RESUMO
Investors are presented with a multitude of options and markets for pursuing higher returns, a task that often proves complex and challenging. This study examines the effectiveness of reinforcement learning (RL) algorithms in optimizing investment portfolios, comparing their performance with traditional strategies and benchmarking against American and Brazilian indices. Additionally, it was explore the impact of incorporating commodity derivatives into portfolios and the associated transaction costs. The results indicate that the inclusion of derivatives can significantly enhance portfolio performance while reducing volatility, presenting an attractive opportunity for investors. RL techniques also demonstrate superior effectiveness in portfolio optimization, resulting in an average increase of 12% in returns without a commensurate increase in risk. Consequently, this research makes a substantial contribution to the field of finance. It not only sheds light on the application of RL but also provides valuable insights for academia. Furthermore, it challenges conventional notions of market efficiency and modern portfolio theory, offering practical implications. It suggests that data-driven investment management holds the potential to enhance efficiency, mitigate conflicts of interest, and reduce biased decision-making, thereby transforming the landscape of financial investment.
RESUMO
This paper describes a new model for portfolio optimization (PO), using entropy and mutual information instead of variance and covariance as measurements of risk. We also compare the performance in and out of sample of the original Markowitz model against the proposed model and against other state of the art shrinkage methods. It was found that ME (mean-entropy) models do not always outperform their MV (mean-variance) and robust counterparts, although presenting an edge in terms of portfolio diversity measures, especially for portfolio weight entropy. It further shows that when increasing return constraints on portfolio optimization, ME models were more stable overall, showing dampened responses in cumulative returns and Sharpe indexes in comparison to MV and robust methods, but concentrated their portfolios more rapidly as they were more evenly spread initially. Finally, the results suggest that it was also shown that, depending on the market, increasing return constraints may have positive or negative impacts on the out-of-sample performance.
RESUMO
PURPOSE: This paper aims to support the equity reassignment process of large family business conglomerates, which can be complex due to both the nature and number of companies involved and specific owner requirements. Addressing these issues is especially important in the context of family businesses, since a successful reassignment might resolve and prevent family conflicts. DESIGN/METHODOLOGY/APPROACH: The paper presents a model that determines the optimal reassignment in terms of a specific owner's preferences. This model can also handle different types of requirements, including accounting for equity and intra-loan partition between owners and controlling for liquidity, capital structure, and transaction costs. The model also considers risk diversification for each member's fortune by considering the uncertainty involved in the future value of each firm, which can change at any point depending on industry and market conditions. The methodology not only finds the optimal solution in terms of a specific target, but it allows for post-optimal analysis so that owners can obtain important insights in terms of the costs involved in adding each requirement to the model. FINDINGS/RESULTS: The model was successfully applied in a real case study. The tool played a primary role in identifying a new equity distribution for a family holding structure composed of 4 members and 26 companies. In the first step, the model derived an optimal solution in terms of the target chosen by the owners, but it did not fully satisfy all members. However, owners were able to come to a decision regarding final reassignment after doing a sensible post-optimal analysis. ORIGINALITY/VALUE: Previous research has focused on analyzing the special characteristics of family-run businesses and how they differ with respect to non-family-run businesses in terms of performance, governance, and management, among other things. However, this paper is the first referring to the process of ownership reassignment and to use an optimization model in its methodology. It is also the first study that bridges the gaps between the disciplines of portfolio optimization, corporate finance, and family business.
RESUMO
Climate-change induced uncertainties in future spatial patterns of conservation-related outcomes make it difficult to implement standard conservation-planning paradigms. A recent study translates Markowitz's risk-diversification strategy from finance to conservation settings, enabling conservation agents to use this diversification strategy for allocating conservation and restoration investments across space to minimize the risk associated with such uncertainty. However, this method is information intensive and requires a large number of forecasts of ecological outcomes associated with possible climate-change scenarios for carrying out fine-resolution conservation planning. We developed a technique for iterative, spatial portfolio analysis that can be used to allocate scarce conservation resources across a desired level of subregions in a planning landscape in the absence of a sufficient number of ecological forecasts. We applied our technique to the Prairie Pothole Region in central North America. A lack of sufficient future climate information prevented attainment of the most efficient risk-return conservation outcomes in the Prairie Pothole Region. The difference in expected conservation returns between conservation planning with limited climate-change information and full climate-change information was as large as 30% for the Prairie Pothole Region even when the most efficient iterative approach was used. However, our iterative approach allowed finer resolution portfolio allocation with limited climate-change forecasts such that the best possible risk-return combinations were obtained. With our most efficient iterative approach, the expected loss in conservation outcomes owing to limited climate-change information could be reduced by 17% relative to other iterative approaches.