Predicting The Age of Abalone Using Classification and Regression

The objective of this project is to develop a machine learning application capable of predicting the age of abalone using both regression and classification approaches. The dataset, containing biological measurements of abalone specimens, is preprocessed to include an actual age calculation (Rings + 1.5) and an age group categorization into “Young”, “Middle-aged”, and “Old”.Two predictive models aredeveloped:Regression Model using a Random Forest Regressor to estimate the exact age in years. Classification Model using a Random Forest Classifier to categorize the age into predefined age groups.Both models are trained within pipelines that include a OneHotEncoder for categorical preprocessing and evaluated using RMSE and accuracy metrics, respectively. The models are deployed in a user-friendly Streamlit web application that supports both manual input and batch prediction through CSV upload. Users can select between prediction types and download the results for further analysis.This dual- model deployment offers flexibility for various use cases, enabling scientific exploration, fisheries resource management, and educational purposes.