Few-Shot Learning Patterns in Financial Time-Series for Trend-Following Strategies

Abstract

Forecasting models for systematic trading strategies do not adapt quickly when financial market conditions rapidly change, as was seen in the advent of the COVID-19 pandemic in 2020, causing many forecasting models to take loss-making positions. To deal with such situations, we propose a novel time-series trend-following forecaster that can quickly adapt to new market conditions, referred to as regimes. We leverage recent developments from the deep learning community and use few-shot learning. We propose the Cross Attentive Time-Series Trend Network -- X-Trend -- which takes positions attending over a context set of financial time-series regimes. X-Trend transfers trends from similar patterns in the context set to make forecasts, then subsequently takes positions for a new distinct target regime. By quickly adapting to new financial regimes, X-Trend increases Sharpe ratio by 18.9% over a neural forecaster and 10-fold over a conventional Time-series Momentum strategy during the turbulent market period from 2018 to 2023. Our strategy recovers twice as quickly from the COVID-19 drawdown compared to the neural-forecaster. X-Trend can also take zero-shot positions on novel unseen financial assets obtaining a 5-fold Sharpe ratio increase versus a neural time-series trend forecaster over the same period. Furthermore, the cross-attention mechanism allows us to interpret the relationship between forecasts and patterns in the context set.

arXiv commentminor edits

References in corpus (22)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Time Series Forecasting With Deep Learning: A Survey
• RL${}^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
• Entity Embeddings of Categorical Variables
• DeepLOB: Deep Convolutional Neural Networks for Limit Order Books
• A Multi-Horizon Quantile Recurrent Forecaster
• Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution
• Bayesian Model-Agnostic Meta-Learning
• Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting
• Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels
• Neural Processes
• Sequential Neural Processes
• Slow Momentum with Fast Reversion: A Trading Strategy Using Deep Learning and Changepoint Detection
• Recurrent Attentive Neural Process for Sequential Data
• Learning Deep Time-index Models for Time Series Forecasting
• Recurrent Neural Processes
• Trading with the Momentum Transformer: An Intelligent and Interpretable Architecture
• Spatio-Temporal Momentum: Jointly Learning Time-Series and Cross-Sectional Strategies
• Deep Inception Networks: A General End-to-End Framework for Multi-asset Quantitative Strategies