Time-series Momentum Strategies Research Articles

Time series momentum and macroeconomic risk

The time series momentum strategy, previously known as trend following, has been shown to deliver consistent profitability over a long time horizon in futures markets. Funds pursuing this strategy are now a component of many institutional portfolios, due to the expectation of positive returns in equity bear markets. However, the return drivers of the strategy and its performance in other economic conditions are less well understood. We find evidence that the returns to the strategy are connected to the business cycle. Returns are positive in both recessions and expansions, but profitability is higher in expansions. Decomposing asset prices into factor related and idiosyncratic components, we associate a significant portion of returns with exposure to time varying economic factors, consistent with rational asset pricing theories having a role in explaining the profitability of the strategy.

Time Series Momentum and Reversal: Intraday Information from Realized Semivariance

The presence of time series momentum has been widely documented in financial markets across asset classes and countries. In this study, we find a predictable pattern of the realized semivariance estimators for the returns of commodity futures, particularly during the reversals of time series momentum. Based on this finding, we propose a rule-based time series momentum strategy that has a statistically significant higher Sharpe ratio compared to the benchmark of the original time series momentum strategy in the out-of-sample data. The results are robust for different subsamples and various lookback windows.

Enhancing Time-Series Momentum Strategies Using Deep Neural Networks

Although time-series momentum is a well-studied phenomenon in finance, common strategies require the explicit definition of both a trend estimator and a position sizing rule. In this article, the authors introduce deep momentum networks—a hybrid approach that injects deep learning–based trading rules into the volatility scaling framework of time-series momentum. The model also simultaneously learns both trend estimation and position sizing in a data-driven manner, with networks directly trained by optimizing the Sharpe ratio of the signal. Backtesting on a portfolio of 88 continuous futures contracts, the authors demonstrate that the Sharpe-optimized long short-term memory improved traditional methods by more than two times in the absence of transactions costs and continued outperforming when considering transaction costs up to 2–3 bps. To account for more illiquid assets, the authors also propose a turnover regularization term that trains the network to factor in costs at run-time. TOPICS:Statistical methods, simulations, big data/machine learning Key Findings • While time-series momentum strategies have been extensively studied in f inance, common strategies require the explicit specification of a trend estimator and position sizing rule. • In this article, the authors introduce deep momentum networks —a hybrid approach that injects deep learning–based trading rules into the volatility scaling framework of timeseries momentum. • Backtesting on a portfolio of continuous futures contracts, Deep Momentum Networks were shown to outperform traditional methods for transaction costs of up to 2–3 bps, with a turnover regularisation term proposed for more illiquid assets.

Time series momentum: Is it there?

Time series momentum (TSM) refers to the predictability of the past 12-month return on the next one-month return and is the focus of several recent influential studies. This paper shows that asset-by-asset time series regressions reveal little evidence of TSM, both in- and out-of-sample. While the t-statistic in a pooled regression appears large, it is not statistically reliable as it is less than the critical values of parametric and nonparametric bootstraps. From an investment perspective, the TSM strategy is profitable, but its performance is virtually the same as that of a similar strategy that is based on historical sample mean and does not require predictability. Overall, the evidence on TSM is weak, particularly for the large cross section of assets.

Re-examining differences between momentum and time series momentum among individual stocks

ABSTRACTIn this paper, we provide a comprehensive comparison of momentum (CSMOM) and time series momentum (TSMOM) among individual stocks in the US stock market from January 1964 to December 2015 and find that the two are distinct among individual stocks. With zero-cost strategies on both of them, we find that the explanations in Goyal and Jegadeesh (2018) cannot fully explain the differences between the performances of CSMOM strategies and TSMOM strategies.

Trends’ Signal Strength and the Performance of CTAs

We propose a new asset-based factor that relies on aggregating momentum signals over different horizons. Aggregating signals this way captures assets’ trend signal strength, thereby addressing a limitation in existing time series momentum strategies. Our factor mimics a trend-following manager that increases exposure to markets where trends develop and decreases exposure to markets where trends fade. Taking into account a number of practical implementation issues, we found that our proposed factor performs better at replicating the stylized facts of Commodity Trading Advisors’ returns than previous methods and allows a more meaningful assessment of fund alpha.

