Course Outline
| Faculty Name: | Afzalur Rahman |
| Affiliation: | Department of Finance and Accounting |
| Email ID: | Afzalur.rahman@woxsen.edu.in |
Click here for course content
Brief Description and Relevance of the Course
The insurance industry globally and in India is undergoing a fundamental transformation driven by technology, data analytics, and artificial intelligence. This course is designed to equip MBA students with a dual lens — deep understanding of insurance and risk management principles combined with hands-on proficiency in the analytics tools and technologies reshaping the industry. Students will explore the full spectrum from insurance fundamentals and risk pooling to InsurTech innovations, AI-driven underwriting and claims, fraud analytics, climate risk, parametric insurance, and digital compliance. The course follows a learn-by-doing approach where every concept session is reinforced by a practical lab using Python, Excel, Power BI, ChatGPT, KNIME, and Looker Studio. By the end of the course, students will be capable of designing data-driven insurance solutions, building analytics dashboards, developing risk models, and evaluating InsurTech business models — making them industry-ready for roles in insurance operations, underwriting analytics, claims analytics, risk management, and InsurTech firms.
Course Intended Learning Outcomes (CILOs)
| CILO | Description | PILO Mapping | Degree of Emphasis |
| CILO-1 | Analyze insurance fundamentals, risk management principles, InsurTech innovations, and digital transformation trends in the Indian insurance context. | Business Domain Knowledge | Introduced |
| CILO-2 | Apply analytics tools (Excel, Power BI, Looker Studio, Python, KNIME) and AI technologies (ChatGPT, Machine Learning) to insurance data for underwriting, claims processing, customer analytics, fraud detection, and risk assessment. | Analytical & Quantitative Skills | Emphasised |
| CILO-3 | Design and evaluate data-driven insurance solutions including risk scoring models, parametric insurance products, fraud detection systems, compliance dashboards, and ethical AI governance frameworks for digital risk management. | Technology, Innovation & Ethics | Emphasised |
Reading Material Recommended
| Code | Textbook / Report Name | Edition / Year | CILO Mapped |
| TB1 | Insurance: Principles and Practice — M. N. Mishra & S. B. Mishra | 22nd Edition, 2020 | CILO-1 |
| RB1 | Risk Management and Insurance — Harrington & Niehaus | 2nd Edition, 2018 | CILO-1 |
| RB2 | Python for Data Analysis — Wes McKinney | 3rd Edition, 2022 | CILO-2, CILO-3 |
| RB3 | Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow — Aurélien Géron | 3rd Edition, 2022 | CILO-2, CILO-3 |
| RB4 | IRDAI Annual Reports and NASSCOM InsurTech Reports (Latest) | Latest | CILO-1, CILO-3 |
Session-Wise Topics and Reading / Reference
MODULE 1: Insurance Fundamentals and Digital Transformation (Sessions 1–4)
MODULE 2: Insurance Data and Analytics (Sessions 5–7)
| Session | Topic | Session Intended Learning Outcome (SILO) | Pedagogy | CILO | Reading |
| 5 | Insurance Data Sources & Cleaning | Apply data cleaning and preprocessing techniques on insurance datasets (customer, policy, claims data) using Python Pandas. | Lab-based, Hands-on (Python) | CILO-2 | TB2 |
| 6 | Data Visualization for Insurance | Create insurance data visualizations for KPIs (loss ratios, claim ratios, persistency) using Python Matplotlib and Seaborn. | Lab-based, Hands-on (Python) | CILO-2 | TB2 |
| 7 | Power BI for Insurance Analytics | Design interactive insurance dashboards in Power BI for claims analysis, policy trends, and customer segmentation. | Lab-based, Hands-on (Power BI) | CILO-2 | TB2 |
MODULE 3: InsurTech Innovations (Sessions 8–10)
| Session | Topic | Session Intended Learning Outcome (SILO) | Pedagogy | CILO | Reading |
| 8 | Introduction to InsurTech | Evaluate InsurTech evolution, global trends, and the Indian InsurTech startup landscape with business model analysis. | Lecture, Case Analysis | CILO-1 | TB1, RB4 |
