Resume screening is the process of assessing candidates' resumes to determine their suitability for a particular position. The purpose of resume screening is to identify the most qualified candidates who meet the requirements for the job. Conventionally, resume screening has been a manual process, with hiring managers spending significant time reviewing each resume individually. Besides the fact that it is a time-consuming procedure, there are also unknown biases. Therefore, it is important to research the methods for automating resume screening using Artificial Intelligence and Machine Learning. To address this, this paper proposes a two-phase model named “Prospect” based on feature extraction and matching using machine learning. The first phase pre-processes the dataset and extracts resume content by using feature extraction. The second phase applies “selection” and “rejection” classification by applying a matching score algorithm and custom logic. To validate its approach, this paper also designs a unique Prospect dataset with approximately 5,000(thousand) resumes, which incorporates different data sets to generate an unbiased classification output. Experimental result shows that the Prospect model categorizes the resume in “selected” and “rejected” categories with a 93.5% accuracy which improves the overall accuracy by 19.5% compared to convolutional neural network models.