Time-Series Momentum in the Chinese Commodity Futures Market

This study examines time-series momentum in the Chinese commodity futures market. The findings show that a time-series momentum strategy performs best with a one-month look-back period and a one-month holding period. Furthermore, this strategy outperforms passive long and cross-sectional momentum strategies in the Chinese futures market based on Sharpe ratios, risk-adjusted excess returns, and cumulative returns. But highly volatile market characteristic with many speculative investors limits the period in which time-series momentum is maintained. Our findings suggest that the anomaly is observed in international asset markets, including Chinese commodity futures, and support the implication that speculators profit from time-series momentum strategy is the expense of hedgers.

Time-Series Momentum: Is it There?

Time series momentum (TSM) refers to the predictability of the past 12-month return on the next one-month return and is the focus of several recent influential studies. This paper shows that asset-by-asset time series regressions reveal little evidence of TSM, both in- and out-of-sample. While the t-statistic in a pooled regression appears large, it is not statistically reliable as it is less than the critical values of parametric and nonparametric bootstraps. From an investment perspective, the TSM strategy is profitable, but its performance is virtually the same as that of a similar strategy that is based on historical sample mean and does not require predictability. Overall, the evidence on TSM is weak, particularly for the large cross section of assets.

Cross-sectional and time-series momentum returns: are Islamic stocks different?

ABSTRACTWe search for differences in both unconditional and conditional momentum returns of Islamic and Non-Islamic stocks and test implications of competing behavioural theories that aim to explain momentum returns. Our results show that there is no significant difference in momentum returns between Islamic versus Non-Islamic stocks with respect to both cross-sectional (CS) and time-series (TS) momentum strategies even when we condition momentum returns on market dynamics, information uncertainty and idiosyncratic volatility. We also find that the TS strategy outperforms (underperforms) the CS strategy in market continuations (transitions) consistent with the recent evidence in the U.S. market.Furthermore, we find that CS and TS strategies of both Islamic and Non-Islamic stocks are profitable only when the market continues in the same state consistent with overconfidence driving momentum returns of both Islamic and Non-Islamic stocks.

Cross-Sectional and Time-Series Momentum Returns and Market Dynamics: Are Islamic Stocks Different?

We search for differences in both unconditional and conditional momentum returns of Islamic and Non-Islamic stocks and test implications of competing behavioral theories that aim to explain momentum returns. Our results show that there is no significant difference in momentum returns between Islamic versus Non-Islamic stocks with respect to both cross-sectional (CS) and time-series (TS) momentum strategies even when we condition momentum returns on market dynamics, information uncertainty (IU), and idiosyncratic volatility (IV). We also find that the TS strategy outperforms (underperforms) the CS strategy in market continuations (transitions) consistent with the recent evidence in the U.S. market. Furthermore, we find that CS and TS strategies of both Islamic and Non-Islamic stocks are profitable only when the market continues in the same state consistent with overconfidence driving momentum returns of both Islamic and Non-Islamic stocks.

Returns Signal Momentum

A new type of momentum based on past return signs is introduced, called Returns Signal Momentum. This is mainly driven by sign dependence, which is positively related to average return and negatively related to return volatility. An empirical application using a universe of commodity and financial futures offers supporting evidence to this momentum factor. Investment strategies based on Returns Signal Momentum result in higher returns and Sharpe ratio and lower drawdown when compared to Time Series Momentum and other benchmark strategies. Overall, Returns Signal Momentum can benefit investors as an effective strategy for speculation and hedging.

Time series momentum and contrarian effects in the Chinese stock market

This paper concentrates on the time series momentum or contrarian effects in the Chinese stock market. We evaluate the performance of the time series momentum strategy applied to major stock indices in mainland China and explore the relation between the performance of time series momentum strategies and some firm-specific characteristics. Our findings indicate that there is a time series momentum effect in the short run and a contrarian effect in the long run in the Chinese stock market. The performances of the time series momentum and contrarian strategies are highly dependent on the look-back and holding periods and firm-specific characteristics.

Volatility Weighting Applied to Momentum Strategies

In this article, the authors consider two forms of volatility weighting—own volatility and underlying volatility—applied to cross-sectional and time-series momentum strategies. They present some simple theoretical results for the Sharpe ratios of weighted strategies and show empirical results for momentum strategies applied to U.S. industry portfolios. The authors find that both the timing effect and the stabilizing effect of volatility weighting are relevant. They also introduce a dispersion weighting scheme that treats cross-sectional dispersion as (partially) forecastable volatility. Although dispersion weighting improves the Sharpe ratio, it seems to be less effective than volatility weighting. <b>TOPICS:</b>Analysis of individual factors/risk premia, portfolio construction, statistical methods, performance measurement

Risk reduction in a time series momentum trading strategy

In this paper, we investigate the four most commonly used risk measures - return volatility, beta, value-at-risk and stressed value-at-risk - of a time series momentum (TSM) trading strategy. We demonstrate that the TSM strategy results in reduced risk measures compared with the passive buy-and-hold strategy. We then validate the hypothesis with a bivariate risk model of AR(1) processes. The reduction in risk measures ranged from 24% to 46% under the given model of AR(1) processes. These findings should be relevant to portfolio managers, traders or risk managers who are interested in managing the financial risk of trading strategies based on TSM.

