Applied Machine Learning In Data-Driven Systems: Case Studies In Prediction, Clustering, Recommendation, And Simulation

Abstract

With the increasing availability of massive datasets and computational resources, machine learning (ML)Has emerged as a key driver of innovation in numerous fields. This paper presents an in-depth exploration of five widely-used machine learning techniques: Decision Trees, Entity Resolution, K-Means Clustering,Monte Carlo Simulation, and ALS-based Collaborative Filtering. Each method is contextualized through a case study, illustrating its practical implementation using scalable platforms like Apache Spark and Python. We explore the theoretical foundations, implementation challenges, and domain-specific applications ofeach model. In addition to demonstrating the performance and interpretability of these algorithms, this paper highlights the trade-offs and synergies across models when applied to diverse real-world datasets. The intent is to guide practitioners and researchers in choosing the most suitable ML approach based on problem characteristics, interpretability requirements, and scalability constraints.