Stock Market Prediction with Multiple Regression, Fuzzy Type-2 Clustering and Neural Networks

Enke, David; Grauer, Manfred; Mehdiyev, Nijat

doi:10.1016/j.procs.2011.08.038

Cited by 69 publications

(37 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering the non-linearities and discontinueous factors Daviv Enke et al analyzed about the three stage stock market prediction, where in the first phase, it defines economic and financial variable which is having a strong relationship with its output, here multiple Regression Analysis is applied. In the second phase a prediction model is designed by a type-2 fuzzy clustering optimized by DE and for the third phase to perform [33] the future reasoning a fuzzy type-2 based neural network is used. The simulated result shows that the performance of the above three model is better than the traditional model.…”

Section: Psomentioning

confidence: 99%

A Survey on Impact of Bio-inspired Computation on Stock Market Prediction

Das¹,

Mishra²,

Rout³

2017

JESTR

View full text Add to dashboard Cite

Financial forecasting is one of the imperative fields of research, where investors invest money and get restless for the future changes of the stock values in the market. In the recent course of time forecasting stock price is one of the challenging tasks. To predict the stock price most Artificial Neural Network (ANN) based model are used in the historical data along with statistical measures, technical indicators etc. With the development of ANNs, investors are hoping the best prediction because networks have great capability of machine learning problems such as classification and prediction. ANNs particularly Back Propagation (BP) has overlooked the non-stationary and noise characteristics of stock market data, as the training of BP is intricate due to the noise data and the network fall into a natural solution such as always predict an usual output. Most optimization techniques have been used for training the weights of forecasting models. Since no single optimization technique is invariably superior to others. Recently various nature inspired optimization techniques have been introduced and successfully employed to many fields of Financial Engineering. This survey aims to study the mostly used Bio-inspired optimization techniques on Stock Market Prediction and makes a comparative analysis between them.

show abstract

Section: Psomentioning

confidence: 99%

A Survey on Impact of Bio-inspired Computation on Stock Market Prediction

Das¹,

Mishra²,

Rout³

2017

JESTR

View full text Add to dashboard Cite

show abstract

“…Many studies have examined that features representation is a critical factor in the performance of ANN because it contains important hidden information in order to train the ANN consistently for predicting the future trends (Charkha, 2008;Desai et al, 2013;Enke et al, 2011;Goswami et al, 2009;Kamijo and Tanigawa, 1990;Tiong et al, 2013). Few experiments were conducted by Lawrence (1997), Yao and Tan (2000), Kordos and Cwiok (2011), which have utilised technical analysis methods to analyse the trend signals and to train the ANN for predicting the direction of trends.…”

Section: Fig 1 the Structure Of Annmentioning

confidence: 99%

Forex prediction engine: framework, modelling techniques and implementations

Tiong

Ngo

Lee

2016

IJCSE

View full text Add to dashboard Cite

This paper presents foreign exchange (Forex) prediction engine that included framework, modelling techniques and implementations, to support the needs of financial organizations or individual investors. In the financial sector, Forex prediction is considered to be a complex field, based on the noise of exchange rates as the major challenge. However, there are some financial instruments that are available to guide the individual for future investments. We propose a promising Forex prediction engine using historical Forex data, to extract a pattern movement over a period of time series using Linear Regression Line (LRL) technique and the proposed segmentation algorithm. Subsequently, Artificial Neural Network (ANN) algorithm is applied to classify unique groups of uptrend and downtrend patterns. Dynamic Time Warping (DTW) algorithm is implemented through brute force to identify the similarity trend and the matched result that is used to predict the trend movement for next day. This research reveals the structure of Forex prediction engine by the description of an integrated framework using technical analysis method and machine learning algorithm. The experimental results of AUD -USD and EUR -USD currencies demonstrated 71% of accuracy and its predictions are reliable.

show abstract

“…The idea of type II fuzzy sets have been applied to a number of fields such as stock market analysis [10], prediction [11], marketing strategy planning [12] and pattern recognition [13].…”

Section: Type II Fuzzy Setsmentioning

confidence: 99%

“…The classifier's upper bound Y I U and lower bound Y II L are extensions of equations (10) and (11) as follows:…”

Section: A Building a Fuzzy Qualitative Regression Presetmentioning

confidence: 99%

A Fuzzy Support Vector Machine with Qualitative Regression Preset

Wei

Watada

Pedrycz

2012

2012 Sixth International Conference on Genetic and Evolutionary Computing

View full text Add to dashboard Cite

In this paper, we formulate a qualitative classification model by means of qualitative fuzzy regression presetbased fuzzy support vector machine (FQR-FSVM). This new model will make it possible to achieve discrimination of output while characterizing membership for each class in terms of multi-dimensional qualitative inputs (attributes). Moreover, the new model will largely shorten the computing time especially for large database by using linear preset of fuzzy qualitative regression classifier to limit the non-linear classification region.

show abstract

Stock Market Prediction with Multiple Regression, Fuzzy Type-2 Clustering and Neural Networks

Cited by 69 publications

References 9 publications

A Survey on Impact of Bio-inspired Computation on Stock Market Prediction

A Survey on Impact of Bio-inspired Computation on Stock Market Prediction

Forex prediction engine: framework, modelling techniques and implementations

A Fuzzy Support Vector Machine with Qualitative Regression Preset

Contact Info

Product

Resources

About