewei Jiang (USC), Gloria Yang Yu (SMU) and Jinyuan Zhang (UCLA Anderson) | Mar 2022 |
Financial inclusion is presumed to have improved because of advances in FinTech over the last ten years. This paper shows that the effects of new technology on the market for banking services are not straightforward -- digital disruption alters competition among banks, which influences how the welfare effects from FinTech are distributed among consumers.
Higher-Order Risk Premium and Return Spillovers between Commodity and Stock Markets
Marinela Adriana Finta (SKBI) | Mar 2022 |
This study examines the spillovers between risk premia and returns of commodity (grain, metal, and energy sectors) and equity markets (the U.S., U.K., Germany, and Japan). Risk premia are defined as the difference between implied volatility, skewness, and kurtosis and their realized moments. Our results show that cross-market and cross-moment spillovers vary over time, and various announcements explain this variation. We uncover the substantial effects of equity markets for commodity markets, and as those of returns for the risk premia. Moreover, we highlight the prominent influence of the metal sector for the other commodity sectors and equity market, and that of skewness risk premia for the returns.
Is Carbon Risk Priced in the Cross-Section of Corporate Bond Returns?
Tinghua Duan (IESEG School of Management), Frank Weikai Li (SMU) and Quan Wen (Georgetown University) | Feb 2022 |
The ‘carbon risk premium’ hypothesis says that bonds of more carbon-intensive ﬁrms should earn significantly higher returns, but this paper fails to find evidence supporting this view. The dominant explanation is that investors under-appreciate the negative relation between a firm's carbon intensity and its fundamental performance and creditworthiness.
Jun Yu (SMU) and Shuping Shi (Macquarie University) | Jan 2022 |
Market volatility can help us understand other financial variables and macroeconomic conditions. But volatility is often regarded as an imperfect measure of market risk or anxiety. Nevertheless, this paper helps practitioners and academics strive for a rigorous empirical volatility model that more accurately describes current market behaviour and the interactions among market participants.
Outsourcing Climate Change
Rui Dai (University of Pennsylvania), Rui Duan (WU), Hao Liang (SMU), Lilian Ng (York University) | Jan 2022 |
This paper examines whether and how firms combat climate change. Our study provides robust evidence that firms outsource part of their carbon emissions to foreign suppliers and shows how internal and external stakeholders significantly shape firms’ environmental policies. Furthermore, firms tend to seek a foreign supplier and decrease their emission abatement efforts as pressure to reduce domestic emissions intensifies. These firms are also less incentivized to develop green technologies. Finally, we find that outsourcing emissions has real and economic consequences, with investors demanding a higher carbon premium for their exposures to carbon risks associated with increased outsourced emissions.
Does The Institutional Environment Affect the Value of Analyst Recommendations Around the World?
Wanyi Yang (SKBI) and Jun Ma (University of Auckland) | Aug 2021 |
This paper investigates whether the value of analyst recommendations varies across countries and whether this difference is associated with a country’s institutional environment. Using recommendations from a sample of 32 countries from 1994 to 2015, we found that stock prices react to analysts significantly differently across countries. In particular, recommendation announcements in countries with higher accounting standards, more effective security law enforcement, better earnings quality, common law origins, and better protection of private property are associated with significantly higher price reactions. The results are robust using alternative research settings. The institutional environment affects the value of recommendation revisions across countries as well.
Greenwashing: Evidence from Hedge Funds
Hao Liang (SMU LKCSB), Melvyn Teo (SMU LKCSB) and Lin Sun (Fudan University) | Aug 2021 |
We find that a non-trivial number of hedge funds that endorse the United Nations Principles for Responsible Investment indulge in greenwashing. Hedge funds that greenwash underperform both genuinely green and nongreen funds after adjusting for risk. Consistent with an agency explanation, greenwashers (i) underperform more when incentive alignment is poor, (ii) trigger more regulatory violations, and (iii) report more suspicious returns. By exploiting regulatory reforms that aim to enhance stewardship and curb greenwashing, we provide causal evidence that relates agency problems to greenwashing and fund underperformance. Investors, however, do not appear to discriminate between greenwashers and genuinely green funds.
