Designing a neural network for forecasting financial and economic time series

Kaastra, Iebeling; Boyd, Milton S.

doi:10.1016/0925-2312(95)00039-9

Cited by 892 publications

(485 citation statements)

References 8 publications

Supporting

Mentioning

457

Contrasting

Unclassified

Order By: Relevance

“…The network satisfying the least error criterion is selected finally. It should be also noted that to avoid overfitting and since we wanted to compare a set of NN classifiers we stuck to just a single hidden layer 44 .…”

Section: Affective State Classificationmentioning

confidence: 99%

“…Another important aspect in designing such networks is selection of the number of hidden neurons. The "fixed" approach suggested by Kaastra and Boyd 44 is best suitable for offline computation despite being time consuming, where a group of networks are trained using different number of neurons. The network satisfying the least error criterion is selected finally.…”

Section: Affective State Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Assessment of Driver Stress from Physiological Signals collected under Real-Time Semi-Urban Driving Scenarios

Singh¹,

Conjeti²,

Banerjee³

2014

IJCIS

View full text Add to dashboard Cite

Designing a wearable driver assist system requires extraction of relevant features from physiological signals like galvanic skin response and photoplethysmogram collected from automotive drivers during real-time driving. In the discussed case, four stress-classes were identified using cascade forward neural network (CASFNN) which performed consistently with minimal intra-and inter-subject variability. Task-induced stress-trends were tracked using -based regression model with CASFNN configuration. The proposed framework will enable proactive initiation of rescue and relaxation procedures during accidents and emergencies.

show abstract

Section: Affective State Classificationmentioning

confidence: 99%

Section: Affective State Classificationmentioning

confidence: 99%

Assessment of Driver Stress from Physiological Signals collected under Real-Time Semi-Urban Driving Scenarios

Singh¹,

Conjeti²,

Banerjee³

2014

IJCIS

View full text Add to dashboard Cite

show abstract

“…Neural networks have been applied to various studies in economics (Kaastra & Boyd, 1996), consumer choice (Chiang et al, 2006;Hu, Shanker, & Hung, 1999), and customer loyalty (Hsu, Shih, Huang, Lin, & Lin, 2009) and information systems adoptions (Chong, 2013). These studies showed that neural networks can be applied to broad areas of research, consistently providing good results.…”

Section: Neural Network Overviewmentioning

confidence: 99%

A neural network approach to predicting price negotiation outcomes in business-to-business contexts

Moosmayer

Chong

Liu

et al. 2013

Expert Systems with Applications

View full text Add to dashboard Cite

“…They are immune to error term assumptions and can tolerate noise, chaotic components, and extremities better than most other methods [23]. ANNs, like conventional regression analysis, attempt to minimize the sum of squared errors [24].…”

Section: Formulation Of the Proposed Modelmentioning

confidence: 99%

“…Data pre-processing is the process of analysing and transforming the input and output variables to minimize noise, highlight important relationships and detect trends [23]. In order to assist ANN learning, data pre-processing is usually performed by means of standardisation before ANN training.…”

Section: Data Pre-processingmentioning

confidence: 99%

Generation of synthetic benchmark electrical load profiles using publicly available load and weather data

Pillai¹,

Putrus²,

Pearsall³

2014

International Journal of Electrical Power & Energy Systems

View full text Add to dashboard Cite

Electrical load profiles of a particular region are usually required in order to study the performance of renewable energy technologies and the impact of different operational strategies on the power grid. Load profiles are generally constructed based on measurements and load research surveys which are capital and labour-intensive.In the absence of true load profiles, synthetically generated load profiles can be a viable alternative to be used as benchmarks for research or renewable energy investment planning. In this paper, the feasibility of using publicly available load and weather data to generate synthetic load profiles is investigated. An Artificial Neural Network (ANN) based method is proposed to synthesize load profiles for a target region using its Typical Meteorological Year 2 (TMY2) weather data as the input. To achieve this, the proposed ANN models are first trained using TMY2 weather data and load profile data of neighbouring regions as the input and targeted output. The limited number of data points in the load profile dataset and the consequent averaging of TMY2 weather data to match its period resulted in limited data availability for training. This challenge was tackled by incorporating generalization using Bayesian regularization into training. The other major challenge was facilitating ANN extrapolation and this was accomplished by the incorporation of domain knowledge into the input weather data for training. The performance of the proposed technique has been evaluated by simulation studies and tested on three real datasets. Results indicate that the generated synthetic load profiles closely resemble the real ones and therefore can be used as benchmarks.

show abstract

Designing a neural network for forecasting financial and economic time series

Cited by 892 publications

References 8 publications

Assessment of Driver Stress from Physiological Signals collected under Real-Time Semi-Urban Driving Scenarios

Assessment of Driver Stress from Physiological Signals collected under Real-Time Semi-Urban Driving Scenarios

A neural network approach to predicting price negotiation outcomes in business-to-business contexts

Generation of synthetic benchmark electrical load profiles using publicly available load and weather data

Contact Info

Product

Resources

About