Learning risk preferences from investment portfolios using inverse optimization

Yu, Shi Ming; Wang, Haoran; Dong, Chaosheng

doi:10.1016/j.ribaf.2023.101879

Cited by 7 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Risk preferences reflect an individual’s attitude toward risk and are an important indicator for predicting personal behavior or choices ( 34 , 35 ). They can be divided into two types: risk-seeking and risk-averse.…”

Section: Literature Review and Research Hypothesesmentioning

confidence: 99%

Research on the decision-making of work safety investment in industrial park enterprises: evidence from behavioral experiments

Liu,

Bao,

Yang

et al. 2024

Front. Public Health

View full text Add to dashboard Cite

Due to the clustering of risk factors, industrial park safety accidents can easily trigger a domino effect. Work safety investment is the foundation of enterprise work safety in industrial parks. Therefore, increasing the work safety investment of enterprises in industrial parks is the key condition to prevent accidents. However, due to the typical negative externalities of industrial park work safety accidents, the decision-making process of work safety in park enterprises is influenced by other enterprises within the park, including imitation behaviors. This makes the decision-making of work safety in park enterprises very specific. In order to clarify the influencing factors and effects of work safety investment in industrial park enterprises, this study uses a behavioral experiment method and conducts decision-making experiments using the experimental platform O-Tree. The study recruits 76 participants who play the role of decision-makers in park enterprises. This study uses a lottery price experiment and a dictator experiment to measure the risk preference and altruism preference of the participants, respectively. The study introduces the real background of work safety investment in industrial park enterprises and collects data on work safety investment by the participants in different experimental scenarios. The research results show that the safety attitudes of decision-makers, altruism preference, accident experience, government work safety supervision, park management measures, and safety benefits positively influence work safety investment in park enterprises. The risk preference of decision-makers and the resource capability of work safety negatively influence work safety investment in park enterprises. Work safety investment in park enterprises is influenced by the work safety investment of other enterprises within the park.

show abstract

Section: Literature Review and Research Hypothesesmentioning

confidence: 99%

Research on the decision-making of work safety investment in industrial park enterprises: evidence from behavioral experiments

Liu,

Bao,

Yang

et al. 2024

Front. Public Health

View full text Add to dashboard Cite

show abstract

“…Yu et al. (2020) was dedicated to learning the risk preferences from investment portfolios using an inverse optimization technique. In particular, the proposed inverse optimization approach can be used to measure time‐varying risk preferences directly from market signals and portfolios.…”

Section: Applications In Financementioning

confidence: 99%

“…(2021) considered learning within a set of m prespecified investment portfolios, and Wang and Yu (2021) and Yu et al. (2020) developed learning algorithms and procedures to infer risk preferences, respectively, under the framework of Markowitz mean–variance portfolio optimization. It would be interesting to consider a model‐free RL approach where the robo‐advisor has the freedom to learn and improve decisions beyond a prespecified set of strategies or the Markowitz framework.…”

Section: Further Developments For Mathematical Finance and Reinforcem...mentioning

confidence: 99%

Recent advances in reinforcement learning in finance

Hambly

Yang

2023

Mathematical Finance

View full text Add to dashboard Cite

The rapid changes in the finance industry due to the increasing amount of data have revolutionized the techniques on data processing and data analysis and brought new theoretical and computational challenges. In contrast to classical stochastic control theory and other analytical approaches for solving financial decision‐making problems that heavily reply on model assumptions, new developments from reinforcement learning (RL) are able to make full use of the large amount of financial data with fewer model assumptions and to improve decisions in complex financial environments. This survey paper aims to review the recent developments and use of RL approaches in finance. We give an introduction to Markov decision processes, which is the setting for many of the commonly used RL approaches. Various algorithms are then introduced with a focus on value‐ and policy‐based methods that do not require any model assumptions. Connections are made with neural networks to extend the framework to encompass deep RL algorithms. We then discuss in detail the application of these RL algorithms in a variety of decision‐making problems in finance, including optimal execution, portfolio optimization, option pricing and hedging, market making, smart order routing, and robo‐advising. Our survey concludes by pointing out a few possible future directions for research.

show abstract

“…The authors discovered that investors can effectively integrate sparse ESG data into their portfolio construction to ameliorate portfolio selection. Shi Yu et al [11] recently introduced an innovative approach to gauging risk preference in portfolio selection. The study connects the mean-variance portfolio allocation framework to the domains of psychology and behavioral science.…”

Section: Literature Reviewmentioning

confidence: 99%

Maximizing Returns and Minimizing Risk: A Data-Driven Portfolio Optimization Analysis Using Markowitz's Theory and Sharpe Ratio

2023

AJBM

View full text Add to dashboard Cite

The implementation of new technologies in the financial sphere is expanding as the era of big data arrives. This study uses Python tools to choose four representative stocks from 11 distinct industries for portfolio analysis, based on Markowitz's portfolio theory. The best portfolio solution is discovered through empirical research: Maximum Sharpe ratio of one; The anticipated return, standard deviation, and Sharpe ratio were compared and examined, and the effective frontier of the asset portfolio was calculated using Monte Carlo simulation. In addition, as a simple trading method, build two different simple moving averages. Backtesting reveals that the ideal portfolio's return rate is close to 20% using this strategy.

show abstract

Learning risk preferences from investment portfolios using inverse optimization

Cited by 7 publications

References 35 publications

Research on the decision-making of work safety investment in industrial park enterprises: evidence from behavioral experiments

Research on the decision-making of work safety investment in industrial park enterprises: evidence from behavioral experiments

Recent advances in reinforcement learning in finance

Maximizing Returns and Minimizing Risk: A Data-Driven Portfolio Optimization Analysis Using Markowitz's Theory and Sharpe Ratio

Contact Info

Product

Resources

About