Comparative Analysis of Predictive Algorithms for Performance Measurement

Abstract

Predictive algorithms, also known as mathematical models, utilize historical data to accurately predict future outcomes. These algorithms identify patterns and relationships within the data, resulting in precise predictions. The growing importance of predictive algorithms in various domains, such as finance, healthcare, marketing, weather forecasting, E-commerce, etc., has led to an increasing need for robust and accurate models. Machine learning (ML) and deep learning (DL) algorithms, including supervised, unsupervised, & reinforcement learning, play a crucial role in prediction. Supervised algorithms include classification and regression, while unsupervised algorithms primarily focus on clustering. In this study, a detailed comparative analysis of eight classification algorithms, six regression algorithms, and five clustering algorithms is performed using diverse datasets and performance metrics. ROBERTA, ResNet, Random Forest Regression, and K-means clustering algorithms outperformed traditional algorithms in textual classification, image classification, regression, and clustering. This study enables data scientists and practitioners to make informed decisions when selecting appropriate models for their specific applications.