| 9 | Digital Customer Acquisition | Analyze digital customer acquisition strategies and customer lifetime value using customer journey analytics in Python. | Lecture, Lab (Python) | CILO-1, CILO-2 | TB2, RB4 |
| 10 | Embedded & Usage-Based Insurance | Examine embedded insurance models and usage-based insurance (telematics, pay-as-you-drive) using sensor data analysis in Python. | Lecture, Data Analysis (Python) | CILO-1, CILO-2 | TB1, RB4 |
MODULE 4: Artificial Intelligence in Insurance (Sessions 11–14)
| Session | Topic | Session Intended Learning Outcome (SILO) | Pedagogy | CILO | Reading |
| 11 | AI & Machine Learning Fundamentals | Apply machine learning fundamentals (regression, classification, clustering) to insurance use cases using Scikit-learn. | Lab-based, Hands-on (Python) | CILO-2, CILO-3 | RB3 |
| 12 | AI for Underwriting | Build risk scoring and underwriting decision models using Python ML techniques on policyholder data. | Lab-based, Hands-on (Python) | CILO-2, CILO-3 | RB3 |
| 13 | AI for Claims Processing | Implement automated claims classification and severity prediction using Python machine learning models. | Lab-based, Hands-on (Python) | CILO-2, CILO-3 | RB3 |
| 14 | Generative AI in Insurance | Design AI-powered insurance chatbots, policy document generators, and customer interaction workflows using ChatGPT and prompt engineering. | Lab-based, Hands-on (ChatGPT) | CILO-2, CILO-3 | TB1, RB4 |
MODULE 5: Fraud Analytics and Digital Risk (Sessions 15–17)
| Session | Topic | Session Intended Learning Outcome (SILO) | Pedagogy | CILO | Reading |
| 15 | Insurance Fraud Analytics | Analyze types of insurance fraud (application fraud, claims fraud) and build fraud indicator dashboards using Power BI and Python. | Lecture, Lab (Power BI/Python) | CILO-2, CILO-3 | TB1, RB4 |
| 16 | Fraud Detection Using ML | Implement fraud detection workflows using anomaly detection algorithms in Python and KNIME Analytics Platform. | Lab-based, Hands-on (Python/KNIME) | CILO-2, CILO-3 | RB3, RB4 |
| 17 | Cyber Risk & Cyber Insurance | Evaluate cyber threats, cyber insurance products, and build a cyber risk assessment matrix for Indian enterprises. | Lecture, Case Study (Excel) | CILO-1, CILO-3 | TB1, RB4 |
MODULE 6: Climate Risk and Parametric Insurance (Sessions 18–20)
| Session | Topic | Session Intended Learning Outcome (SILO) | Pedagogy | CILO | Reading |
| 18 | Climate Risk in Insurance | Analyze climate risk impacts on insurance portfolios (property, crop, health) using Python data analysis and Looker Studio visualization. | Lecture, Lab (Python/Looker Studio) | CILO-1, CILO-2 | TB1, RB4 |
| 19 | Parametric Insurance Design | Design parametric insurance products with trigger-based payout models using Python simulation and index data. | Lab-based, Hands-on (Python) | CILO-2, CILO-3 | RB4 |
| 20 | Catastrophe Modeling & Risk Assessment | Build catastrophe risk models and assess natural disaster (cyclone, flood, earthquake) exposure using Monte Carlo simulation in Python. | Lab-based, Hands-on (Python) | CILO-2, CILO-3 | RB3, RB4 |
MODULE 7: Advanced Analytics and Business Intelligence (Sessions 21–23)
| Session | Topic | Session Intended Learning Outcome (SILO) | Pedagogy | CILO | Reading |
| 21 | Advanced Python for Insurance Analytics | Apply advanced Python techniques — time series forecasting (claim trends) and regression analysis (premium prediction) — on insurance data. | Lab-based, Hands-on (Python) | CILO-2, CILO-3 | RB2, RB3 |
| 22 | Customer Retention & Churn Analytics | Build customer retention and churn prediction models using Python ML and KNIME workflow automation. | Lab-based, Hands-on (Python/KNIME) | CILO-2, CILO-3 | RB2, RB3 |
| 23 | Looker Studio for Executive Reporting | Create executive insurance KPI dashboards (market share, profitability, regulatory metrics) using Looker Studio for management reporting. | Lab-based, Hands-on (Looker Studio) | CILO-2 | RB4 |
MODULE 8: Governance, Compliance and Capstone (Sessions 24–26)
| Session | Topic | Session Intended Learning Outcome (SILO) | Pedagogy | CILO | Reading |
