Material Cost Prediction for Jewelry Production Using Deep Learning Technique
Keywords:jewelry, deep learning, diamond price, silver price, gold price
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.
Authors who publish with Engineering Journal agree to transfer all copyright rights in and to the above work to the Engineering Journal (EJ)'s Editorial Board so that EJ's Editorial Board shall have the right to publish the work for nonprofit use in any media or form. In return, authors retain: (1) all proprietary rights other than copyright; (2) re-use of all or part of the above paper in their other work; (3) right to reproduce or authorize others to reproduce the above paper for authors' personal use or for company use if the source and EJ's copyright notice is indicated, and if the reproduction is not made for the purpose of sale.