Tool wear is major factor in cutting process, which directly affects the machining precision and part quality. Thus, a tool wear monitoring system is crucial in the machining process to determine the stages of tool wear and to enable replacement of tool before catastrophic failure. In this paper, a data-driven based approach is employed to classify the tool wear stages in a CNC machine using feature vectors derived from vibration and force measurements. Three different data-driven algorithms are used namely—J-48, random forests, and LMT (logistic model tree) to classify the tool wear stages. The prediction accuracy obtained using these approaches proves the ability of machine learning methods to identify the inherent features embedded in the sensor signals to classify the stages of tool wear. Further, t-SNE plots obtained from feature vectors of vibration and force measurements individually and combined prove the effectiveness of the multi-sensor approach in tool wear estimation.