Market timing using combined forecasts and machine learning

Mascio, David A.; Fabozzi, Frank J.; Zumwalt, J. Kenton

doi:10.1002/for.2690

Cited by 17 publications

(18 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, it is important to choose appropriate predictors prior to estimation of predictive regressions because the model and parameter uncertainty may adversely affect the explanatory variables marginal predictive content (see Bai & Ng, 2008;Kuzin, Marcellino, & Schumacher, 2011;Cepni & Guney, 2019;Cepni, Guney, & Swanson 2019;Cepni, Guney, & Swanson, 2020;Farooq & Qamar, 2019;Terui & Li, 2019;Mascio, Fabozzi, & Zumwalt, 2021). In this respect, as an robustness check, we investigate alternative variable selection methods, namely, the Elastic Net, the least absolute shrinkage operator (LASSO), and the Ridge regression in order to preselect variables prior to the predictions (see Tibshirani, 1996;Fu, 1998;Zou & Hastie, 2005).…”

Section: Out-of-sample Forecasting Resultsmentioning

confidence: 99%

Do local and global factors impact the emerging markets' sovereign yield curves? Evidence from a data‐rich environment

Çepni

Güney

Küçüksaraç

et al. 2021

Journal of Forecasting

View full text Add to dashboard Cite

This paper investigates the relation between yield curve and macroeconomic factors for 10 emerging sovereign bond markets using the sample from January 2006 to April 2019. To this end, the diffusion indices obtained under four categories (global variables, inflation, domestic financial variables, and economic activity) are incorporated by estimating dynamic panel data regressions together with the yield curve factors. Besides, in order to capture dynamic interaction between yield curve and macroeconomic/financial factors, a panel vector autoregressive (VAR) analysis based on the system generalized method of moments (GMM) approach is utilized. Empirical results suggest that the level factor responds to shocks originated from inflation, domestic financial variables, and global variables. Furthermore, the slope factor is affected by shocks in global variables, and the curvature factor appears to be influenced by domestic financial variables. We also show that macroeconomic/financial factors captures significant predictive information over yield curve factors by running individual country factor-augmented predictive regressions and variable selection algorithms such ridge regression, least absolute shrinkage operator (LASSO), and Elastic Net. Our findings have important implications for policymakers and fund managers by explaining the underlying forces of movements in the yield curve and forecasting accurately dynamics of yield curve factors.

show abstract

Section: Out-of-sample Forecasting Resultsmentioning

confidence: 99%

Do local and global factors impact the emerging markets' sovereign yield curves? Evidence from a data‐rich environment

Çepni

Güney

Küçüksaraç

et al. 2021

Journal of Forecasting

View full text Add to dashboard Cite

show abstract

“…Several methods of finding the (optimal) combination forecast have been proposed in a large body of literature: for example, a weighted average of forecasts, with the weights adding up to unity (Granger & Ramanathan, 1984); trimming (Granger & Jeon, 2004); rankbased approaches (Aiolfi & Timmermann, 2006); a least-squares forecast averaging (Hansen, 2008b); a complete subset regression (Elliott et al, 2013); iterated (Lin et al, 2018) or depthweighted combinations (Lee & Sul, 2021). Recently, ML techniques have been proposed to select and weight appropriate individual forecasts using, for example, Lasso-based procedures (Diebold & Shin, 2019;Mascio et al, 2020;Freyberger et al, 2020); a combining method for sophisticated models with the historical average serving as shrinkage target (Zhang et al, 2020); or the Combination Elastic Net (Rapach & Zhou, 2020). However, in many practical applications, the simple average of candidate forecasts is more robust than more sophisticated combination approaches (Qian et al, 2019), a phenomenon known as the forecast combination puzzle.…”

Section: Literature Reviewmentioning

confidence: 99%

Forecast combinations for benchmarks of long-term stock returns using machine learning methods

Scholz

2022

Ann Oper Res

View full text Add to dashboard Cite

Forecast combinations are a popular way of reducing the mean squared forecast error when multiple candidate models for a target variable are available. We apply different approaches to finding (optimal) weights for forecasts of stock returns in excess of different benchmarks. Our focus lies thereby on nonlinear predictive functions estimated by a fully nonparametric smoother with the covariates and the smoothing parameters chosen by cross-validation. Based on an out-of-sample study, we find that individual nonparametric models outperform their forecast combinations. The latter are prone to in-sample over-fitting and in consequence, perform poorly out-of-sample especially when the set of possible candidates for combinations is large. A reduction to one-dimensional models balances in-sample and out-of-sample performance.

show abstract

“…Due to the large number of listed companies, it is impossible to optimize the stock portfolio with normal methods and there is a possibility of increasing the stock portfolio risk. Due to severe market fluctuations, new research on portfolio optimization in recent years has used the H&B method to optimize its portfolio [ 11 ]. In this method, regardless of market fluctuations, shares of listed companies are purchased and held until the end of the investment period.…”

Section: Introductionmentioning

confidence: 99%

Stock Portfolio Optimization Using a Combined Approach of Multi Objective Grey Wolf Optimizer and Machine Learning Preselection Methods

Mazraeh

Daneshvar

Zaj

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The present paper deals with optimizing the stock portfolio of active companies listed on the Tehran Stock Exchange based on the forecast price. This paper is based on a combination of different filtering methods such as optimization of trading rules based on technical analysis (ROC, SMA, EMA, WMA, and MACD at six levels—Very Very Weak (VVW), Very Weak (VW), Weak (W), Strong (S), Very Strong (VS), and Very Very Strong (VVS)), Markov Chains, and Machine Learning (Random Forest and Support Vector Machine) Filter stock exchanges and provide buy signals between 2011 and 2020. In proportion to each combination of filtering methods, a buy signal is issued and based on the mean-variance (M-V) model, the stock portfolio is optimized based on increasing the portfolio return and minimizing the stock portfolio risk. Based on this, out of 480 companies listed on the Tehran Stock Exchange, 85 active companies have been selected and stock portfolio optimization is based on two algorithms, MOGWO and NSGA II. The analysis results show that the use of SVM learning machine leads to minor correlation error than the random forest method. Therefore, this method was used to predict stock prices. Based on the results, it was observed that if the shares of companies are filtered, the risk of transactions decreases, and the return on the stock portfolio increases. Also, if two filtering methods are applied simultaneously, the stock portfolio returns slightly and the risk increases. In the analysis, MOGWO algorithm has obtained 133.13% stock return rate with a risk of 3.346%, while the stock portfolio returns in NSGA II algorithm 107.73, with a risk of 1.459%. Comparison of solution methods shows that the MOGWO algorithm has high efficiency in stock portfolio optimization.

show abstract

Market timing using combined forecasts and machine learning

Cited by 17 publications

References 57 publications

Do local and global factors impact the emerging markets' sovereign yield curves? Evidence from a data‐rich environment

Do local and global factors impact the emerging markets' sovereign yield curves? Evidence from a data‐rich environment

Forecast combinations for benchmarks of long-term stock returns using machine learning methods

Stock Portfolio Optimization Using a Combined Approach of Multi Objective Grey Wolf Optimizer and Machine Learning Preselection Methods

Contact Info

Product

Resources

About