Implementation of Data Mining in Coal Production Control with Dashboard Integration as Decision Support System

Mining companies generally have a business model that utilizes contractors for the mining operations so the mine owners are responsible for supervising and controlling mining operations by contractors which are expected to run effectively and efficiently with the help of available technology. The objective of this study is to create a real-time dashboard as a decision support system based on the production achievement of mining contractors after being analysed using data mining techniques with K-Means clustering model. Data processing method used refers to the Cross Industry Standard Process for Data Mining (CRISP-DM) with Python programming language and the dashboard created using Tableau Desktop. There are 4 clusters formed based on the data used. The evaluation of the model was carried out with a silhouette score of 0.425, which means that the distribution of the data has not been clearly grouped. A real-time production control dashboard created as the last stage of CRISP-DM as well as a decision support system for mine owner companies. The information provided includes production achievement, achievement of production parameters, time use management and recommendations for interventions based on contractor clusters.

data mining, machine learning, coal production, visualization dashboard, contractor.