Physical Frictions and Digital Banking Adoption
Hyun Soo CHOI (KAIST) and Roger K. LOH (SMU) | Aug 2021 |
Behavioural literature suggests that minor frictions can elicit desirable behaviour without obvious coercion. Using closures of ATMs in a densely populated city as an instrument for small frictions to physical banking access, we find that customers affected by ATM closures increase their usage of the bank’s digital platform. Other spillover effects of this adoption of financial technology include increases in point-of-sale (POS) transactions, electronic funds transfers, automatic bill payments and savings, and a reduction in cash usage. Our results show that minor frictions can help overcome the status-quo bias and facilitate significant behaviour change.
Japanese Monetary Policy and Its Impact on Stock Market Implied Volatility During Pleasant and Unpleasant Weather
Marinela Adriana Finta (SKBI) | Mar 2021 |
We investigate the effect of Japan’s Monetary Policy Meeting releases on the intraday dynamics of the Nikkei Stock Average Volatility Index and its futures during pleasant and unpleasant weather. We show that at the time of a monetary policy release when the temperature is pleasant, there is a significant decline in Japanese equities’ implied volatility and futures, which lasts for about 10 minutes and 5 minutes, respectively. This decline is longer and exhibits a greater variation when releases occur during cold days. Finally, we emphasize the achievable economic profits and losses, given the reaction of Nikkei VI futures to the Japanese monetary policy releases during pleasant and unpleasant weather days, respectively. In particular, taking a short position at the start of the trading day on pleasant days and closing this position at the end of the trading day generates an average annual return of 5.6%.
This paper was published in the Pacific-Basin Finance Journal, Volume 67, Jun 2021. Access the published paper.
Corporate Social Responsibility and Sustainable Finance: A Review of the Literature
Hao Liang (SMU), Luc Renneboog (Tilburg University) | Sep 2020 |
Corporate Social Responsibility (CSR) refers to the incorporation of Environmental, Social, and Governance (ESG) considerations into corporate management, financial decision making, and investors’ portfolio decisions. Socially responsible firms are expected to internalize the externalities (e.g. pollution) they create, and are willing to be accountable to shareholders as well as a broader group of stakeholders (employees, customers, suppliers, local communities,…). Over the past two decades, various rating agencies developed firm-level measures of ESG performance, which are widely used in the literature. A problem for past and a challenge for future research is that these ratings show inconsistencies, which depend on the rating agencies’ preferences, weights of the constituting factors, and rating methodology.
Forthcoming in Oxford Research Encyclopedia of Economics and Finance.
Decentralizing Money: Bitcoin Prices and Blockchain Security
Emiliano Pagnotta (SKBI) | Nov 2020 |
This paper studies the equilibrium determination of bitcoin prices and its blockchain security. Complementarities between users and miners lead to multiple equilibria: the same blockchain technology is consistent with different price-security levels. Bitcoin’s design embeds price volatility amplification of demand shocks and is prone to exhibit seemingly irrational price jumps. The results clarify when bitcoin demand strengthens against conventional currencies.
This paper was published in The Review of Financial Studies, Volume 35, Issue 2, Feb 2022, Pages 866–907. Access the published paper.
Risk Premium Spillovers Among Stock Markets: Evidence from Higher-Order Moments
Marinela Adriana Finta (SKBI) and Sofiane Abourab (University of Paris XIII) | Jun 2017 |
This paper investigates the volatility, skewness and kurtosis risk premium spillovers among U.S., U.K., German and Japanese stock markets. We define risk premia as the difference between risk-neutral and realized moments. Our findings highlight that during periods of stress and after 2014, cross-market and cross-moment spillovers increase, and this is mirrored by a decrease in within spillovers. We document strong bi-directional spillovers between skewness and kurtosis risk premia and emphasize the prominent role played by the volatility risk premium. Finally, we show that several macroeconomic and financial factors increase with the intensity of risk premium spillovers.
This paper was published in the Journal of Financial Markets, Volume 49, Jun 2020. Access the published paper.