We document significant time series momentum in equity index, currency, commodity, and bond futures for each of the 58 liquid instruments we consider. The enduring effect of time series momentum on stock returns over nearly 100years introduction. In order to take advantage of the research that i have done in the. Time series momentum is related to, but different from, the phenomenon known as momentum in the finance literature, which is primarily crosssectional in nature.
Timeseries momentum and moving average trading rules. The inefficacy of the relevant time series momentum trading strategies rules out the possibility of speculations. Factors, monthly this data set is related to time series momentum moskowitz, ooi and pedersen, 2012, in which we document an assetpricing anomaly we term time series momentum, which we find to be consistent across different asset classes and markets. We find that their results are largely driven by volatilityscaling returns or the socalled risk parity approach to asset allocation rather than by time series momentum. The standard timeseries momentum trading rule in the literature is the sign of the past return over some lookback horizon such as 12 months moskowitz et al. Time series momentum and moving average trading rules. Time series momentum tsm refers to the predictability of the past 12month return on the next onemonth return and is the focus of several.
Applying time series momentum strategies therefore seems to be less selfevident than might be expected. Moskowitz a,n, yao hua ooi b, lasse heje pedersen b,c a university of chicago booth school of business. This article documents a significant time series momentum effect that is consistent and robust across all examined conventional asset classes from 1969 to 2015. We compare and contrast time series momentum tsmom and moving average ma trading rules so as to better understand the sources of their profitability. A diversified portfolio of timeseries momentum across all assets is remarkably stable and robust, yielding a high sharpe ratio with little correlation to passive benchmarks. These findings are robust across a number of subsamples, lookback. In this article the authors develop a monte carlo backtesting procedure for risk premium strategies and employ it to study timeseries momentum tsm. Enhancing time series momentum strategies using deep neural networks bryan lim, stefan zohren, stephen roberts abstractwhile time series momentum 1 is a wellstudied phenomenon in. In this paper, we rigorously establish a relationship between timeseries momentum strategies in futures markets and commodity trading advisors ctas and examine the question of capacity constraints in. Pedersen1 august, 2010 abstract we document significant time series momentum in equity index, currency, commodity, and bond futures for each of the 58 liquid instruments we consider. We find that this phenomenon is remarkably consistent across the 47 diverse futures contracts in our study, and has led some to document time. We first construct a comprehensive dataset of daily futures returns by splicing contracts together. Baltas and kosowski 20 show volatility estimators can be used to improve the performance of timeseries momentum strategies and antonacci 20 shows timeseries momentum or absolute momentum as they call it has value as a standalone or overlay strategy.
Introduction in a recent paper, moskowitz, ooi, and pedersen 2012 introduce a timeseries momentum tsmom trading rule. Timeseries momentum versus moving average trading rules by. May 01, 2012 we find that 12month time series momentum profits are positive not just on average across these assets, but for every asset contract we examine. Apr 09, 2019 while time series momentum is a wellstudied phenomenon in finance, common strategies require the explicit definition of both a trend estimator and a position sizing rule. Time series is a sequence of observations recorded at regular time intervals. Aqr capital managements brian hurst, yao hua ooi, and lasse h. Factors, monthly this data set is related to time series momentum moskowitz, ooi and pedersen, 2012, in which we document an assetpricing anomaly. Jun 23, 2012 we document significant time series momentum in equity index, currency, commodity, and bond futures for each of the 58 liquid instruments we consider.
We find that this phenomenon is remarkably consistent across the 47 diverse futures contracts in our study, and has led some to document time series momentum as an asset pricing anomaly. Enhancing timeseries momentum strategies using deep. As you can see, the timeseries strategy had a larger proportionate drawdown 36% than the bestof strategy 27%. Its a time series phenomenon that is found to be present. Use a vector, matrix, timetable, or table instead for financial time series. Optimal time series momentum 5 among many others, document reversal for holding periods of more than one year, which induces negative autocorrelation in returns. Time series momentum is perhaps the most observable form of any asset return factor. We find that the duration and magnitude of time series momentum is different in developed and emerging markets, but this is no longer the case when controlling for the currency component. Time series momentum trading strategy and autocorrelation. This article documents a significant timeseries momentum effect that is consistent and robust across all examined conventional asset classes from 1969 to 2015. Relying on time series models, empirical residual distributions, and copulas, the authors address two key drawbacks of conventional backtesting procedures. Time series momentum and macroeconomic risk the time series momentum strategy has been shown to deliver consistent profitability over a long time horizon.
A diversified portfolio of time series momentum strategies across all asset classes delivers substantial abnormal returns with little exposure to standard asset. Crosssectional and timeseries momentum returns and. Received 16 august 2010 received in revised form 11 july 2011. Momentum strategies in futures markets and trendfollowing funds. Time series momentum on stock returns over nearly 100years. Enhancing timeseries momentum strategies using deep neural. Enhancing time series momentum strategies using deep neural. However, the number of profitable momentum strategies is significantly. The timeseries momentum strategy is closely related to the. The univariate timeseries momentum strategy relies heavily on. Recent studies on timeseries momentum have focused primarily on futures markets and managed futures funds e. In the last article, i discussed the crosssectional momentum strategy and showed you the outcome of the backtest using the strategy. Crosssectional and timeseries momentum returns and market.
