Age Prediction Model

• The objective of the project was to develop a model to predict individual age using easily obtainable features. This would allow a correlation to be determined between certain features which could then potentially be used to inspire future research into the causes of aging.
• To ensure the best models were used, we decided to train using a variety of algorithms including a Sequential Neural Network, K-Nearest Neighbor, Linear Regression, Random Forest (RF), Univariate Training with RF, Support Vector Regression (SVR), Univariate Training with SVR, and Decision Tree.
• We found that there were few easily obtainable methods of collection that were effective predictors of aging, with bone density, vision sharpness, and hearing ability being the most effective.