Lagged correlation-based deep learning for directional trend change prediction in financial time series
This addresses the challenge of forecasting stock market trends, which is notoriously difficult due to noise and external factors, but the approach appears incremental as it builds on existing correlation-based methods with deep learning enhancements.
The paper tackled the problem of predicting directional trend changes in noisy financial time series using lagged correlations, excluding target series information, and achieved state-of-the-art accuracies on historical stock market data from 2011 to 2016.
Trend change prediction in complex systems with a large number of noisy time series is a problem with many applications for real-world phenomena, with stock markets as a notoriously difficult to predict example of such systems. We approach predictions of directional trend changes via complex lagged correlations between them, excluding any information about the target series from the respective inputs to achieve predictions purely based on such correlations with other series. We propose the use of deep neural networks that employ step-wise linear regressions with exponential smoothing in the preparatory feature engineering for this task, with regression slopes as trend strength indicators for a given time interval. We apply this method to historical stock market data from 2011 to 2016 as a use case example of lagged correlations between large numbers of time series that are heavily influenced by externally arising new information as a random factor. The results demonstrate the viability of the proposed approach, with state-of-the-art accuracies and accounting for the statistical significance of the results for additional validation, as well as important implications for modern financial economics.