Bank Term Deposition Marketing Campaigns Outcome Classification…
Ren Kylo
Data Scientist
ML Engineer
Data Analyst
Python
Bank Term Deposition Marketing Campaigns Outcome Classification Prediction Model
This is a Jupyter project demonstrate on classification model training. You may visit the presentation slide below.
Dataset Overview
The data model study below is based on Kaggle open dataset: https://www.kaggle.com/datasets/thedevastator/bank-term-deposit-predictions
This dataset, titled Direct Marketing Campaigns for Bank Term Deposits, is a collection of data related to the direct marketing campaigns conducted by a Portuguese banking institution. These campaigns primarily involved phone calls with customers, and the objective was to determine whether or not a customer would subscribe to a term deposit offered by the bank. Most of the outcomes of the dataset is 'unsuccessful' (i.e. unbalanced data), therefore the study will prioritize on balanced accuracy (i.e. simple average accuracy of successful and unsuccessful outcome, instead of weight average accuracy of the two outcomes) and recall.
Objective
The goal is to predict the outcome of the marketing campaign by training model with provided data, and study what are the key factors affecting the result.
Model Training Flow
Data Cleaning & Exploration
Data Transformation
Model Selection
Base Model Training
Feature Engineering and Model Finetune
Conclusion
