Skip to content

Latest commit

 

History

History
20 lines (15 loc) · 1.3 KB

README.md

File metadata and controls

20 lines (15 loc) · 1.3 KB
Raw

Bank Direct Marketing Classification

USING MACHINE LEARNING FOR BANK DIRECT MARKETING: AN APPLICATION OF THE CRISP-DM METHODOLOGY

Overview

In this third practical application assignment, we compare the performance of the classifiers (k-nearest neighbors, logistic regression, decision trees, and support vector machines). The dataset is from UCI with the marketing of bank products over the telephone in Portugal.

Data

The dataset used comes from the UCI Machine Learning repository. The data is from a Portuguese banking institution and is a collection of the results of multiple marketing campaigns.

Deliverables:

After understanding, preparing and modeling the data, I built two Jupyter Notebooks that include a clear statement demonstrating my knowledge of the business problem, a correct and concise interpretation of descriptive and inferential statistics, my findings, and next steps and recommendations. I compare the performance of the classifiers (k-nearest neighbors, logistic regression, decision trees, and support vector machines).

I have attached the following three files.

  1. “Practical_Application_III_TB_1_Intro_and_EDA_Final.ipynb”
  2. Practical Application III-TB-1-FeatureEngr-Modelling-Classification-Final.ipynb
  3. A pdf document with a summary of the classification models