An Empirical Study on Importance of Modeling Parameters and Trading Volume-Based Features in Daily Stock Trading Using Neural Networks
Journal Title: Informatics - Year 2018, Vol 5, Issue 3
Abstract
There have been many machine learning-based studies to forecast stock price trends. These studies attempted to extract input features mostly from the price information with little focus on the trading volume information. In addition, modeling parameters to specify a learning problem have not been intensively investigated. We herein develop an improved method by handling those limitations. Specifically, we generated input variables by considering both price and volume information with even weight. We also defined three modeling parameters: the input and the target window sizes and the profit threshold. These specify the input and target variables, between which the underlying functions are learned by multilayer perceptrons and support vector machines. We tested our approach over six stocks and 15 years and compared with the expected performance over all considered parameter specifications. Our approach dramatically improved the prediction accuracy over the expected performance. In addition, our approach was shown to be stably more profitable than both the expected performance and the buy-and-hold strategy. On the other hand, the performance was degraded when the input variables generated from the trading volume were excluded from learning. All these results validate the importance of the volume and the modeling parameters in stock trading prediction.
Authors and Affiliations
Thuy-An Dinh and Yung-Keun Kwon
Keywords
Related Articles
- EP ID EP44147
- DOI https://doi.org/10.3390/informatics5030036
- Views 281
- Downloads 0
Alt-Splice Gene Predictor Using Multitrack-Clique Analysis: Verification of Statistical Support for Modelling in Genomes of Multicellular Eukaryotes
One of the main limitations of the typical hidden Markov model (HMM) implementation for gene structure identification is that a single structure is identified on a given sequence of genomic data—i.e., identification of...
Medical and Para-Medical Personnel’ Perspectives on Home Health Care Technology
User-based research is strongly recommended in design for older adults. The aim of this paper is to focus the attention on the poorly explored role of medical and para-medical personnel’s perspective on home health car...
Statistical Deadband: A Novel Approach for Event-Based Data Reporting
Deadband algorithms are implemented inside industrial gateways to reduce the volume of data sent across different networks. By tuning the deadband sampling resolution by a preset interval D, it is possible to estimate...
Advancing Social Media and Mobile Technologies in Healthcare Education
Social media and mobile technologies are important new tools in healthcare education, both to assist healthcare professionals learn and maintain their craft, and for the education of patients and families. Social media...
Fitness Activity Recognition on Smartphones Using Doppler Measurements
Quantified Self has seen an increased interest in recent years, with devices including smartwatches, smartphones, or other wearables that allow you to monitor your fitness level. This is often combined with mobile apps...