This repository contains 2 Jupyter Notebook ipynb files:
- Phase1_Group79_Predictive_Modelling_Model_Comparisions.ipynb (includes data cleaning and EDA steps)
- Phase2_Group79_Data Cleaning_EDA.ipynb (includes predictive modelling and model comparisions)
These files were submitted as the assignments for the 'Machine Learning' course during my Master's Degree at RMIT Univeristy by me and the other two team members.
Standard bank advertising is boring for both bank and their customers, despite the fact that bank marketing strategies have largely remained conventional. Thinking outside the box and implementing new marketing ideas for banks would assist in developing creative campaigns, which will support business, customer interest, and most certainly the effectiveness of actual bank marketing campaigns.
Most people consider banking to be a mundane necessity. Using innovative bank marketing concepts such as gamification, automation, chat bots, and incentives to inspire customers to use bank services could change that.
The objective of this assignment is to predict whether the customer will subscribe for the term deposit or not during the bank marketing campaigns. Building such predictive model could really help bank to identify patterns in the past bank marketing campaigns data and help them improve the future strategies for marketing campaigns. For an example, it could save effort, time and cost by targeting only customers who are more likely to subscribe for the term deposit.