Final project exploring KNN classifier, logistic regression, random forest, and SVM predictive models. All data obtained from Kaggle dataset - Bank Customer Churn Rate - and can be obtained by accessing the following URL: https://www.kaggle.com/datasets/shubhammeshram579/bank-customer-churn-prediction?select=Churn_Modelling.csv

The objective of this project is to develop an understanding of decision tree models, including construction of such models using random forest sampling and bootstrap aggregation (bagging) methods. All work is performed using airline satisfaction score data. For reference:<https://www.ibm.com/communities/analytics/watson-analytics-blog/sample-data-airline-survey/>).

The variance-bias tradeoff is explored in detail through application of various shrinkage and dimension reduction techniques applied to linear regression model characterizing the relationship between mdev and 11 predictor variables in the Boston dataset. LOOCV and K-Fold CV are also utilized to train and test the initial Boston regression model prior to employing any statistical modeling techniques.

Classification Analysis_Overview - KNN, LDA, Logistic Regression