Sand production is one of the major problems in many oil and gas assets around the world. Uncontrollable sand production can affect hydrocarbon recovery and increase operational costs. This paper aims to develop a classification approach to suggest the optimal sand control method using machine learning algorithms. Four different models have been used, namely K-Nearest Neighbors, Support Vector Machine, Random Forest and Decision Tree. After extensive exploratory data analysis, nine parameters were included in the model: Sorting coefficient D10/D95, Mass fraction smaller than 44 micron, Well deviation angle through the pay zone, Pay-zone true vertical thickness, Bottom hole pressure, Maximum oil rate, Maximum gas rate, Permeability, Well type. By comparing the different models in this study Random Forest classifier achieved the highest evaluation metrics: f1-score of 0.9568, precision of 0.9580, and recall of 0.9568 respectively. These results combined with the confusion matrix to assess the model performance have shown that up to a certain level machine learning methods can ensure the adequate completion for the candidate well. The proposed work turns out to be a potential approach that rises to the level of a decision support tool and thus can help engineers set the right completion option. Introduction Sand production has always been one of the major concerns for the oil and gas industry. It is the result of the migration of failed sand grains because of the drag forces caused by fluids flow from an unconsolidated reservoir. Generally, this phenomenon leads to technical problems such as erosion of downhole equipment and surface facilities, production loss, well access obstruction, and economic effects represented by the additional cost of sand disposal. Sand control is, therefore, necessary to mitigate the effect of sand production on hydrocarbon wells. Judhan (2016) defined sand control as all the techniques that allow hydrocarbons production without sand grains production in the wellbore. Sand control consist of two methods: passive and active. Passive sand control methods are generally used to reduce sand during the first stage of production when the sanding rate is low, as this latter gradually increase, active sand control will be required.