Stock Price Forecasting Over Adaptive Timescale Using Supervised Learning and Receptive Fields
Pattern recognition in financial time series is not a trivial task, due to level of noise, volatile context, lack of formal definitions and high number of pattern variants. A current research trend involves machine learning techniques and online computing. However, medium-term trading is still based on human-centric heuristics, and the integration with machine learning support remains relatively unexplored. The purpose of this study is to investigate potential and perspectives of a novel architectural topology providing modularity, scalability and personalization capabilities. The proposed architecture is based on the concept of Receptive Fields (RF), i.e., sub-modules focusing on specific patterns, that can be connected to further levels of processing to analyze the price dynamics on different granularities and different abstraction levels. Both Multilayer Perceptrons (MLP) and Support Vector Machines (SVM) have been experimented as a RF. Early experiments have been carried out over the FTSE-MIB index.
KeywordsStock price forecasting Pattern recognition Artificial neural network Support vector machine
This work was carried out in the framework of the SCIADRO project, co-funded by the Tuscany Region (Italy) under the Regional Implementation Programme for Underutilized Areas Fund (PAR FAS 2007–2013) and the Research Facilitation Fund (FAR) of the Ministry of Education, University and Research (MIUR).
The authors thank Marco Gasperini for his work on the subject during his thesis.
- 1.Zhou, X., Pan, Z., Hu, G., Tang, S., Zhao, C.: Stock market prediction on high-frequency data using generative adversarial nets. Mathematical Problems in Engineering (2018)Google Scholar
- 2.Jabbur, E., Silva, E., Castilho, D., Pereira, A., Brandão, H.: Design and evaluation of automatic agents for stock market intraday trading. In Proceedings of the 2014 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT), vol. 03, pp. 396–403. IEEE Computer Society, August 2014Google Scholar
- 11.Wang, L., An, H., Xia, X., Liu, X., Sun, X., Huang, X.: Generating moving average trading rules on the oil futures market with genetic algorithms. Math. Probl. Eng. (2014)Google Scholar
- 14.Foglia, P., Prete, C.A., Zanda, M.: Relating GSR signals to traditional usability metrics: case study with an anthropomorphic web assistant. In: Instrumentation and Measurement Technology Conference Proceedings. IMTC 2008. IEEE, pp. 1814–1818. IEEE, May 2008Google Scholar