An efficient CMAC neural network for stock index forecasting

Bandeira

2017

JRFM

Neural networks are well suited to predict future results of time series for various data types. This paper proposes a hybrid neural network model to describe the results of the database of the New York Stock Exchange (NYSE). This hybrid model brings together a self organizing map (SOM) with a multilayer perceptron with back propagation algorithm (MLP-BP). The SOM aims to segment the database into different clusters, where the differences between them are highlighted. The MLP-BP is used to construct a descriptive mathematical model that describes the relationship between the indicators and the closing value of each cluster. The model was developed from a database consisting of the NYSE Composite US 100 Index over the period of 2 April 2004 to 31 December 2015. As input variables for neural networks, ten technical financial indicators were used. The model results were fairly accurate, with a mean absolute percentage error varying between 0.16% and 0.38%.

“…The BR 26 is an index that seeks to show the tendency to purchase and sale within the last 26 days, calculated by Equation (16) …”

Section: Implementation Of the Hybrid Modelmentioning

confidence: 99%

Section: A Hybrid Modelmentioning

confidence: 99%

See 1 more Smart Citation

Modeling NYSE Composite US 100 Index with a Hybrid SOM and MLP-BP Neural Model

Bandeira

2017

JRFM

“…Compared with the traditional neural network prediction method, this method not only improves the prediction accuracy obviously, but also more in line with the actual ups and downs of the stock. Chijie Lu et al [10] (2011) used high quantization resolution and large generalization size to reduce generalization errors and used efficient and fast hash codes to accelerate many-to-many mapping, establishing an efficient Cerebellar model joint control neural network (CAMC NN). Based on the experimental results, it was found that the performance of CMAC NN scheme was superior to robustness evaluation and support vector regression (SVR) and back propagation neural network (BPNN).…”

Section: Neural Network Prediction Technologymentioning

confidence: 99%

A Survey of Stock Forecasting Model Based on Artificial Intelligence Algorithm

Deng¹,

Gan²

2017

JMI

Abstract. Stock forecasting technology has become a hot spot for scholars and investors, with its unique charm to attract a large number of scholars and investors to be committed to the stock market forecast research. Particularly, intelligent forecasting technology has made significant achievements in this regard. This paper describes 14 advanced neural networks and support vector machine forecasting techniques at home and abroad, analyzes and summarizes the characteristics and key points of each forecasting method. Finally, it puts forward the existing problems of stock forecasting research methods and explores the prospect of the future.

2017 25th European Signal Processing Conference (EUSIPCO)

“…Additionally, the CMAC uses a set of overlapping local basis functions, which can provide good performance in some practical applications where local concept drifts are present (see Section III-A). Because of its fast online training and simplicity, it is very useful in many real-time applications such as control (its original purpose) [15], predistortion [16], classification [17], and time series forecasting [18].…”

Section: B Convex Combinationmentioning

confidence: 99%

Generalized CMAC adaptive ensembles for concept-drifting data streams

Gonzalez-Serrano

Figueiras-Vidal

2017

Abstract-In this paper we propose to use an adaptive ensemble learning framework with different levels of diversity to handle streams of data in non-stationary scenarios in which concept drifts are present. Our adaptive system consists of two ensembles, each one with a different level of diversity (from high to low), and, therefore, with different and complementary capabilities, that are adaptively combined to obtain an overall system of improved performance. In our approach, the ensemble members are generalized CMACs, a linear-in-the-parameters network. The ensemble of CMACs provides a reasonable trade-off between expressive power, simplicity, and fast learning speed.At the end of the paper, we provide a performance analysis of the proposed learning framework on benchmark datasets with concept drifts of different levels of severity and speed.