Higher Cumulative Returns Research Articles

Enhancing Portfolio Performances through LSTM and Covariance Shrinkage

Portfolio optimization is a crucial aspect of finance, requiring advanced analytical tools and modeling techniques. This paper proposes a new method for portfolio optimization that combines Long Short-Term Memory (LSTM) forecasting with Covariance Shrinkage and Mean-Variance Optimization (MVO) to construct diversified portfolios that maximize risk-adjusted returns. The study utilizes an LSTM-based model to predict stock prices, evaluating its performance using the RMSE metric. The calculated RMSE of 0.0849 indicates accurate and robust predictions. The portfolio constructed shows different weights each day for different assets based on the minimum variance and maximum Sharpe ratio portfolios. As of January 3rd, 2023, the assets with the largest proportion in the Maximum Sharpe Ratio portfolio and in the Minimum Volatility portfolio, are respectively BA, accounting for 27.64% of the portfolio and PG, accounting for 32.66% of the portfolio. This paper compares the performance of the proposed method and benchmark methods by applying 30 daily portfolio weights to real returns. The portfolio constructed by the proposed method has higher cumulative return with a higher Sharpe ratio and lower maximum drawdown, indicating a better ability to diversify risks and create returns. The proposed method offers a new perspective on portfolio optimization, which can potentially benefit investors and asset managers.

Deep reinforcement learning in stock portfolios

This paper investigates stock portfolios by application of Deep Reinforcement Learning (DRL) Models to achieve an optimal tactical asset allocation. The research problem is described as an optimization scenario that seeks to maximize the portfolio risk adjusted returns for a given portfolio asset allocation. The problem is set up with an initial capital investment which is invested in a set of assets. The initial strategic allocation is determined, which in our case is the equal weight allocation, and all of the capital is invested in the set of assets. At each point in time, the assets are reallocated according to the allocation which will increase the portfolio value. Two DRL models are implemented. The performance of the DRL models is compared with the uniform weights portfolio. The results show that, generally, two DRL models have higher cumulative returns.

Intelligent Black–Litterman Portfolio Optimization Using a Decomposition-Based Multi-Objective DIRECT Algorithm

It is agreed that portfolio optimization is of great importance for the financial market. However, input sensitivity and highly-concentrated portfolios have posed a challenge. In this paper, a random forest-based Black–Litterman model is developed, aiming to further enhance the portfolio performance, which adopts a novel method for generating investor views on the basis of random forests. More specifically, the view vector is generated based on the predicted asset returns obtained by random forests, and the confidence matrix which contains the uncertainty of each view is measured by the difference in the predicted values of multiple trees. Furthermore, motivated by decomposition strategy, a novel multi-objective DIRECT algorithm is introduced to effectively resolve the proposed model. Through the construction of a unique indicator, the algorithm possesses the capacity to select potentially-optimal hyperrectangles in all reference directions simultaneously, which will further improve the exploratory nature. Experimental results have demonstrated that the proposed algorithm achieves a better performance over NSGA-II and MOEA/D on the MOP and DTLZ benchmark problems. It is also experimentally verified that the random forest-based Black–Litterman model can obtain higher cumulative returns and Sharpe ratios in the application of Chinese stock markets when compared to the classic MV model.

Maximally predictable currency portfolios

We investigate the predictability of the G10 currencies with respect to lagged currency returns from the perspective of a U.S. investor, using the maximally predictable portfolio (MPP) approach of Lo and MacKinlay (1997). We show that, out-of-sample, the MPP yields a higher Sharpe ratio, higher cumulative return and lower maximum drawdown than both a naïve equal-weighted portfolio of the currencies and an equal-weighted portfolio of momentum trading strategies, and that a mean–variance investor would be willing to pay a performance fee to switch from the naïve and momentum portfolios to the MPP. The MPP has performed particularly well since the 2008 financial crisis, in contrast with the momentum portfolio, the value of which declined significantly over this period. Our results are robust to the estimation window length, the type and level of portfolio weight constraints and transaction costs.

