Deconstructing the Time-Series Momentum Strategy

#118 – Time Series Momentum Effect

Authors: Kim, Tse, Wald

Title: Time Series Momentum and Volatility Scaling



Moskowitz, Ooi, and Pedersen (2012) show that time series momentum delivers a large and significant alpha for a diversified portfolio of various international futures contracts over the 1985 to 2009 period. Although we confirm these results with similar data,  we find that their results are driven by the volatility-scaled returns (or the so-called risk parity approach to asset allocation) rather than by time series momentum. The alpha of time series momentum monthly returns drops from 1.27% with volatility-scaled weights to 0.41% without volatility scaling, which is significantly lower than the cross-sectional momentum alpha of 0.95%. Using  volatility-scaled positions, the cumulative return of a time series momentum strategy is higher that that of the buy-and-hold  strategy; however, timeseriesmomentuman buy-and-hold offer similar cumulative returns if they are not scaled by volatility. The superior performance of the time series momentum strategy also vanishes in the more recent post-crisis period of 2009 to 2013.

Notable quotations from the academic research paper:

"We revisit the findings of MOP (Moskowitz, Ooi, and Pedersen 2012 time series momentum strategy) using 55 futures contracts over the 1985to 2013 period. One special procedure used by MOP is that they scale the returns of the different futures contracts by a simple lagged estimate of volatility. In particular, an asset with a lower volatility will take a greater position size and have a higher weight in the portfolio. Using the same period as MOP, 1985-2009, and also volatility-scaling returns, we find similar results: A portfolio of 55 futures contracts based on the prior 12-month momentum offers an alpha of 1.27% per monthand the alphas of all the individual contracts (except one) are positive with an average of 1.31%. However, if we use unscaled equal-weighted returns, the portfolio alpha and the average individual alpha drop to 0.41% and 0.42%, respectively.

More specifically, MOP scale the volatility of each individual futures contract to correspond to the volatility of an average stock by effectively leveraging the positions. When we scale the futures contracts toa lower (higher) volatility, we obtain smaller (larger) alphas, and scaling the buy-and-hold strategy produces similar results. Thus the magnitude of the TSMOM strategy appears to be largely due to leveraging a strategy which happened to generate a positive alpha. Without volatility scaling, the monthly time series momentum returns underperform the cross-sectional momentum strategy.

Moreover, while we find a positive alpha when applying a TSMOM (time series momentum) strategy to individual contracts, the individual contract returns do not generally outperform a buy-and-hold futures strategy. Specifically, TSMOM offers higher profits than buy-and-hold for 29 (out of 55) contracts using unscaled returns, and 31 contracts using volatility-scaled returns.

MOP also show that time series momentum profits are larger than those from the cross-sectional momentum (XSMOM) strategy of Jegadeesh and Titman (1993). In contrast, examining the foreign exchange market only, Menkoff et al. (2012) find that the TSMOM strategy is less profitable than the XSMOM strategy. We note that when implementing the TSMOM, Menkoff et al. do not volatility-scale their results. In our study, we show that the alpha of the XSMOM, 0.95%, lies between the alphas obtained from the TSMOM using equal (non-volatility-scaled) and volatility-scaled weights. Therefore, the different weighting schemes may explain the conflicting conclusions of MOP and Menkoff et al.

The volatility scale used by MOP is similar to the so-called risk parity approach to asset allocation. A risk parity portfolio is an equally weighted portfolio, where the weights refer to risk (proxied by standard deviation in MOP) rather than dollar amount invested in each asset (Kazemi, 2012). Risk parity balances a portfolio by increasing (decreasing) the weights of low (high) risk assets and using leverageto attain higher portfolio returns.

We also examine the results for several sub-periods: pre and post-2001, and following the financial crisis, 2009-2013. The choice of 2001 is based on a potential structural break in commodity futures markets around the passage of the Commodity Futures Modernization Act (CFMA) in December 2000. We show that the superior performance of TSMOM is concentrated in the pre-2001 period. When we use more recent periods, we find that the performance of TSMOM is worse than that of a buy-and-hold strategy. These results are consistent with the increase in market quality documented for the equity market by Chordia, Roll, and Subrahmanyam (2011)."

Are you looking for more strategies to read about? Check

Do you want to see performance of trading systems we described? Check

Do you want to know more about us? Check

Share onRefer to a friend

Subscribe for Newsletter

Be first to know, when we publish new content

    The Encyclopedia of Quantitative Trading Strategies

    Log in

    1. bi-weekly algo & quant academic research insights
    2. tips on new trading strategies & Quantpedia features
    3. notifications about exclusive Quantpedia offers & promos
    and be the first who get:
    - bi-weekly newsletter with academic research insights
    - special report about top strategies each month
    - exclusive discount offers & coupons