ConFuse: Convolutional Transform Learning Fusion Framework For Multi-Channel Data Analysis

TL;DR

ConFuse introduces an unsupervised convolutional transform learning framework for multi-channel time series analysis, demonstrating superior performance in financial forecasting compared to benchmark deep networks.

Contribution

The paper presents a novel fusion framework based on convolutional transform learning that effectively processes multi-channel data without supervision.

Findings

Outperforms benchmark deep networks in stock forecasting

Effective fusion of multi-channel data via transform learning

Unsupervised training approach enhances predictive accuracy

Abstract

This work addresses the problem of analyzing multi-channel time series data %. In this paper, we by proposing an unsupervised fusion framework based on %the recently proposed convolutional transform learning. Each channel is processed by a separate 1D convolutional transform; the output of all the channels are fused by a fully connected layer of transform learning. The training procedure takes advantage of the proximal interpretation of activation functions. We apply the developed framework to multi-channel financial data for stock forecasting and trading. We compare our proposed formulation with benchmark deep time series analysis networks. The results show that our method yields considerably better results than those compared against.