Mop also look at time series momentum and argue that time series momentum directly matches the predictions of many prominent behavioral and rational asset pricing theories. As part of our second main contribution we carry out a detailed methodological investigation of the time series momentum trading rule. We find persistence in returns for one to 12 months that partially reverses over longer horizons, consistent with sentiment theories of initial underreaction and delayed overreaction. Timeseries momentum versus moving average trading rules. On the other hand, timeseries momentum uses a securitys own past return to predict its future return moskowitz et al. Pedersen1 august, 2010 abstract we document significant time series momentum in equity index, currency, commodity, and bond futures. Focusing on the more recently proposed timeseries momentum dynamic, we contribute by analyzing the intraday momentum effect in the increasingly important and as yet unstudied chinese commodity futures market. Enhancing time series momentum strategies using deep.
Timeseries momentum refers to the trading strategy that results from the aggregation of a number of univariate momentum strategies on a volatilityadjusted basis. Time series momentum moskowitz, ooi, and pedersen 2010 6 outline of talk data time series momentum regression evidence ts momentum strategies time series momentum vs. Second, we extend the existing work on time series momentum along the asset class dimension. The key difference between time series and cross sectional data is that the time series data focuses on the same variable over a period of time while the cross sectional data focuses on. First, we construct a very comprehensive set of time series momentum benchmark portfolios. In this paper, we introduce deep momentum networks a hybrid approach which injects deep learning based trading rules into the volatility scaling framework of time series momentum. Moreover, to the best of our knowledge, our paper is the. Pdf moskowitz, ooi, and pedersen 2012 show that time series momentum delivers a large and significant alpha for a diversified portfolio of. Pdf time series momentum and volatility scaling researchgate. Time series momentum is an assetpricing anomaly in financial markets that was only recently documented by academia.
Time series momentum and volatility scaling article pdf available in journal of financial markets 30 june 2016 with 2,159 reads how we measure reads. Moskowitza,n, yao hua ooib, lasse heje pedersenb,c a university of chicago booth school of business and nber, united states b aqr capital management, united states. Pedersen contribute to the literature on timeseries momentum with their june 2017 study, a century of evidence on trendfollowing. Tsmom signals occur at points that coincide with a ma direction change, whereas ma buy sell signals only require price to move above below a ma. Pdf optimal time series momentum youwei li and tony. While time series momentum is a wellstudied phenomenon in finance, common strategies require the explicit definition of both a trend estimator and a position sizing rule. In this article the authors develop a monte carlo backtesting procedure for risk premium strategies and employ it to study time series momentum tsm. Unless otherwise stated, all rights belong to the author. It is the data of the same variable over a period of time such as months, quarters, years etc. Timeseries and crosssectional momentum strategies under. This study conducts an investigation of intraday time.
Difference between time series and cross sectional data. Dec 22, 2016 moskowitz, ooi, and pedersen2012 show that time series momentum delivers a large and significant alpha for a diversified portfolio of international futures contracts. In this paper, we rigorously establish a relationship between time series momentum strategies in futures markets and commodity trading advisors ctas and examine the question of capacity constraints in trendfollowing investing. An additional advantage is that timeseries momentum returns appear to be largest when the stock markets returns are most extreme.
Pdf optimal time series momentum youwei li and tony he. Time series analysis in python a comprehensive guide. The univariate time series momentum strategy relies heavily on. Time series momentum tsmom and moving average ma trading rules are closely related. This guide walks you through the process of analyzing the characteristics of a given time series in python. The only difference between the two approaches being that cross sectional momentum assigns stocks to the winner and loser portfolio on the basis of their relative. Time series momentum trading in green stocks emerald insight. The time series momentum strategy is closely related to the extensive technical trading literature. Funds pursuing these strategies are now a component of many institutional portfolios, due to the expectation of positive returns in equity bear markets. Its a time series phenomenon that is found to be present in different asset markets equities, commodities, fixedincome, and currencies. May 23, 20 a university technology of sydney, ultimo rd, haymarket.
May 23, 20 a university technology of sydney, ultimo rd, haymarket nsw 2000, australia b trinity college, university of cambridge, address. K abstract this article assumes general stationary processes for prices and derives the. Timeseries momentum tsmom and moving average ma trading rules are closely related. Time series momentum refers to the trading strategy that results from the aggregation of a number of univariate momentum strategies on a volatilityadjusted basis. Timeseries momentum refers to the trading strategy that results from the aggregation of a number of univariate.
Moskowitza,n, yao hua ooib, lasse heje pedersenb,c a university of chicago booth school of business and nber, united states b aqr capital management, united states c new york university, copenhagen business school, nber, cepr, united states article info article history. You may download, display and print this publication for your own personal use. They constructed an equalweighted combination of onemonth, threemonth. The momentum literature focuses on the relative performance of securities in the crosssection, finding that securities that recently outperformed their peers over the past three. Time series analysis in python a comprehensive guide with. This time series momentum or trend effect persists for about a year and then partially reverses over longer horizons. Barberis, shleifer and vishny 1998, daniel, hirshleifer and subrahmanyam 1998, and hong and stein 1999 all focus on a. Crossasset signals and time series momentum sciencedirect. In order to take advantage of the research that i have done in the previous article which is related to measuring time series momentum, i would like to perform a backtest on this strategy and also to compare these two momentum strategies.
We document significant time series momentum in equity index, currency. Time series momentum moskowitz, ooi, and pedersen 2010 6 outline of talk data time series momentum regression evidence tsmomentum strategies time series momentum vs. Time series momentum tobias moskowitz yao hua ooi lasse h. Time series momentum, volatility scaling, and crisis alpha. The standard time series momentum trading rule in the literature is the sign of the past return over some lookback horizon such as 12 months moskowitz et al.
1425 714 176 1310 923 663 543 263 893 1155 17 1202 1036 339 148 679 1318 1064 84 1192 775 742 813 934 9 515 624 24 674 659 846 1132 1428 18 848 1111 556