Material Cost Prediction for Jewelry Production Using Deep Learning Technique

  • Chanida Phitthayanon King Mongkut’s University of Technology North Bangkok
  • Vichai Rungreunganun King Mongkut's University of Technology North Bangkok
Keywords: jewelry, deep learning, diamond price, silver price, gold price

Abstract

Production cost management is a key factor to increase industrial competitiveness. The precious metals and the gemstones comprise 65% of the jewelry material cost. Managing raw material cost is a challenging task especially when the price highly fluctuates. In this article, deep learning models were proposed to predict the prices of main raw materials of jewelry which are silver, gold, and diamond. These models are designed for Thai jewelry manufactures which are mostly small businesses. Therefore, our models only consider historical price data. This is because small businesses usually do not have access to other relevant data, i.e. oil prices and other economic data.

The proposed precious metal price model can provide prediction with RMSE of 0.00765 which is comparable to other models in literature while requires less data and offers a simpler model. Also, the proposed diamond price model can provide RMSE of 0.0181 which is 42.41% improvement from the model normally used by jewelry manufacturers.

In addition to the raw material price prediction model, a quantization method of diamond 4C grade is proposed and validated statistically and visually. This quantization method could be used in a diamond analysis.

Downloads

Download data is not yet available.

Author Biographies

Chanida Phitthayanon

Department of Industrial Engineering, Faculty of Engineering, King Mongkut’s University of Technology North Bangkok, Bangkok, Thailand

Tel. 082-9565991

Vichai Rungreunganun

Department of Industrial Engineering, Faculty of Engineering, King Mongkut’s University of Technology North Bangkok, Bangkok, Thailand

Published In
Vol 23 No 6, Nov 30, 2019
How to Cite
[1]
C. Phitthayanon and V. Rungreunganun, “Material Cost Prediction for Jewelry Production Using Deep Learning Technique”, Eng. J., vol. 23, no. 6, pp. 145-160, Nov. 2019.