Momentum strategies play a crucial role in alternative investments, particularly in commodity trading advisors (CTAs). However, these strategies often struggle to adapt to rapid changes in market conditions, as evidenced by the challenges faced during the 2020 market crash. One specific issue arises immediately after momentum turning points, where trends reverse from an uptrend to a downtrend or vice versa. Time-series momentum (TSMOM) strategies are prone to making poor bets in such situations. To address this problem and enhance the response to regime change, the authors propose a novel approach that incorporates an online changepoint detection (CPD) module into a Deep Momentum Network (DMN) pipeline. The DMN utilizes a deep-learning architecture called Long Short-Term Memory (LSTM), which enables simultaneous learning of trend estimation and position sizing. By integrating the CPD module, the model can effectively balance two key components:
1) A slow momentum strategy that capitalizes on persistent trends without overreacting to localized price movements; and 2) A fast mean-reversion strategy regime that promptly flips positions and then reverts them back to exploit localized price moves. The CPD module generates outputs indicating the location and severity score of changepoints, allowing the model to learn how to respond appropriately based on data-driven insights. To evaluate their model's performance, the authors conducted backtesting over the period from 1995 to 2020. The inclusion of the CPD module resulted in a one-third improvement in Sharpe ratio—a measure of risk-adjusted returns—compared to traditional models. The benefits of this module were particularly pronounced during periods of significant nonstationarity, with performance boosts reaching approximately two-thirds during recent years tested (2015–2020). Notably, this is intriguing because traditional momentum strategies have underperformed during this period. Overall, this study introduces a promising approach for addressing challenges faced by momentum strategies when adapting to changing market conditions. By incorporating an online CPD module into a DMN pipeline, it achieves improved performance and better navigates regime changes while enhancing risk-adjusted returns for investors.
Momentum strategies are ways to make money by following trends in the market. Commodity trading advisors (CTAs) use these strategies a lot. Sometimes, these strategies have a hard time keeping up with fast changes in the market, like what happened in 2020 when the market crashed. Time-series momentum (TSMOM) strategies don't work well after big changes in momentum. The authors of this study came up with a new way to combine two different strategies using special computer programs. They tested this new approach from 1995 to 2020 and found that it made more money compared to traditional methods, especially during recent years."
Definitions
- Momentum: Following trends or movements in the market.
- Alternative investments: Different ways of investing money other than just buying stocks or bonds.
- Commodity trading advisors (CTAs): People who help others invest in things like gold, oil, or crops.
- Market conditions: How things are going in the stock market or economy.
- Turning points: Big changes or shifts in momentum.
- Online changepoint detection (CPD) module: A computer program that can detect when there are big changes happening.
- Deep Momentum Network (DMN) pipeline: A special system that combines different strategies for making money.
- Long Short-Term Memory (LSTM) architecture: A type of computer program that can predict future trends based on past data.
- Sharpe ratio: A way to measure how good an investment strategy is at making money
Exploring the Benefits of Incorporating Online Changepoint Detection into Deep Momentum Networks
Momentum strategies are a key component of alternative investments, particularly in commodity trading advisors (CTAs). However, these strategies often struggle to adapt to rapid market changes. This was especially evident during the 2020 market crash, when momentum turning points caused trends to reverse from an uptrend to a downtrend or vice versa. Time-series momentum (TSMOM) strategies were particularly vulnerable in such situations and could make poor bets as a result. To address this issue and enhance response times for regime change, researchers have proposed incorporating an online changepoint detection (CPD) module into a Deep Momentum Network (DMN) pipeline.
The DMN Pipeline with CPD Module
The DMN utilizes a deep-learning architecture called Long Short-Term Memory (LSTM), which enables simultaneous learning of trend estimation and position sizing. By integrating the CPD module, the model can effectively balance two key components:
1) A slow momentum strategy that capitalizes on persistent trends without overreacting to localized price movements; and 2) A fast mean-reversion strategy regime that promptly flips positions and then reverts them back to exploit localized price moves. The CPD module generates outputs indicating the location and severity score of changepoints, allowing the model to learn how to respond appropriately based on data-driven insights.
Evaluating Performance Through Backtesting
To evaluate their model's performance, the authors conducted backtesting over the period from 1995 to 2020. The inclusion of the CPD module resulted in a one-third improvement in Sharpe ratio—a measure of risk-adjusted returns—compared to traditional models. The benefits of this module were particularly pronounced during periods of significant nonstationarity, with performance boosts reaching approximately two-thirds during recent years tested (2015–2020). Notably, this is intriguing because traditional momentum strategies have underperformed during this period.
Conclusion
Overall, this study introduces a promising approach for addressing challenges faced by momentum strategies when adapting to changing market conditions. By incorporating an online CPD module into a DMN pipeline, it achieves improved performance and better navigates regime changes while enhancing risk-adjusted returns for investors
Momentum strategies are an important part of alternative investments and are at the heart of commodity trading advisors (CTAs). These strategies have, however, been found to have difficulties adjusting to rapid changes in market conditions, such as during the 2020 market crash. In particular, immediately after momentum turning points, where a trend reverses from an uptrend (downtrend) to a downtrend (uptrend), time-series momentum (TSMOM) strategies are prone to making bad bets. To improve the response to regime change, we introduce a novel approach, where we insert an online changepoint detection (CPD) module into a Deep Momentum Network (DMN) [1904.04912] pipeline, which uses an LSTM deep-learning architecture to simultaneously learn both trend estimation and position sizing. Furthermore, our model is able to optimise the way in which it balances 1) a slow momentum strategy which exploits persisting trends, but does not overreact to localised price moves, and 2) a fast mean-reversion strategy regime by quickly flipping its position, then swapping it back again to exploit localised price moves. Our CPD module outputs a changepoint location and severity score, allowing our model to learn to respond to varying degrees of disequilibrium, or smaller and more localised changepoints, in a data driven manner. Back-testing our model over the period 1995-2020, the addition of the CPD module leads to an improvement in Sharpe ratio of one-third. The module is especially beneficial in periods of significant nonstationarity, and in particular, over the most recent years tested (2015-2020) the performance boost is approximately two-thirds. This is interesting as traditional momentum strategies have been underperforming in this period.
