Building Cross-Sectional Systematic Strategies By Learning to Rank

Poh, Daniel; Lim, Bryan; Zohren, Stefan; Roberts, Stephen

doi:10.2139/ssrn.3751012

Cited by 5 publications

(7 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As fitness scores are sorted from the Score block in Figure 1, we can simply long the top best assets and short the bottom worst ones. This also provides an alternative to recently proposed learning-to-rank algorithms to construct such long-short strategies [28].…”

Section: The Design Of the Differential Function H 2 For Constraintsmentioning

confidence: 99%

A Universal End-to-End Approach to Portfolio Optimization via Deep Learning

Zhang¹,

Zhang²,

Cucuringu³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We propose a universal end-to-end framework for portfolio optimization where asset distributions are directly obtained. The designed framework circumvents the traditional forecasting step and avoids the estimation of the covariance matrix, lifting the bottleneck for generalizing to a large amount of instruments. Our framework has the flexibility of optimizing various objective functions including Sharpe ratio, mean-variance trade-off etc. Further, we allow for short selling and study several constraints attached to objective functions. In particular, we consider cardinality, maximum position for individual instrument and leverage. These constraints are formulated into objective functions by utilizing several neural layers and gradient ascent can be adopted for optimization. To ensure the robustness of our framework, we test our methods on two datasets. Firstly, we look at a synthetic dataset where we demonstrate that weights obtained from our end-to-end approach are better than classical predictive methods. Secondly, we apply our framework on a real-life dataset with historical observations of hundreds of instruments with a testing period of more than 20 years.

show abstract

Section: The Design Of the Differential Function H 2 For Constraintsmentioning

confidence: 99%

A Universal End-to-End Approach to Portfolio Optimization via Deep Learning

Zhang¹,

Zhang²,

Cucuringu³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Related to the issue of portfolio selection is the ranking of a subset of assets to buy or trade in a long/short portfolio. Poh et al (2021) apply learning to rank algorithms which are primarily designed for natural language processing, to cross-sectional momentum trading strategies. Cross-sectional strategies mitigate some of the risk associated with wider market moves by buying the top α-percentile of strategies with the highest expected future returns and selling the bottom α-percentile of strategies with the lowest expected future returns.…”

Section: Learning To Rank Portfolios Of Assetsmentioning

confidence: 99%

Sequential asset ranking in nonstationary time series

Borrageiro

2022

Preprint

View full text Add to dashboard Cite

Financial time series are both autocorrelated and nonstationary, presenting modelling challenges that violate the independent and identically distributed random variables assumption of most regression and classification models. The prediction with expert advice framework makes no assumptions on the data-generating mechanism yet generates predictions that work well for all sequences, with performance nearly as good as the best expert with hindsight. We conduct research using S&P 250 daily sampled data, extending the academic research into cross-sectional momentum trading strategies. We introduce a novel ranking algorithm from the prediction with expert advice framework, the naive Bayes asset ranker, to select subsets of assets to hold in either long-only or long/short portfolios. Our algorithm generates the best total returns and risk-adjusted returns, net of transaction costs, outperforming the long-only holding of the S&P 250 with hindsight. Furthermore, our ranking algorithm outperforms a proxy for the regress-then-rank cross-sectional momentum trader, a sequentially fitted curds and whey multivariate regression procedure.

show abstract

“…For implementation details, please refer to [1]. We use pairs in {(8, 24), (16,28), (32, 96)}. We can think of these indicators preforming a similar function to a convolutional layer.…”

Section: B Deep Learningmentioning

confidence: 99%

“…Rather than using handcrafted techniques to identify trends and select positions, [1] introduces Deep Momentum Networks (DMNs), where a Long Short-Term Memory (LSTM) [11] deep learning architecture achieves this by directly optimising on the Sharpe ratio of the signal. Deep Learning has been widely utilised for time-series forecasting [12], achieving a high level of accuracy across various fields, including the field of finance for both daily data [1,[13][14][15][16] and in a high frequency setting, using limit order book data [17,18]. In recent years, implementation of such deep learning models has been made accessible via extensive open source frameworks such as TensorFlow [19] and PyTorch [20].…”

Section: Introduction Time-series (Ts) Momentummentioning

confidence: 99%

Slow Momentum with Fast Reversion: A Trading Strategy Using Deep Learning and Changepoint Detection

Wood,

Roberts,

Zohren

2021

Preprint

Self Cite

View full text Add to dashboard Cite

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 change-point detection (CPD) module into a Deep Momentum Network (DMN) [1] 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 meanreversion 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. Using a portfolio of 50, liquid, continuous futures contracts over the period 1990-2020, the addition of the CPD module leads to an improvement in Sharpe ratio of 33%. Even more notably, this 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 400%. This is especially interesting as traditional momentum strategies have been underperforming in this period.K. Wood, S. Roberts and S. Zohren are with the Department of Engineering Science and the Oxford-

show abstract

Building Cross-Sectional Systematic Strategies By Learning to Rank

Cited by 5 publications

References 24 publications

A Universal End-to-End Approach to Portfolio Optimization via Deep Learning

A Universal End-to-End Approach to Portfolio Optimization via Deep Learning

Sequential asset ranking in nonstationary time series

Slow Momentum with Fast Reversion: A Trading Strategy Using Deep Learning and Changepoint Detection

Contact Info

Product

Resources

About