Enhanced stock price variation prediction via DOE and BPNN-based optimization

Hsieh, Ling‐Feng; Hsieh, Su-Chen; Tai, Pei-Hao

doi:10.1016/j.eswa.2011.04.229

Cited by 28 publications

(28 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Objective Method [20] Stock price trend forecasting Partially connected ANN [21] Stock market forecasting ANN and adaptive exponential smoothing [22] Direction of stock price index ANN and Support Vector Machine (SVM) [23] Stock price index forecasting ANN, SVM, Random Forest (RF) and naive-Bayes [24] Stock price variation forecasting…”

Section: Refmentioning

confidence: 99%

Maximum and minimum stock price forecasting of Brazilian power distribution companies based on artificial neural networks

Laboissiere

Fernandes

Lage

2015

Applied Soft Computing

116

View full text Add to dashboard Cite

Section: Refmentioning

confidence: 99%

Maximum and minimum stock price forecasting of Brazilian power distribution companies based on artificial neural networks

Laboissiere

Fernandes

Lage

2015

Applied Soft Computing

116

View full text Add to dashboard Cite

“…We have chosen five popular technical indicators that appear frequently in the literature [9,19,20,32,36]. Exponential Moving Average (EMA), Moving Average Convergence Divergence We will now explain each of these component strategies and how we arrive to a combined decision.…”

Section: Technical Trading Strategiesmentioning

confidence: 99%

On the quest for robust technical trading strategies using multi-objective optimization

2014

View full text Add to dashboard Cite

We present a robust multi-market optimization methodology for technical trading strategies, whereby robustness is incorporated via the environmental variables of the problem. The search for the optimum parameters is conducted over several markets, in the hope of exposing the GA to differing conditions, increasing the robustness of the solutions produced. Our results show an improvement in terms of performance for the solutions generated under this robust method when compared to those offered by single-market optimization.

show abstract

“…On the other hand, it is difficult to figure out the fitting curve when the prediction object is impacted by many elements and the relations among them are non-linear and chaotic. Some techniques like artificial neural network (ANN) (Voyant et al 2011) and back propagation neural network (BPNN) (Hsieh, Hsieh, and Tai 2011) could handle the multiple-input-prediction problem, but as it is well known, they all need huge amount of sample data. The grey theory, especially the multivariable grey model (Wu et al 2015) could solve the prediction problem with small sample, but it cannot effectively deal with the prediction problem with multiple inputs.…”

Section: Introductionmentioning

confidence: 99%

Customer demand prediction of service-oriented manufacturing incorporating customer satisfaction

Cao

Jiang

Wang

2015

International Journal of Production Research

View full text Add to dashboard Cite

With the emergence of individualised and personalised customer demands, the interaction of service and product has come into the sight of manufacturers and thus promoted the arising of service-oriented manufacturing (SOM), a new business mode that combines manufacturing and service. Be similar to the conventional manufacturing, the customer demand prediction (CDP) of SOM is very important since it is the foundation of the following manufacturing stages. As there are always tight and frequent interactions between service providers and customers in SOM, the customer satisfaction would significantly influence the customer demand of the following purchasing periods. To cope with this issue, a novel CDP approach for SOM incorporating customer satisfaction is proposed. Firstly, the structural relationships among customer satisfaction index and the influence factors are quantitatively modelled by using the structural equation model. Secondly, to reduce the adverse effect of multiple structural input data and small sample size, the least square support vector mechanism is employed to predict customer demand. Finally, the CDP of the air conditioner compressor which is a typical SOM product is implemented as the real-case example, and the effectiveness and validity of the proposed approach is elaborated from the prediction results analysis and comparison.

show abstract

Enhanced stock price variation prediction via DOE and BPNN-based optimization

Cited by 28 publications

References 36 publications

Maximum and minimum stock price forecasting of Brazilian power distribution companies based on artificial neural networks

Maximum and minimum stock price forecasting of Brazilian power distribution companies based on artificial neural networks

On the quest for robust technical trading strategies using multi-objective optimization

Customer demand prediction of service-oriented manufacturing incorporating customer satisfaction

Contact Info

Product

Resources

About