Yuling Lin; Wurong Shih; Jinglu Hu
March 2013
International Journal of Electronic Business Management;2013, Vol. 11 Issue 1, p23
Academic Journal
In this paper, a quasi-Linear Regression (quasi-LR) model is proposed for developing a stock evaluation system. The main idea is to build the system by using machine learning method, instead of using ANP analysis based on the results of expert questionnaire. The proposed quasi- LR model consists of linear part and nonlinear part, which is identified by using a hierarchical algorithm in such a way that the linear part of the model describes the importance relations among the input financial indicators, while the nonlinear part of the model represents the nonlinear mapping between the financial indexes and the stock performance. Numerical experiments on the past real stock data of 150 Taiwanese stocks are used to have a pilot run of the system. The results show the promising effectiveness of the proposed stock evaluation system.


Related Articles

  • Classification of Indian Stock Market Data Using Machine Learning Algorithms. Soni, Sneha; Shrivastava, Shailendra // International Journal on Computer Science & Engineering;2010, p2942 

    Classification of Indian stock market data has always been a certain appeal for researchers. In this paper, first time combination of three supervised machine learning algorithms, classification and regression tree (CART) , linear discriminant analysis (LDA) and quadratic discriminant analysis...

  • Artificial Intelligence and Data Mining 2014. Fuding Xie; Suohai Fan; Jianzhou Wang; Lu, Helen; Caihong Li // Abstract & Applied Analysis;2014, p1 

    No abstract available.

  • On Discriminative Bayesian Network Classifiers and Logistic Regression. Teemu Roos; Hannes Wettig; Peter Grnwald; Petri Myllymki; Henry Tirri // Machine Learning;Jun2005, Vol. 59 Issue 3, p267 

    Abstract Discriminative learning of the parameters in the naive Bayes model is known to be equivalent to a logistic regression problem. Here we show that the same fact holds for much more general Bayesian network models, as long as the corresponding network structure satisfies a certain...

  • Latent Classification Models. Helge Langseth; Thomas D. Nielsen // Machine Learning;Jun2005, Vol. 59 Issue 3, p237 

    Abstract One of the simplest, and yet most consistently well-performing set of classifiers is the Nave Bayes models. These models rely on two assumptions: (i) All the attributes used to describe an instance are conditionally independent given the class of that instance, and (ii) all attributes...

  • Machine learning for science and society. Rudin, Cynthia; Wagstaff, Kiri // Machine Learning;Apr2014, Vol. 95 Issue 1, p1 

    The special issue on 'Machine Learning for Science and Society' showcases machine learning work with influence on our current and future society. These papers address several key problems such as how we perform repairs on critical infrastructure, how we predict severe weather and aviation...

  • NetiNeti: discovery of scientific names from text using machine learning methods. Akella, Lakshmi Manohar; Norton, Catherine N.; Miller, Holly // BMC Bioinformatics;2012, Vol. 13 Issue 1, p211 

    Background: A scientific name for an organism can be associated with almost all biological data. Name identification is an important step in many text mining tasks aiming to extract useful information from biological, biomedical and biodiversity text sources. A scientific name acts as an...

  • Fast Affinity Propagation Clustering based on Machine Learning. Shrivastava, Shailendra Kumar; Rana, J. L.; Jain, R. C. // International Journal of Computer Science Issues (IJCSI);Jan2013, Vol. 10 Issue 1, p302 

    Affinity propagation (AP) was recently introduced as an unsupervised learning algorithm for exemplar based clustering. In this paper a novel Fast Affinity Propagation clustering Approach based on Machine Learning (FAPML) has been proposed. FAPML tries to put data points into clusters based on...

  • High Performance Medical Classifiers. Fountoukis, S. G.; Bekakos, M. P. // AIP Conference Proceedings;8/13/2009, Vol. 1148 Issue 1, p99 

    In this paper, parallelism methodologies for the mapping of machine learning algorithms derived rules on both software and hardware are investigated. Feeding the input of these algorithms with patient diseases data, medical diagnostic decision trees and their corresponding rules are outputted....

  • Product Name Recognition for Informal Text: Exploring Features. Tao HE; Juan LIU // Applied Mechanics & Materials;2014, Issue 551, p617 

    Product name recognition refers to locate the name of product in text automatically. We built a conditional random field to recognize product name from forum posts and explored various features to compare their impact on the performance. These features include not only traditional features used...


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics