Predicting Consumer Retail Sales Using Neural Networks

2002 ◽  
pp. 26-40 ◽  
Author(s):  
G. Peter Zhang ◽  
Min Qi
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Data Preprocessing ◽  
Grocery Store ◽  
Neural Network Modeling ◽  
Retail Sales ◽  
Planning Decisions ◽  
Forecasting Performance ◽  
Preprocessing Technique

Forecasting future retail sales is one of the most important activities that form the basis for all strategic and planning decisions in effective operations of retail businesses as well as retail supply chains. This chapter illustrates how to best model and forecast retail sales time series that contain both trend and seasonal variations. The effectiveness of data preprocessing such as detrending and deseasonalization on neural network forecasting performance is demonstrated through a case study of two different retail sales: computer store sales and grocery store sales. We show that without data preprocessing neural networks are not able to effectively model retail sales with both trend and seasonality in the data, and either detrending or deseasonalization can greatly improve neural network modeling and forecasting accuracy. A combined approach of detrending and deseasonalization is shown to be the most effective data preprocessing technique that can yield the best forecasting result.

scholarly journals A design methodology for approximate multipliers in convolutional neural networks: A case of MNIST

2021 ◽  
Vol 10 (1) ◽  
pp. 1
Author(s):  
Kenta Shirane ◽  
Takahiro Yamamoto ◽  
Hiroyuki Tomiyama
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Design Methodology ◽  
Critical Path ◽  
High Accuracy ◽  
Path Delay ◽  
Trade Off ◽  
Critical Path Delay

In this paper, we present a case study on approximate multipliers for MNIST Convolutional Neural Network (CNN). We apply approximate multipliers with different bit-width to the convolution layer in MNIST CNN, evaluate the accuracy of MNIST classification, and analyze the trade-off between approximate multiplier’s area, critical path delay and the accuracy. Based on the results of the evaluation and analysis, we propose a design methodology for approximate multipliers. The approximate multipliers consist of some partial products, which are carefully selected according to the CNN input. With this methodology, we further reduce the area and the delay of the multipliers with keeping high accuracy of the MNIST classification.

scholarly journals Research and Application of a Novel Combined Model Based on Multiobjective Optimization for Multistep-Ahead Electric Load Forecasting

Energies ◽  
2019 ◽  
Vol 12 (10) ◽  
pp. 1931 ◽  
Author(s):  
Yechi Zhang ◽  
Jianzhou Wang ◽  
Haiyan Lu
Keyword(s):  
Power Distribution ◽  
Data Preprocessing ◽  
Combined Model ◽  
Forecasting Accuracy ◽  
Forecasting Models ◽  
Power Stations ◽  
South Wales ◽  
Model Combining ◽  
Forecasting Performance ◽  
Preprocessing Technique

Accurate forecasting of electric loads has a great impact on actual power generation, power distribution, and tariff pricing. Therefore, in recent years, scholars all over the world have been proposing more forecasting models aimed at improving forecasting performance; however, many of them are conventional forecasting models which do not take the limitations of individual predicting models or data preprocessing into account, leading to poor forecasting accuracy. In this study, to overcome these drawbacks, a novel model combining a data preprocessing technique, forecasting algorithms and an advanced optimization algorithm is developed. Thirty-minute electrical load data from power stations in New South Wales and Queensland, Australia, are used as the testing data to estimate our proposed model’s effectiveness. From experimental results, our proposed combined model shows absolute superiority in both forecasting accuracy and forecasting stability compared with other conventional forecasting models.

Static and Dynamic Neural Networks for Simulation and Optimization of Cogeneration Systems

2006 ◽  
Author(s):  
Roozbeh Zomorodian ◽  
Hiwa Khaledi ◽  
Mohammad Bagher Ghofrani
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Sensitivity Study ◽  
State Behavior ◽  
Pinch Point ◽  
Dynamic Neural Networks ◽  
Simulation And Optimization ◽  
Whole Plant ◽  
Feed Forward Neural Networks

In this paper, the application of neural networks for simulation and optimization of the cogeneration systems has been presented. CGAM problem, a benchmark in cogeneration systems, is chosen as a case study. Thermodynamic model includes precise modeling of the whole plant. For simulation of the steady sate behavior, the static neural network is applied. Then using dynamic neural network, plant is optimized thermodynamically. Multi layer feed forward neural networks is chosen as static net and recurrent neural networks as dynamic net. The steady state behavior of CGAM problem is simulated by MFNN. Subsequently, it is optimized by dynamic net. Results of static net have excellence agreement with simulator data. Dynamic net shows that in thermodynamic optimization condition, σ and pinch point temperature difference have the lowest value, while CPR reaches a high value. Sensitivity study shows turbomachinery efficiencies have the highest effect on the performance of the system in optimum condition.

