In recent decades, metal additive manufacturing has evolved as a niche manufacturing process to fabricate complex shapes and a wide range of feature sizes without any unique tool. The printing quality and reliability of the part depend on the single-track characteristics of laser powder bed fusion (LPBF). The experimental quantitative prediction of single-track characteristics and the influence of process parameters is time-consuming and costly. Machine learning methods hold great potential in addressing the obstacles encountered in LPBF. This study, proposed a common supervised machine learning method to predict the printability of metal alloy. The single-track characteristics say the track width measured which is used as a basic dataset for training the prediction model. The results show that predicted single-track characteristics for the corresponding process parameters achieve accuracy greater than 80%. The proposed machine learning methodology can help in reducing the time consumption of predicting the printability of the metal alloy.