Problem Definition: Performing Multiclass classification to predict the Income Brackets of people from last years US Census data. Different models are used for this Multiclass classification problem to predict the income whether to <50K,<50K, 50-100K or $>100K and analysis on accuracy of using these classifiers is presented in this notebook. Additionally advantages and disadvatages of using classification model to fill the categorical Missing vaues is discussed. Feature Engineering and Hypertuning of the classifiers is performed to improve overall Models accuracy.

GitHub Logo