Forecasting systemic risk in portfolio selection: The role of technical trading rules

Abstract

This paper proposes and implements methods for determining whether incorporating technical trading rules accurately forecasts systemic risk and improves the performance of out-of-sample portfolios. The proposed methodology considers various trading rules for forecasting and addressing potential systemic risk in portfolio selection problems. The method incorporates major trading rules as early warning systems or alarm rules to detect market failure within diverse reward-risk measures. Methodologically, the alarm rules are integrated into portfolio selection strategies that predict returns using multifactor models. Therefore, the portfolio strategies combine the predictive ability of both technical trading rules and multifactor models. Empirical analyses validate the suggested approaches and evaluate the impacts of different technical trading rules on portfolio selection problems. This paper compares the ex ante sample paths of several portfolio strategies aiming to maximize portfolio wealth using either reward-risk or drawdown-based performance measures. The results show that the proposed methodologies outperform the classic approach in terms of out-of-sample performance.

Dual Focus on Systemic Risk in Portfolio Management

“…Step 2: Apply the PCA approach to the Pearson correlation matrix of the returns to obtain the main 𝑠 factors (components) explaining at least 85% of the total portfolio variability. Then use a common OLS estimator for the approximation of returns assuming that 𝑟 𝑖 is a linear function of factors 𝑓 𝑗 formulated as 𝑟 𝑖 = 𝑎 𝑖 + ∑ 𝑏 𝑖,𝑗 𝑓 𝑗 𝑠 𝑗=1 + 𝜀 𝑖 , where 𝑎 𝑖 is constant of the 𝑖-th return, 𝑏 𝑖,𝑗 is coefficient for factor 𝑓 𝑗 and 𝜀 𝑖 is residual part of the 𝑖-th return (Ortobelli and Tichý, 2015;Kouaissah and Hocine, 2021).…”

“…Since the beginning of financial markets, the prediction and modelling of stock price behaviour have been significant challenges that are examined by both financial analysts and researchers, respectively, see Ahn et al (2019) and Kouaissah and Hocine (2021). With the increasing fluctuation and volatility of prices in global markets during crisis periods, systemic risk warning is becoming more relevant.…”

“…The inclusion of a simple type of alarm in the portfolio selection process was originally proposed by Kouaissah and Hocine (2021). However, the authors used different indicators from technical analysis and their generally applied rules.…”

Mastery of “Monthly Effects”: Big Data Insights into Contrarian Strategies for DJI 30 and NDX 100 Stocks over a Two-Decade Period

“…Although our findings may contradict previous research that technical trading rules do not outperform the market in stock markets [92][93][94], they may be consistent with relevant studies that apply contrarian technical trading rules would result in considerable returns in stock markets. Thus, we infer that the efficacy of trading rules may be related to the investment horizon and investment instruments [5,95,96].…”

The Profitability of Technical Analysis during the COVID-19 Market Meltdown

“…M'ng (2018) devised a novel adjustable moving average indicator for the Far East equity markets that resulted in excess returns over the buy-and-hold strategy. Finally, Kouaissah and Hocine (2020) successfully applied TRs for portfolio selection strategies.…”