ESTABLISHING AN INDEX ARBITRAGE MODEL BY APPLYING NEURAL NETWORKS METHOD — A CASE STUDY OF NIKKEI 225 INDEX

2001 ◽  
Vol 11 (05) ◽  
pp. 489-496
Author(s):  
AN-PIN CHEN ◽  
CHIEH-YOW CHIANGLIN ◽  
HISU-PEI CHUNG
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Stock Index ◽  
The Neural Network ◽  
Time Period ◽  
Network Method ◽  
Index Arbitrage ◽  
Impact Risk ◽  
Cost Of Carry

This paper applies the neural network method to establish an index arbitrage model and compares the arbitrage performances to that from traditional cost of carry arbitrage model. From the empirical results of the Nikkei 225 stock index market, following conclusions can be stated: (1) The basis will get enlarged for a time period, more profitability may be obtained from the trend. (2) If the neural network is applied within the index arbitrage model, twofold of return would be obtained than traditional arbitrage model can do. (3) If the T_basis has volatile trend, the neural network arbitrage model will ignore the peak. Although arbitrageur would lose the chance to get profit, they may reduce the market impact risk.

scholarly journals SUPERIORITY OF ARTIFICIAL NEURAL NETWORKS OVER STATISTICAL METHODS IN PREDICTION OF THE OPTIMAL LENGTH OF ROCK BOLTS

2012 ◽  
Vol 18 (5) ◽  
pp. 655-661 ◽  
Author(s):  
Hadi Hasanzadehshooiili ◽  
Ali Lakirouhani ◽  
Jurgis Medzvieckas
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Statistical Models ◽  
Network Modeling ◽  
Neural Network Modeling ◽  
Rock Bolts ◽  
Optimal Length ◽  
The Neural Network ◽  
Rock Bolting ◽  
Geological Conditions

Rock bolting is one of the most important support systems used for rock structures. Rock bolts are widely used in underground excavations as they are suitable for a wide range of geological conditions and allow using progressive design methods; besides, they help economising in the use of materials and manpower. Thus, to provide the most effective support at minimum cost by means of rock bolting, it is essential to optimise the elements contributing to bolt design, including their length, as well as bolt density and tension during installation. This paper considers the length of bolts for optimisation of the design phase, which is one of the most important parameters impacting the entire design procedure. Presenting and comparing results of some statistical models, neural network modeling is introduced as powerful means in prediction of the optimal length of rock bolts. Subsequent to training and testing of a large number of 1-layer and 2-layer backpropagation neural networks, it was reported that the optimal model was the network with the architecture of 6-18-3-1 as it demonstrated the minimum RMSE and MAE as well as the maximum R2. In comparison to statistical models (0.7182 for the value of R2 in the multiple linear regression model, 0.68 in the polynomial model and 0.7 in the dimensionless model), the results obtained by the neural network modeling – i.e. the coefficient of determination R2 of 0.9259, the value of mean absolute error MAE of 0.068, and the root mean squared error RMSE of 0.078 – not only proved their superiority but also introduced the neural network modelling as a highly capable prediction tool in forecasting the optimal length of rock bolts. Furthermore, sensitivity analysis was used to obtain parameters that have the greatest and the least impact on the optimal bolt length: the effect of the overburden thickness, tensile strength, cohesion and Poisson's ratio on the optimal bolt length was almost the same while the friction angle had the least influence.

Study on the Combination of SOM and K-Means Algorithms in Manufacturing Process Quality Control

2013 ◽  
Vol 427-429 ◽  
pp. 1315-1318 ◽  
Author(s):  
Yi Bing Li ◽  
Fei Pan
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Quality Control ◽  
Manufacturing Process ◽  
Low Cost ◽  
Research Topic ◽  
High Quality ◽  
Neural Network Algorithm ◽  
Som Neural Network

Nowadays, customers are seeking products of high quality and low cost. The use of neural networks in quality control has been a popular research topic over the last decade. An adaptive self-organizing mapping (SOM) neural network algorithm is proposed to overcome the shortages of traditional neural networks in this paper. In order to improve the classification effectiveness of SOM neural network, this paper designs an improved SOM neural network, which combined the SOM and K-means algorithms. The flow of combination of SOM and K-means algorithms was analyzed in this paper. And the case study of cement slide shoe bearing in manufacturing process was also given to illustrate the feasible and effective.

Sign in / Sign up

Export Citation Format

Share Document