Improving the Efficiency of Forecasting Productivity, Using a Taguchi Experiment Design Approach (Case Study: Food Industries in Iran)

Subject Areas : Business Management

Seyed mahmon Zanjirchi ¹ , Mehdi Hatamimanesh ² , Hamedreza Kadkhodazadeh ³ , Seyedali Mohammadbanifatmi ⁴

1 - Assistant Professor of Industrial Management, Faculty of Economics, Management and Accounting, Yazd University
2 - Graduated Student, Industrial Management Department, Yazd University
3 - Master of Science (MSc), Industrial Management Department, Yazd University of Jihad
4 - Master of Science (MSc), Industrial Management Department, Yazd University

Received: 2016-01-26 Accepted : 2016-01-26 Published : 2015-03-21

Keywords: Artificial Neural Network, Productivity forecasting, Taguchi experiment design, Food material companies,

Abstract :

Productivity forecasting is a key factor in strategy planning in an organization. Artificial neural networks method is one of the productivity estimating methods whose users must have enough experience and skill because of its adjustable parameters. Trial and Error is mostly used to find the proper levels of these parameters. This article presents a seven step pattern for selecting proper adjustable parameters for neural network, using Taguchi experiment design method to improve the efficiency of productivity forecasting. As a result, the optimum parameters levels that lead to the most desirable forecasting in neural network are as follows: the number of hidden layers: 2 layers, the number of neurons in each hidden layer: 7 neurons, learning rate: 0.9 and the number of neural network inputs:  productivity indicators with more than 0.85 degree of correlation. Among the above mentioned factors, the number of hidden layers with 71.18% of contribution rate in experiment results is the most important factor in neural network design to forecast the productivity of Iranian food industry. Finally, the overall results of the study showed that using this pattern provides the possibility of choosing competitive strategies besides decreasing forecasting time and cost. Moreover, this pattern helps decision makers with the extent of the consideration that must be put into each adjustable parameter by determining the contribution rate of each parameter in the experiment results.

References:

-  AL-Zwainy, Sarhan; Hatem Rasheed & Huda Farhan Ibraheem. (2012), development of the construction productivity estimation model using artificial neural network for finishing works for floors with marble. ARPN Journal of Engineering and Applied Sciences, 7, pp 714-722.

-  Arifovik, Jasmina & Ramazan Gencay. (2013), Using genetic algorithms to select architecture of a feedforward articial neural network. Physica A, Volume 289, Issues 3–4, pp 474-594.

-  Chen, Shiyi & Amelia Paulino. (2013), Energy consumption restricted productivity re-estimates and industrial sustainability analysis in post-reform China, Energy Policy, Volume 57, pp 52-60.

-  Chen, Toly & Richard Romanowski. (2014), Forecasting the productivity of a virtual enterprise by agent-based fuzzy collaborative intelligence—With Facebook as an example, Applied Soft Computing, Volume 24, pp 511-521.

-  Culotta, Salma, Maria Galletto & Arad Macaione. (2011),  Influence of raw data analysis for the use of neural networks for win farms productivity prediction. Clean Electrical Power (ICCEP), International Conference on Italia.

-  Du jardin, Philippe. (2012), Bankruptcy prediction and neural networks: the contribution of variable selection methods. Edhec Business School-Information Technology Department, 73, pp 271-284.

-  Hong Chien-wen. (2012), Using the Taguchi method for effective market segmentation. Expert Systems with Applications, Volume 39, Issue 5, pp 5451–5459.

-  Jammazi, Rania & Chaker Aloui. (2014), Crude oil price forecasting: Experimental evidence from wavelet decomposition and neural network modeling. Energy Economics, Volume 34, Issue 3, pp 828–841

-  Muqeem, Sahan; Arin Idrus, Fateh Khamidi & Samir Zakaria. (2012), Prediction Modeling of Construction Labor Production Rates using Artificial Neural Network. 2nd International Conference on Environmental Science and Technology in Singapore.

-  Sergey, Samoilenko & Kweku Muata. (2013), Using Data Envelopment Analysis (DEA) for monitoring efficiency-based performance of productivity- driven organizations: Design and implementation of a decision support system. Omega, Volume 41, Issue 1, pp 131–142.

-  Sheikh Zahoor, Ishaque; Sarwar Azam; Ehsan Nadeem; Danial Saeed Pirzada & Nasir Zafar Moeen. (2013), identifying productivity blemishes in Pakistan automotive industry: a case study. International Journal of Productivity and Performance Management, Volume 61 Issue 2, pp 173-193.

-  Walczac, Steven & Narciso Cerpa. (2012), Heuristic Principles for the Design of Artificial Neural Networks. Informational Software Technology, Volume 41, Issue 2, 25, pp 107–117.

-  Yao Albert & Sio. (2013), Analysis and Design of a Taguchi–Grey Based Electricity Demand Predictor for Energy Management Systems, Energy Conversion and Management, Volume 45, Issues 7–8, pp 1205–1217.