Malware is a growing concern that not only affects large businesses but the basic consumer as well. As a result, there is a need to develop tools that can identify the malicious activities of malware authors. A useful technique to achieve this is memory forensics. Memory forensics is the study of volatile data and its structures in Random Access Memory (RAM). It can be utilized to pinpoint what actions have occurred on a computer system. This dissertation utilizes memory forensics to extract relationships between objects and supervised machine learning as a novel method for identifying malicious processes in a system memory dump. In this work, the Object Association Extractor (OAE) was created to extract objects in a memory dump and label the relationships as a graph of nodes and edges. With OAE, we extracted processes from 13,882 memory images that contained malware from the repository VirusShare and 91 memory images created with benign software from the package management software Chocolatey. The final dataset contained 267,824 processes. Two feature sets were created from the processes dataset and used to train classifiers based on four classification algorithms. These classifiers were evaluated against the ZeroR method using accuracy and recall as the evaluation metrics. The experiments showed that both sets of features used to build classifiers were able to beat the ZeroR method for the Decision Tree and Random Forest algorithms. The Random Forest classifier achieved the highest performance by reaching a recall score of almost 97%.