Assessfy Pvt. Ltd Moderate 5 milestones 100 marks

Customer Churn Prediction for an Indian Telco

Target year: TE Sem 5-6 (Mini-Project-IIA/IIB) AICTE: 3 credits · ~75 hrs Bloom: Analyze MU CBCS: DS601/DS701 Mini-Project 2A/2B

Real-world project · AICTE-aligned · AI-graded · Audit-ready certificate

Enroll as Student Mentor this project

Milestones

Available mentors

Enrolled students

Core skills

About this project

Use the public Telco Churn dataset (or simulated Jio/Airtel-style data). Build classifiers (logistic regression, random forest, XGBoost). Tune via cross-validation. Interpret model with SHAP. Recommend 3 retention actions based on highest-impact features.

Course Learning Outcomes (CLOs):
CLO1: Apply tree-based + linear classifiers to a tabular business problem.
CLO2: Handle class imbalance using appropriate techniques.
CLO3: Tune hyperparameters with cross-validation.
CLO4: Explain model predictions with SHAP.
CLO5: Translate model insights into business actions.

Industry/societal relevance: Jio, Airtel, Vi all run churn-prediction pipelines internally; foundational analytics-team project. Also relevant to Indian fintech (PhonePe, GPay).

Milestones

1. Data Prep + EDA

15 marks 5d

Load IBM Telco Churn (~7k rows × 21 cols). Handle missing, encode categoricals, check class balance.

2. Baseline Models

20 marks 10d

Logistic regression + Random Forest. 5-fold CV. Report ROC-AUC + F1 for both.

3. Imbalance + Tuning

20 marks 14d

SMOTE oversampling + Optuna tuning of XGBoost. Report final ROC-AUC > 0.83.

4. SHAP Interpretation

25 marks 14d

Compute SHAP values. Top-10 most-important features globally + local explanations for 3 sample customers.

5. Business Recommendations

20 marks 14d

3 retention strategies tied to top features (e.g., "Tenure < 6 months + monthly plan" → bundled discount offer). 8-page report.

Open internships using this project -->

Upcoming sessions

Session	Window	Enrolled
Customer Churn Prediction for an Indian Telco	11 Jun 2026 to 10 Jun 2028	0

Skills you'll learn

Python MLImbalanced classification (SMOTE)Hyperparameter tuning (GridSearch + Optuna)Model interpretability (SHAP)Business-recommendation framing

Tools used

Python 3.11scikit-learnXGBoostimbalanced-learnSHAPOptunaJupyterGitHub

Prerequisites

Intro ML; Python intermediate; basic statistics; reading-comprehension on business KPIs

Available mentors

Priyang Kumar

Free

You'll earn — Certificate (PDF)

AICTE-aligned Project Completion Certificate

A formal, audit-ready PDF certificate issued by Assessfy + your institute on successful completion. Includes AICTE credit hours, your evaluator's signature, and a QR code for third-party verification.

AICTE-aligned

Certificate of Project Completion

This is to certify that

has successfully completed the project

Customer Churn Prediction for an Indian Telco

Scan to Verify

Date

Signature

Auto-issued on completion QR-verifiable

You'll earn — Digital Badge

Shareable LinkedIn / Resume Skill Badge

A compact, verifiable Open-Badges-2.0-compliant digital credential. Add to your LinkedIn profile, GitHub README, or resume in one click. Recruiters can validate authenticity via a unique URL.

Moderate

Customer Churn Prediction for an Indi…

Assessfy

Auto-issued on completion One-click LinkedIn add