Trend Following: Equity and Bond Crisis Alpha

We study time-series momentum (trend-following) strategies in bonds, commodities, currencies and equity indices between 1960 and 2015. We find that momentum strategies performed consistently both before and after 1985, periods which were marked by strong bear and bull markets in bonds respectively. We document a number of important risk properties. First, that returns are positively skewed, which we argue is intuitive by drawing a parallel between momentum strategies and a long option straddle strategy. Second, performance was particularly strong in the worst equity and bond market environments, giving credence to the claim that trend-following can provide equity and bond crisis alpha. Putting restrictions on the strategy to prevent it being long equities or long bonds has the potential to further enhance the crisis alpha, but reduces the average return. Finally, we examine how performance has varied across momentum strategies based on returns with different lags and applied to different asset classes.

Emerging markets: Is the trend still your friend?

Using an extensive sample consisting of 30 emerging countries and 38years of data, we examine the profitability of two momentum and two trend following strategies. Over the entire sample, we find excess returns that are economically and statistically significant for all four strategies. Furthermore, we show that the significance of the excess returns remains after adjusting for macroeconomic risk factors. In addition, we find that in spite of their relative neglect, trend strategies frequently demonstrate superior performance, compared to momentum strategies. However, contrary to previous research, we do not find that time series momentum strategies outperform cross-sectional momentum strategies. Finally, we show that the effectiveness of the alternative strategies is largely diminished once transactions costs and liberalizations in emerging markets are considered.

Adaptive Time Series Momentum: An Objective Benchmark for Systematic Trend-Following Strategies

We propose a market-based benchmark for Managed Futures funds that relies on simple time series momentum strategies. Our benchmark mimics managers’ allocation process by increasing exposure when trends are developing and decreasing exposure when trends are fading by allocating to short and long-term trend-following strategies simultaneously. In addition, we take into account transaction costs, allowing a meaningful assessment of fund alpha. Our approach offers investors an alternative to widely used manager-based CTA benchmarks. Our model outperforms the explanatory power of existing market-based factor models applied to Managed Futures funds.

Momentum and Risk Adjustment

Dudler and Gmur introduce a new class of momentum strategies: the risk-adjusted time-series momentum (RAMOM) strategies, which are based on averages of past futures returns that have been normalized by their volatility. They test these strategies on a universe of 64 liquid futures contracts and show that RAMOM strategies outperform the standard time-series momentum strategies. In addition, RAMOM trading signals have another useful and important feature: They are naturally less dependent on high volatility. Finally, dollar turnover of RAMOM strategies is about 40% lower than that of time series momentum (TSMOM), implying a drastic reduction in trading costs.

Trend Following and Macroeconomic Risk

The time series momentum strategy has been shown to deliver consistent profitability over a long time horizon. Funds pursuing these strategies are now a component of many institutional portfolios, due to the expectation of positive returns in equity bear markets. However, the return drivers of the strategy and its performance in other economic conditions are less well understood. The authors find evidence that the returns to the strategy are connected to the business cycle. Returns are positive in both recessions and expansions, but profitability is especially high in expansions. About 40% of returns are due to time varying factor-related risk exposure, consistent with rational asset pricing theories having a role in explaining the profitability of the strategy.

Volatility Weighting Applied to Momentum Strategies

We consider two forms of volatility weighting (own volatility and underlying asset volatility) applied to cross-sectional and time-series momentum strategies. We present some simple theoretical results for the Sharpe ratios of weighted strategies and show empirical results for momentum strategies applied to US industry portfolios. We find that both the timing effect and the stabilizing effect of volatility weighting are relevant for the improvement in Sharpe ratios. We also introduce a dispersion weighting scheme which treats cross-sectional dispersion as (partially) forecastable volatility. Although dispersion weighting improves the Sharpe ratio, it seems to be less effective than volatility weighting.