| 24 | Insurance Regulations & Digital Governance | Explain IRDAI regulations, data protection frameworks (DPDP Act), and build compliance monitoring dashboards using Power BI. | Lecture, Lab (Power BI) | CILO-1, CILO-3 | TB1, RB4 |
| 25 | Ethical AI & Responsible Insurance | Evaluate ethical AI principles, identify algorithmic bias in underwriting/claims, and design an AI governance framework using ChatGPT. | Lecture, Case Discussion (ChatGPT) | CILO-1, CILO-3 | RB3, RB4 |
| 26 | Capstone Project Presentations | Present and defend a comprehensive insurance analytics capstone project integrating multiple tools, datasets, and concepts covered in the course. | Presentation, Project Defence | CILO-3 | All |
Performance Evaluation Components for the Course
| Session No. | Marks | Evaluation Form | AI Assessment Level | CILO Outcome Measured |
| 1–10 | 20 | Quiz on Insurance Fundamentals, InsurTech & Digital Transformation | 1 — No AI | CILO-1, CILO-2 |
| 11–20 | 20 | Insurance Analytics Dashboard Project | 2 — AI-Assisted Idea Generation & Structuring | CILO-2, CILO-3 |
| 21–26 | 20 | Capstone Project — Comprehensive Insurance Analytics Solution | 2 — AI-Assisted Idea Generation & Structuring | CILO-2, CILO-3 |
| End Term | 40 | End Term Practical Examination (Python/Power BI based problem solving) | 1 — No AI | CILO-1, CILO-2, CILO-3 |
| Total | 100 |
Evaluation Components & CILO Alignment
| Evaluation Component | CILO Alignment | Description |
| Quiz on Insurance Fundamentals & InsurTech (Sessions 1–10) | CILO-1, CILO-2 | This assessment evaluates students’ conceptual understanding of insurance fundamentals, risk management, digital transformation, InsurTech innovations, and basic analytics concepts through objective and short analytical questions. |
| Insurance Analytics Dashboard Project (Sessions 11–20) | CILO-2, CILO-3 | Students build an interactive analytics dashboard using Power BI, Python, or Looker Studio on a real-world insurance dataset. The dashboard must demonstrate claims analytics, underwriting insights, or fraud indicators with proper KPIs, visualizations, and business recommendations. AI tools may be used for idea structuring and code assistance. |
| Capstone Project — Comprehensive Insurance Analytics Solution (Sessions 21–26) | CILO-2, CILO-3 | Students undertake an end-to-end insurance analytics project integrating data cleaning, analysis, modeling, visualization, and business storytelling. Projects may include fraud detection systems, parametric insurance models, customer churn prediction, risk scoring engines, or AI-powered insurance chatbots. The final session includes a live presentation and defence. |
| End Term Practical Examination | CILO-1, CILO-2, CILO-3 | A 3-hour practical examination conducted in a computer lab where students solve insurance analytics problems using Python and/or Power BI. Questions assess data analysis, model building, dashboard creation, and business interpretation skills. No AI tools are permitted. |
Capstone Project Options
Students choose one of the following for their capstone project:
- Insurance Claims Dashboard — Power BI / Looker Studio dashboard analyzing claims patterns, settlement ratios, and fraud indicators
- Fraud Detection System — Python ML model with KNIME workflow for detecting suspicious insurance claims
- Insurance Chatbot — Generative AI powered customer service chatbot for policy inquiries and claims reporting
- Customer Risk Scoring Model — Python ML model for underwriting risk assessment and premium recommendation
- Claims Analytics using Python — End-to-end claims data analysis with visualization and predictive modeling
- Parametric Insurance Product Design — Python-based parametric insurance model with trigger mechanisms and payout simulation
- Customer Churn Prediction — ML model to predict policy lapses and recommend retention strategies
- Digital Risk Assessment Framework — Comprehensive framework for assessing and visualizing digital operational risks
Rubrics
CILO-1: Analyze insurance fundamentals, risk management principles, InsurTech innovations, and digital transformation trends in the Indian insurance context.
