- Target Audience: Telecom engineers, data analysts, AI enthusiasts, students in communications/CS, professionals from telcos/ISPs
- Format: Applied learning → Explain → Demo → Hands-on → Deploy.
Module 1: Introduction to AI in Telecom
1.1 Why AI matters in Telecom (network scale, data, automation)1.2 Overview of key challenges: churn, fraud, congestion, QoS.
1.3 Dataviv OS Walkthrough - how it abstracts complexity for telecom datasets.
Activity
Load sample CDR (Call Detail Record) dataset into Dataviv, explore traffic patterns.
Module 2: Telecom Data Foundations
2.1 Types of telecom data:2.2 CDRs (voice/data usage)
2.3 Network logs (OSS/BSS)
2.4 RF signal data
2.5 IoT & sensor data from towers
2.6 Cleaning & preparing telecom datasets.
Activity:
Students prepare noisy CDR dataset → feature engineering for churn prediction.
Module 3: AI for Customer Experience
3.1 Churn prediction models (classification, survival analysis)3.2 Personalized offers with recommender systems.
3.3 NLP for customer care chatbots.
Hands-On:
Build a churn prediction model on Dataviv OS - visualize churn risk da
Module 4 - Network Optimization & Predictive Maintenance
4.1 Self-Optimizing Networks (SON) basics.4.2 Predictive maintenance using ML (time-series analysis on logs).
4.3 Real-time anomaly detection in traffic patterns.
Hands-On:
Train anomaly detection model for tower equipment logs →,l k deploy as an alerting service in OS.
Module 5- Fraud Detection in Telecom
5.1 SIM fraud, call spoofing, fake recharge detection.5.2 Using anomaly detection and graph AI for fraud.
Hands-On:
Apply anomaly detection model to detect unusual calling patterns.
Module 6 - AI for Signal & Quality Enhancement
Learning OutcomeDemonstrate AI mastery through a major research project.
6.1 Basics of Signal-to-Noise Ratio (SNR) in telecom.
6.2 AI in call quality enhancement (denoising, packet loss recovery).
6.3 Edge AI for real-time optimization.
Hands-On:
Publishing AI research or deploying a real-world AI solution
Module 7 - AI in 5G & Beyond
7.1 AI-driven network slicing.7.2 AI for spectrum allocation & traffic prediction.
7.3 Future: 6G + AI-native networks.
Case Study Activity:
Design a mock AI strategy for a telco deploying 5G in a city.
Module 8 - Capstone Project
Learners pick one applied project and build end-to-end:7.1 Churn predictor with personalized retention offers.
7.2 Fraud detection engine for CDRs.
7.3 Predictive maintenance system for towers.
7.4 AI-assisted customer support chatbot.
7.5 QoS monitoring & signal anomaly detection.
Deliverable:
Deployed model on Dataviv OS + short presentation/demo.
Learning Outcome
By the end of the course, learners will: