Compilation of Meet Notes: https://drive.google.com/drive/folders/1J34x9fVfvDjDwM5Jk4lSZgvkXDbmtUj7?usp=sharing
Welcome to our Business Analytics Group Project for the BUSA8000: Techniques in Business Analytics course, Session 2, 2024 at Macquarie Business School (MQBS). This project exemplifies our commitment to delivering education and research with a meaningful impact on business decision-making and society’s biggest challenges.
Objective: As Data Analysts for LuminaTech Lighting, our team is tasked with analyzing an extensive dataset related to sales, customer demographics, and product inventory. This analysis supports the management team’s strategic decisions in enhancing customer retention, refining sales strategies, and improving operational performance.
- Purpose
- Dataset Description
- Skills and Techniques
- Analysis Process
- Results and Insights
- Submission Files
The purpose of this project is to perform a comprehensive analysis of LuminaTech Lighting’s business data. We aim to provide data-driven insights that can help the company make informed decisions and drive sustainable growth.
The dataset includes:
- Sales and accounting details (order dates, fiscal data, product codes, etc.)
- Customer demographics and district codes
- Product and pricing adjustments
- Currency information related to transactions
Our project focuses on key data analysis skills such as:
- Data Cleaning: Handling missing values, correcting errors, and normalizing data
- Exploratory Data Analysis (EDA): Using Python packages for statistical and visual analysis
- Statistical Testing: Performing t-tests and regression analyses to derive significant insights
- Visualization: Presenting trends, correlations, and patterns in clear, valuable visualizations
- Predictive Modeling: Building and evaluating models to forecast future sales
- Churn Analysis: Identifying high-risk customer segments for proactive retention strategies
The analysis is broken down into six sections:
- Data Cleaning: Identifying and resolving issues in raw data (e.g., missing values, inconsistent entries).
- Exploratory Insights: Uncovering five key insights with visualizations and explanation.
- Testing Differences: Conducting two-sample tests to compare subsets of data.
- Inference: Using regression analysis to understand variable relationships and impact.
- Prediction Modeling: Developing a predictive model for sales prices in 2014.
- Churn Analysis: Examining factors contributing to customer churn.
Each section includes detailed documentation of methods, results, and their relevance to the management team’s strategic objectives.
We gained valuable insights, such as:
- Customer Retention Trends: Patterns that help in devising targeted retention strategies
- Sales and Profitability by District: Understanding which areas drive the highest profitability
- Predictive Model Accuracy: Reliable projections for future sales performance
- Factors Influencing Churn: Key indicators that signal potential customer loss
These insights support actionable recommendations that can enhance sales strategies and operational efficiency for LuminaTech Lighting.
- Group Report: A detailed document outlining the analysis, methodologies, and results (no Python code).
- Jupyter Notebook: Python code with comments for reproducibility of the analysis.
- Individual Reflection Report: Personal reflections on project teamwork, learning experiences, and growth.
We adhere to MQBS’s values of integrity, with all contributions original and compliant with academic integrity standards.
This project exemplifies our commitment at MQBS to foster analytical skills and critical thinking essential for solving real-world business challenges. We look forward to feedback to further enhance our analytical capabilities.