This repository contains all the tasks, code, and documentation completed during the BCG Data Science job simulation on The Forage platform. The simulation focused on analyzing customer churn, building predictive models, and presenting insights for a major utility company.
-
Introduction
- Overview of the BCG Data Science Simulation
- Objectives and Key Learning Outcomes
-
Task 1: Data Exploration
- Exploratory Data Analysis (EDA)
- Key Findings and Data Visualizations
-
Task 2: Data Cleaning and Preprocessing
- Steps for Cleaning and Preparing the Data
- Handling Missing Values and Outliers
-
Task 3: Model Building
- Choice of Model: RandomForestClassifier
- Hyperparameter Tuning with GridSearchCV
- Evaluation Metrics: accuracy_score, classification_report, and confusion_matrix
-
Task 4: Model Evaluation
- Results and Performance Metrics
- Precision: 90%, F1 Score: 95%, Accuracy: 95%
-
Task 5: Business Recommendations
- Insights on Customer Churn
- Strategic Recommendations for PowerCo
-
Task 6: Final Report
- PowerPoint Presentation
- Summary of Findings and Recommendations
- /notebooks/: Jupyter Notebooks for each task
- /data/: Raw and Processed Data Files
- /reports/: Final Report and PowerPoint Presentation
- /images/: Visualizations and Graphs
- README.md: Detailed Explanation of the Project
- Clone the repository:
git clone https://github.com/muhammadadilnaeem/BCG-Data-Science-Job-Simulation-on-Forage-August-2024.git
- Navigate to the project directory:
cd BCG-Data-Science-Job-Simulation-on-Forage-August-2024
- Install the required libraries:
pip install -r requirements.txt
- Run the Jupyter notebooks or Python scripts.
This repository is under GNU GENERAL PUBLIC LICENSE Version 3.