Predictive Analytics System Using Big Data Framework

In the realm of healthcare, big data analytics has emerged as a vital tool, especially in addressing diseases like breast cancer, which significantly impact women worldwide. This study introduces a robust and scalable pipeline model designed to analyze breast cancer data efficiently and predict the probability of breast cancer occurrence. Implemented on the Apache Spark infrastructure, the system leverages the random forest algorithm, a powerful machine learning technique. The UCI breast cancer dataset is employed as the primary source of input data. The effectiveness of the proposed system is thoroughly evaluated by comparing logistic regression against the naïve Bayes algorithm in terms of key performance metrics such as accuracy, precision, recall, and F-measure. The findings from the evaluation demonstrate the efficacy of the proposed approach, with the system achieving an impressive accuracy rate of 97.4% within the big data analytics environment.