Skip to content

PravallikaBonula/Bank_Marketing_SQL_Analysis

Repository files navigation

#Bank_Marketing_SQL_Analysis

Customer Analytics and campaign Effectiveness Analysis using SQL in Databricks

#Project Overview

This project leverages SQL-based data analysis to extract actionable insights from the Bank Marketing Dataset. The dataset contains customer demographic, financial, and marketing campaign details. By applying churn prediction, campaign effectiveness measurement, and customer segmentation, the project demonstrates how raw data can be transformed into strategic insights for business growth.

#Project structure

#Data Description

Features Include

• Age – Customer age

• Job – Occupation type

• Marital – Marital status

• Education – Education level

• Balance – Bank account balance

• Loan – Loan status

• Housing – Housing loan status

• Contact – Contact communication type

• Campaign – Number of contacts made during campaign

• Response – Campaign response (yes/no)

Size: Rows: ~5,000+ | Columns: 10

#Methodology

Data Preprocessing - Structured the dataset in databricks SQL Analysis - Queries for segmentation , campaign effectiveness, Churn. Insights Extraction - Identified high-risk, response patterns,and retention oppurtunities.

##SQL Queries Implemented

Customer segmentation - by Age,balance,job,marital Status.

Campaign Effectiveness - by Contact channel,occupation,education,wealth segments.

Churn Prediction - churn flagging, churn rate analysis by demographics and financial factors.

#Key Insights

Segmentation

Young , low-balance customers with loans showed the highest churn risk (68%).

Middle-aged, stabled-balance customers emerged as strong cross-selloppurtunities.

retired,high-balance customers displayed loyalty but require personalized engagement to maintain relationships.

Campaign Effectiveness

Overall campaign success rate stood at ~12% (1,652/5,000 customers).

Campaigns with more than three contact attempts resulted in dimnishing returns.

top-Performing groups : Students (36.7%) , Technicians (36.5%),Entrepeneurs(34%).

Churn Analysis

Overall churn was 66.96% (~3,348 customers).

Low-balance + active loan customers were the most vulnerable segment.

A clear overlap was observed between non-responders and churn-prone customers,Understanding disengagement as a churn predictor.

###Business Impact

Optimized Marketing ROI - Enhanced targeting of high-potential segments.

Churn Mitigation - Proactive retention of at-risk customers.

Increased Cross-selling - data driven product recommendations aligned to customer needs.

Strategic Decision-Making - Leveraging churn and segmentation insights for sustainable frowth.

tools & Technologies

**databricks (SQL) ** - data analysis 7 querying

Microsoft Word / Docs - Detailed documentation

GitHub - Project hosting & portfolio showcase

About

Customer Analytics and campaign Effectiveness Analysis using SQL in Databricks

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published