Abstract: In order to solve the problems of over reliance on human experience and single procurement strategy in the process of traditional mine spare parts procurement,big data analysis technology is used to realize optimization of spare parts procurement strategy and intelligent decision-making.On the basis of sorting out the process of spare parts procurement in mining enterprises,the mining spare parts procurement prediction model with "intelligent classification of spare parts-consumption prediction of spare parts " as the core framework is constructed,and the decision-making method for guiding spare parts procurement of mining enterprises is formed.The traditional ABC classification method is extended in attribute classification,and purchase price,consumption speed,and purchase cycle are selected as the classification dimensions of spare parts,and the K-means algorithm is used to realize spare parts classification.Aiming at the procurement characteristics of different types of spare parts,the Prophet-LSTM combination prediction model was constructed,and the reasonable spare parts procurement quantity and procurement time were determined according to the prediction results,so as to realize the intelligent procurement of spare parts in mines.Based on the spare parts data of an underground gold mine in Shandong Province,the model was verified and the results showed that the application of spare parts procurement prediction model to formulate procurement plans effectively improved the management level of spare parts and scientific procurement capabilities of mining enterprises.

Key words: spare parts for mines,big data analysis,procurement strategy,cluster analysis,combination forecasting