DeConFuse : A Deep Convolutional Transform based Unsupervised Fusion Framework
This work addresses stock forecasting and trading by providing an unsupervised fusion framework, though it appears incremental as it builds on prior convolutional transform learning research.
The authors tackled the problem of unsupervised feature extraction for stock forecasting by proposing DeConFuse, a deep convolutional transform learning framework, which outperformed state-of-the-art methods like CNN and LSTM in reliable feature extraction.
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.