We provide a general framework for finding portfolios that perform well out-of-sample in the presence of estimation error. This framework relies on solving the traditional minimum-variance problem ...but subject to the additional constraint that the norm of the portfolio-weight vector be smaller than a given threshold. We show that our framework nests as special cases the shrinkage approaches of Jagannathan and Ma (Jagannathan, R., T. Ma. 2003. Risk reduction in large portfolios: Why imposing the wrong constraints helps. J. Finance 58 1651–1684) and Ledoit and Wolf (Ledoit, O., M. Wolf. 2003. Improved estimation of the covariance matrix of stock returns with an application to portfolio selection. J. Empirical Finance 10 603–621, and Ledoit, O., M. Wolf. 2004. A well-conditioned estimator for large-dimensional covariance matrices. J. Multivariate Anal. 88 365–411) and the 1/ N portfolio studied in DeMiguel et al. (DeMiguel, V., L. Garlappi, R. Uppal. 2009. Optimal versus naive diversification: How inefficient is the 1/ N portfolio strategy? Rev. Financial Stud. 22 1915–1953). We also use our framework to propose several new portfolio strategies. For the proposed portfolios, we provide a moment-shrinkage interpretation and a Bayesian interpretation where the investor has a prior belief on portfolio weights rather than on moments of asset returns. Finally, we compare empirically the out-of-sample performance of the new portfolios we propose to 10 strategies in the literature across five data sets. We find that the norm-constrained portfolios often have a higher Sharpe ratio than the portfolio strategies in Jagannathan and Ma (2003), Ledoit and Wolf (2003, 2004), the 1/ N portfolio, and other strategies in the literature, such as factor portfolios.
Financial engineering is crucial for effectively combining finance with quantitative approaches. This study aims to forecast the performance of the Nasdaq stock market by considering numerous factors ...like wind, hydro, thermal, gas, and nuclear variables. To accomplish this, we utilize sophisticated predictive models, namely adaptive lasso (ALasso), elastic net (Enet), artificial neural network (ANN), convolutional neural network (CNN), and long short-term memory (LSTM). By using these advanced methods, our goal is to offer perceptive and precise predictions, which will enhance comprehension of the complex dynamics within the financial markets. The evidence suggests that the LSTM model has demonstrated superior accuracy in predicting changes in the Nasdaq stock market when compared to ALasso, Enet, ANN, and CNN. While ALasso, Enet, ANN, and CNN exhibit comparable RMSE and MAE values, their performance is slightly less competitive than that of the LSTM model. The marginal differences in RMSE (ALasso: 0.319, Enet: 0.317, ANN: 0.3, CNN: 0.32) and MAE (ALasso: 0.277, Enet: 0.276, ANN: 0.252, CNN: 0.278) emphasize the comparable effectiveness of various methods, but they somewhat drop below the LSTM model in terms of precision. The findings showed the significance of well-known and advanced ML techniques, particularly LSTM, for enhanced accuracy in financial market predictions.
If returns are not predictable, dividend growth must be predictable, to generate the observed variation in divided yields. I find that the absence of dividend growth predictability gives stronger ...evidence than does the presence of return predictability. Long-horizon return forecasts give the same strong evidence. These tests exploit the negative correlation of return forecasts with dividend-yield autocorrelation across samples, together with sensible upper bounds on dividend-yield autocorrelation, to deliver more powerful statistics. I reconcile my findings with the literature that finds poor power in long-horizon return forecasts, and with the literature that notes the poor out-of-sample R² of return-forecasting regressions.
CVXGEN is a software tool that takes a high level description of a convex optimization problem family, and automatically generates custom C code that compiles into a reliable, high speed solver for ...the problem family. The current implementation targets problem families that can be transformed, using disciplined convex programming techniques, to convex quadratic programs of modest size. CVXGEN generates simple, flat, library-free code suitable for embedding in real-time applications. The generated code is almost branch free, and so has highly predictable run-time behavior. The combination of regularization (both static and dynamic) and iterative refinement in the search direction computation yields reliable performance, even with poor quality data. In this paper we describe how CVXGEN is implemented, and give some results on the speed and reliability of the automatically generated solvers.
Statistics and Data Analysis for Financial Engineering provides an overview of the methods and techniques used to extract quantitative information from enormous amounts of data. The text includes R ...Labs with real-data exercises, and integrates graphical and analytical methods for modeling and diagnosing modeling errors.
Expected Idiosyncratic Skewness Boyer, Brian; Mitton, Todd; Vorkink, Keith
The Review of financial studies,
01/2010, Volume:
23, Issue:
1
Journal Article
Peer reviewed
We test the prediction of recent theories that stocks with high idiosyncratic skewness should have low expected returns. Because lagged skewness alone does not adequately forecast skewness, we ...estimate a cross-sectional model of expected skewness that uses additional predictive variables. Consistent with recent theories, we find that expected idiosyncratic skewness and returns are negatively correlated. Specifically, the Fama-French alpha of a low-expected-skewness quintile exceeds the alpha of a high-expected-skewness quintile by 1.00% per month. Furthermore, the coefficients on expected skewness in Fama-MacBeth cross-sectional regressions are negative and significant. In addition, we find that expected skewness helps explain the phenomenon that stocks with high idiosyncratic volatility have low expected returns.
A nonlinear MPC framework is presented that is suitable for dynamical systems with sampling times in the (sub)millisecond range and that allows for an efficient implementation on embedded hardware. ...The algorithm is based on an augmented Lagrangian formulation with a tailored gradient method for the inner minimization problem. The algorithm is implemented in the software framework GRAMPC and is a fundamental revision of an earlier version. Detailed performance results are presented for a test set of benchmark problems and in comparison to other nonlinear MPC packages. In addition, runtime results and memory requirements for GRAMPC on ECU level demonstrate its applicability on embedded hardware.
This paper investigates the dynamic relation between net individual investor trading and short-horizon returns for a large cross-section of NYSE stocks. The evidence indicates that individuals tend ...to buy stocks following declines in the previous month and sell following price increases. We document positive excess returns in the month following intense buying by individuals and negative excess returns after individuals sell, which we show is distinct from the previously shown past return or volume effects. The patterns we document are consistent with the notion that risk-averse individuals provide liquidity to meet institutional demand for immediacy.
In a model with heterogeneous-risk-aversion agents facing margin constraints, we show how securities' required returns increase in both their betas and their margin requirements. Negative shocks to ...fundamentals make margin constraints bind, lowering risk-free rates and raising Sharpe ratios of risky securities, especially for high-margin securities. Such a funding-liquidity crisis gives rise to "bases," that is, price gaps between securities with identical cash-flows but different margins. In the time series, bases depend on the shadow cost of capital, which can be captured through the interest-rate spread between collateralized and uncollateralized loans and, in the cross-section, they depend on relative margins. We test the model empirically using the credit default swap—bond bases and other deviations from the Law of One Price, and use it to evaluate central banks' lending facilities.