Maximally Predictable Currency Portfolios

We investigate the predictability of the G10 currencies with respect to lagged currency returns from the perspective of a U.S. investor, using the maximally predictable portfolio (MPP) approach of Lo and MacKinlay (1997). Out-of-sample, the MPP yields a higher Sharpe ratio, higher cumulative return and lower maximum drawdown than both an equal-weighted portfolio of the currencies and an equal-weighted portfolio of momentum trading strategies. The MPP has performed particularly well since the 2008 financial crisis, in contrast with the momentum portfolio, the value of which declined significantly over this period. Our results are robust to the estimation window length, the type and level of portfolio weight constraints, and transaction costs.

Public Information，Investment Term and Overvaluation

Institutional investors have become the dominant force in China’s stock market and play an important role in stabilizing the market and improving its efficiency. There are obvious distinctions in investment objectives, trading strategies and decision-making approach between short-term and long-term institutional investors, so it is necessary to distinguish them when exploring the relationship between institutional investors and the market stability. Positive public information often keeps investors in optimistic mind and leads to overvaluation of stocks. In the absence of short-selling constraints, stock mispricing will not be corrected by the market in time, so that overvaluation becomes obvious and persistent. Institutional investors with different term usually respond differently to the same information, which may lead to different extent of overvaluation. This paper examines whether there is a difference in the extent of overvaluation among the stocks of different investment term. It also examines whether this difference is affected by the overall market quotation, and whether the institutional investors of different term attach different importance to positive public information. The results suggest that, positive public information leads to more serious overvaluation of the stocks favored by short-term institutional investors when the market is short-sale constrained. The stocks with shorter term have higher cumulative returns during the issuance of positive analyst ratings. The difference in the extent of overvaluation among the stocks of different term is significant in the bull market, but no longer significant in the bear market. This may be because institutional investors（both long-term and short-term）are cautiously optimistic about positive public information in the bear market, and as the prices of stocks generally declined, previously excluded pessimistic” investors can enter the market. Short-term institutional investors are more reliant on public information than long-term institutional investors when they make decisions, which may be seemed as an explanation for the above phenomena. These results show that the short-term behavior of institutional investors aggravates market volatility, which is an important reason for stock price bubbles. Regulatory authorities can identify institutional investors according to investment term and the role of information dissemination. The relationship between short-selling constraints and stock overvaluation has been extensively studied. On this basis, we further explore the relationship between institutional investment term and stock overvaluation. It is always difficult to separate the effect of public information from private information when making an analysis on the impact of market information on institutional investors’ decision-making. We attempt to solve this problem by introducing the social network analysis into the study of institutional investors’ decision-making behavior. We explore the impact of positive public information on institutional investors’ valuation and trading behavior, which advances the research on the relationship between institutional investors’ decision-making behavior and the stability of the capital market, and also provides a reference for institutional investors to formulate relevant strategies.

Individual Differences in the Disposition Effect

The authors model the role of personality traits in explaining the disposition effect building on realization utility theory and Big 5 model and moving from an aggregate level to interindividual differences. The experimental analysis, combining NEO Revised Personality Inventory measures with individual financial data from a trading simulation run by 230 individuals in China and Italy, shows that the disposition effect is driven by 2 distinct psychological processes, one related to holding losers and the other to selling winners. These 2 behavioral mechanisms are uncorrelated and influenced by different personality traits. Controlling for different demographic variables, the authors show (a) a greater sensitivity of the rewarding system that motivates “extroverts” to quickly sell the stock at gain to receive a burst of utility; (b) a tendency for “conscientious” subjects to suppress impulsivity, patiently waiting for higher cumulative returns; and (c) the importance of “openness to experience” to better value information to achieve higher outcomes.

