DeConFuse : A Deep Convolutional Transform based Unsupervised Fusion Framework

TL;DR

DeConFuse introduces a deep convolutional transform learning framework for unsupervised data fusion, demonstrating superior feature extraction in stock forecasting compared to CNN and LSTM methods.

Contribution

It develops a deep convolutional transform learning approach and an unsupervised fusion method with a solid optimization strategy, advancing unsupervised feature learning.

Findings

Outperforms CNN and LSTM in stock forecasting tasks

Provides a mathematically sound optimization for deep CTL

Effective unsupervised feature extraction demonstrated

Abstract

This work proposes an unsupervised fusion framework based on deep convolutional transform learning. The great learning ability of convolutional filters for data analysis is well acknowledged. The success of convolutive features owes to convolutional neural network (CNN). However, CNN cannot perform learning tasks in an unsupervised fashion. In a recent work, we show that such shortcoming can be addressed by adopting a convolutional transform learning (CTL) approach, where convolutional filters are learnt in an unsupervised fashion. The present paper aims at (i) proposing a deep version of CTL; (ii) proposing an unsupervised fusion formulation taking advantage of the proposed deep CTL representation; (iii) developing a mathematically sounded optimization strategy for performing the learning task. We apply the proposed technique, named DeConFuse, on the problem of stock forecasting and trading. Comparison with state-of-the-art methods (based on CNN and long short-term memory network) shows the superiority of our method for performing a reliable feature extraction.