This article analyzes machine learning techniques in the oil and gas pipeline and automobile industries, emphasizing their impact in these domains. Machine learning (ML), a subset of artificial intelligence, which learns from the environment and takes the decision accordingly along with the heuristic learning also. Machine learning techniques such as Support Vector Machines (SVM), Random Forest (RF), K-Nearest Neighbors, Gradient Boosting Machines (XG Boost), decision trees, K-means clustering, and neural networks provide a crucial role in the above-mentioned industries to improve the performance through forecast pipeline faults, optimize maintenance, predictive maintenance, autonomous driving, and quality control. While successful, these technologies have challenges in real-time data handling, compliance interpretation, and ethical considerations in autonomous systems. The capacity of ensemble techniques to handle various data sources and the effectiveness of deep learning algorithms in extracting patterns are common benefits. However, hefty computational needs and probable are overfitting. Common limitations include the necessity for large labeled data. This paper provides a comparative analysis of various learning algorithms based on their performance metrics, which in turn visualize the predominant role and their impacts in the industries. It elaborates the performance measures of learning algorithm to enhance the productivity and early prediction of risks. Advancements in algorithm development and data management are crucial for enhancing the effectiveness of machine learning applications in these areas.