Fund Price Analysis Using Convolutional Neural Networks for Multiple Variables

Investing in funds has the effect of indirectly employing asset management professionals with specialized knowledge and experience, which can result in a diversified investment through the use of a portfolio. In this study, we focus on learning the patterns of prices rather than time points to predict Korean fund prices. We convert time-series data into 2-dimensional images and analyze them using a convolutional neural network. To improve the fund price forecasting performance, we consider the following aspects. A Korean fund should be recommended according to the level of risk aversion. The risk level of the fund is determined by the proportion of risky assets. Therefore, when estimating the fund price, the risk level of the fund needs to be considered. In this study, we use 15 additional variables, such as foreign stock indexes, foreign exchange rates, and Korean stock indices, in addition to the fund price data. The appropriate filter size, which plays an important role in this process, is proposed. In addition, types of networks and architectures are selected as suitable for forecasting the fund price. We also demonstrate that the number of output classes can be adjusted to increase the future return of the fund. Through this methodology with multiple variables, we can achieve a 25% cumulative profit for 2 years. This means that multi-variable models have a higher cumulative return than the single-variable model and KOSPI and thus a higher average of all funds for active investors.

Evaluating the Performance and Diversification Benefits of Emerging-Market Exchange-Traded Funds

This study evaluates the performance and diversification benefits for U.S. investors of emerging-market exchange-traded funds (ETFs) since their inception in January 2003 through June 2015 by comparing their absolute and risk-adjusted performance with the iShares Core S&P 500 ETF (IVV). The authors find that the emerging-market ETF portfolio has very low correlations with IVV during the period of the study. Emerging-market ETF portfolios delivered better absolute performance (returns and wealth) but also had much higher risk (standard deviation of returns). However, the risk-adjusted performance (Sharpe and Omega ratios) of IVV was better than that of the emerging-market ETF portfolio. They also look at the effect of adding some emerging-market ETFs to IVV during the period of study. The authors find that adding some emerging-market ETFs to IVV leads to higher absolute returns, better risk-adjusted performance (Sharpe and Omega ratios), higher cumulative returns, and increased wealth for U.S. investors. Results are statistically significant at 1% in all cases. Therefore, U.S. investors should add some emerging-market ETFs to their domestic allocation based on their risk tolerance for better performance (absolute and risk-adjusted).

Does it pay to diversify?

Individual investors seek diversification in their portfolios using a number of approaches. One approach that is commonly used is to diversify globally. This article evaluates the performance and diversification benefits of international ETFs for U.S. investors during and after the recent financial crisis. Our results show that U.S. ETFs outperform all categories of international ETFs for the period of our study (January 2008 – June 2013); they have higher average monthly returns, lower risk (standard deviation of returns), higher risk-adjusted performance (Sharpe, Sortino, and Treynor ratios) and the highest cumulative returns over the entire period. When we form equally weighted portfolios of each ETF category and compute their risk-adjusted performance, we again find that U.S. ETF portfolios had the best performance for the entire period. We also find that U.S. ETFs have the lowest tracking error during the entire period. Most of these ETFs passively track the benchmark and do not manage for positive ɑ. Previous research has questioned the diversification benefits of international investing during times of financial distress. We find that international ETFs are highly dependent on major U.S. indices during the period of our analysis, and therefore, offered limited diversification benefits for U.S. investors.

ITrade

Among all investors in the Chinese stock market, more than 95% are non-professional individual investors. These individual investors are in great need of mobile apps that can provide professional and handy trading analysis and decision support everywhere. However, financial data is challenging to analyze because of its large-scale, non-linear and noisy characteristics in a varying stock environment. This paper develops a Mobile Data-Driven Stock Trading System (iTrade), which is a mobile app system based on Client-Server architecture and various data mining techniques. The iTrade is characterized by 1) a data-driven intelligent learning model, which can provide further insight compared to empirical technical analysis, 2) a concept drift adaptation process, which facilitates the model adaptation to market structure changes, and 3) a rigorous benchmark analysis, including the Buy-and-Hold strategy and the strategies of three world-famous master investors (e.g., Warren E. Buffett). Technologies used in iTrade include the Least Absolute Shrinkage and Selection Operator (Lasso) algorithm, Support Vector Machine (SVM) and risk-adjusted portfolio optimization. An application case of iTrade is presented, which is based on a seven-year (2005-2011) back-testing. Evaluation results indicated that iTrade could gain much higher cumulative return compared to the benchmark (Shanghai Composite Index). To the best of our knowledge, this is the first study and mobile app system that emphasizes and investigates the concept drift phenomenon in stock market, as well as the performance comparison between data-driven intelligent model and strategies of master investors.

