An Optimized Ensemble Machine Learning Model for Predicting the Age of Abalone

Abalones are endangered marine shells that can be found off the coastlines. It is a tremendous cause of iron and pantothenic acid which is a beneficial diet reserve and farmingall over the world. By estimating the age of abalones, researchers may better understand the ecosystem and conserve this species. For predicting the same, Machine learning uses a range of techniques to quickly and precisely develop mathematical models and make accurate predictions based on previous data. In this paper, an optimized ensembled model is proposed that predicts the age of abalone from physical measurements. Ensembling is done using SMOreg and random forest machine learning models. SMOreg provides us with an accuracy of 84.5% while random forest gives an accuracy of 84.74%. While comparing and validating the performance of the proposed model with the traditional model, accuracy has increased to 90.44%.