Iris Species Recognition: A Fusion of Machine Learning and NoSQL Databases

This paper presents a hybrid system for classifying iris flower species using classical machine learning (ML) algorithms integrated with a NoSQL database. Utilizing the Iris dataset, the system applies algorithms such as Support Vector Machines (SVM), Logistic Regression, and Random Forest to accurately identify the species based on floral measurements. To ensure scalability, the prediction outputs are stored in MongoDB, enabling persistent, queryable storage. The study demonstrates the practical value of integrating ML with flexible data architectures for real-time applications in botany and education.