Momentum and Reversal Effects in Corporate Bond Prices and Credit Cycles

This article studies momentum and reversal patterns in corporate bond prices. The authors analyze returns on two momentum trading strategies—buying bonds with the best past performances (past winners) and buying bonds with the worst past performances (past losers). They consider formation and holding periods of 1 to 24 months. In the case of high-yield bonds, a strategy that buys past winners provides higher cumulative returns than a strategy of buying past losers over the 1998–2009 period. The authors show that this momentum pattern can be attributed to the behavior of credit spreads during a credit cycle. Specifically, the momentum effect is strongest during periods of widening credit spreads and dominates the reversal effect that can be observed during periods of decreasing credit spreads. Alternately, the prices of investment-grade bonds exhibit a reversal pattern, which is due to differences in the durations of the bonds. In this study, the authors also adjust the returns of these portfolios for realistic transaction costs, estimate their risk, and address possible issues of liquidity.

Systematic Funds Outperform Discretionary Funds

This article compares the performance of systematic and discretionary hedge funds. In systematic funds, most trades are originated and executed by computer programs written for that purpose. In discretionary funds, human traders make decisions when to buy and sell which financial securities. The analysis herein shows that systematic funds consistently outperform discretionary funds when performance is measured by Jensen’s Alpha. Systematic funds also exhibit lower correlation with the S&P 500 index and produce higher cumulative returns since inception, although with higher volatility.On the basis of absolute monthly returns, systematic hedge funds outperform discretionary hedge funds whenever markets are falling. When markets are rising, however, discretionary funds tend to deliver higher absolute returns than do systematic funds. On the absolute return basis, the difference between systematic and nonsystematic funds cannot be explained by liquidity considerations: both systematic and discretionary funds deliver comparable returns in both liquid and illiquid markets.Across a variety of other metrics, however, systematic funds perform much better than discretionary funds in limited liquidity across a variety of metrics: systematic funds produce less extreme drawdowns, higher Sharpe ratios, higher Jensen’s alpha, and attract higher Assets Under Management (AUM).Finally, systematic funds exhibit lower skewness and kurtosis than do discretionary funds. When adjusted for skewness and kurtosis, systematic returns are statistically indistinguishable from discretionary returns, suggesting that much of systematic funds’ outperformance comes from better ability to manage extreme events, performing better than discretionary funds in crisis conditions.

Robust multivariate modeling in finance

PurposeProposes a new covariance matrix robust estimator able to capture the correct orientation of the data and the large unconditional variance caused by occasional high volatility periods.Design/methodology/approachDerives easy‐to‐compute estimates for the center and covariance matrix of a data set. The method finds the correct orientation of the data through a robust estimator and the variances through the classical sample covariance matrix.FindingsSimulation experiments confirm the good performance of the proposed estimator under ε‐contaminated normal models and multivariate t‐distributions.Practical implicationsProvides illustrations of the usefulness of this practical tool for the finance industry, in particular when constructing efficient frontiers. Shows that robust portfolios yield higher cumulative returns and possess more stable weights compositions.Originality/valueIt provides an alternative estimator for the covariance matrix able to find a good fit for the bulk of the data as well as for the extreme observations, which could be plugged in widely used financial tools.

Robust Modeling of Multivariate Financial Data

The bottom line in many statistical analysis in finance is the basic issue of modeling a set of multivariate data. Financial data are characterized by their fat tails containing some proportion of extreme observations. We propose a simple model able to capture these main characteristics, and to provide a good fit for the bulk of the data as well as for the atypical observations. Basically, we use a robust covariance estimator to define the center and orientations of the data, and the classical sample covariance to estimate how inflated could this distribution be by the effect of extreme observations. Estimation of the model is done either empirically or by maximum likelihood based on elliptical distributions. Simulation experiments verified the adequacy of the model to real data. We provide illustrations of the usefulness of the proposed procedure, in particular when constructing efficient frontiers. We show that robust portfolios may yield higher cumulative returns and have more stable weights.