Multi-resolution subspace for financial trading

摘要

In this paper, we introduce a new stock trend prediction approach based on subspace classifier and a new feature representation. Our goal is not price prediction but rather trend prediction, which can be formulated as a problem of pattern classification. Recently, several works have approached this problem by applying machine learning techniques. We show that this problem con be efficiently solved using a new method of anchoring. From the feature extracted by technical indicators, we apply an anchoring method to create different features spaces, and a subspace classifier is trained in each feature space. A cascade of classifiers is developed to classify the patterns as "downward trend" or "upward trend". Extensive experiments, carried out on various dataset, confirm the robustness of our approach. We show, that our method permit to obtain a gain higher than standard machine learning classifiers in all the tests.