Incremental Learning of Stock Trends via Meta-Learning with Dynamic Adaptation

TL;DR

This paper introduces MetaDA, a meta-learning approach with dynamic adaptation for incremental stock trend forecasting, effectively capturing emerging and recurring patterns to improve prediction accuracy in non-stationary markets.

Contribution

It proposes a novel meta-learning framework that dynamically adapts to recent and historical data, addressing limitations of existing methods in stock trend prediction.

Findings

MetaDA achieves state-of-the-art forecasting accuracy on real-world datasets.

The method effectively captures both emerging and recurring stock market patterns.

MetaDA demonstrates high efficiency in model adaptation and prediction.

Abstract

Forecasting the trend of stock prices is an enduring topic at the intersection of finance and computer science. Periodical updates to forecasters have proven effective in handling concept drifts arising from non-stationary markets. However, the existing methods neglect either emerging patterns in recent data or recurring patterns in historical data, both of which are empirically advantageous for future forecasting. To address this issue, we propose meta-learning with dynamic adaptation (MetaDA) for the incremental learning of stock trends, which periodically performs dynamic model adaptation utilizing the emerging and recurring patterns simultaneously. We initially organize the stock trend forecasting into meta-learning tasks and train a forecasting model following meta-learning protocols. During model adaptation, MetaDA efficiently adapts the forecasting model with the latest data and a selected portion of historical data, which is dynamically identified by a task inference module. The task inference module first extracts task-level embeddings from the historical tasks, and then identifies the informative data with a task inference network. MetaDA has been evaluated on real-world stock datasets, achieving state-of-the-art performance with satisfactory efficiency.