CILO-2: Apply analytics tools (Excel, Power BI, Looker Studio, Python, KNIME) and AI technologies (ChatGPT, Machine Learning) to insurance data for underwriting, claims processing, customer analytics, fraud detection, and risk assessment.
| Performance Standards | Exceeds Expectations (>80) | Meets Expectations (55–79) | Does Not Meet Expectations (<55) |
| Tool Proficiency | Demonstrates advanced proficiency across multiple analytics tools with clean, efficient, and well-documented code and visualizations. | Applies analytics tools correctly with acceptable accuracy and basic competence. | Unable to use analytics tools effectively or produces incorrect outputs. |
| Data Analysis & Interpretation | Performs sophisticated data analysis, extracts meaningful insurance insights, and translates them into actionable business recommendations. | Conducts basic analysis with reasonable interpretation and standard visualizations. | Analysis is superficial, incorrect, or lacks business relevance. |
| Model Building & Application | Builds accurate predictive models (risk scoring, fraud detection, churn) with appropriate algorithm selection and validation. | Builds functional models with acceptable methodology and basic validation. | Models are incorrect, poorly validated, or not applied to the insurance context. |
CILO-3: Design and evaluate data-driven insurance solutions including risk scoring models, parametric insurance products, fraud detection systems, compliance dashboards, and ethical AI governance frameworks for digital risk management.
| Performance Standards | Exceeds Expectations (>80) | Meets Expectations (55–79) | Does Not Meet Expectations (<55) |
| Solution Design | Designs innovative, well-structured insurance analytics solutions with clear architecture, appropriate tool selection, and stakeholder awareness. | Designs functional solutions with acceptable structure and basic justification. | Solution design is unclear, incomplete, or poorly structured. |
| Implementation Quality | Delivers fully functional implementations with robust error handling, clear documentation, and professional presentation. | Delivers working implementations with basic functionality and acceptable presentation. | Implementation is incomplete, non-functional, or poorly presented. |
| Business Impact & Ethics | Provides strong business rationale with cost-benefit awareness, risk considerations, and ethical AI principles integrated into the solution. | Provides reasonable business justification with basic awareness of risks and ethics. | Lacks business rationale or ignores ethical implications of the solution. |
Attendance & Punctuality
Regular attendance is crucial for meaningful engagement in academic discourse and collaborative learning. Students are expected to attend all classes, with exceptions granted only in rare and justified cases. Personal or voluntary activities are not considered acceptable reasons for absence. Failure to meet attendance requirements may result in your ineligibility to sit for the end-term examination and necessitate retaking the course. Punctuality is equally important, and students arriving late without valid justification may be denied entry to class.
Copyright
All teaching materials provided during the course are protected by copyright laws. These resources are intended exclusively for the academic use of enrolled students. Sharing or distributing course content outside the institution is strictly prohibited. Unauthorized use of copyrighted material violates institutional policy and may attract disciplinary consequences. Students are reminded to always respect intellectual property rights.
Student Code of Ethics
Students are expected to maintain high standards of academic integrity throughout the course. This includes honesty in assignments, examinations, and all forms of academic engagement. The Student Code of Ethics, as outlined in the handbook, provides a framework for responsible behavior. Violations such as plagiarism or cheating will result in serious academic penalties. Adherence to ethical norms fosters a respectful and credible academic environment for all.
Appendix A: Quiz on Insurance Fundamentals, InsurTech & Digital Transformation
Aligned Internal Assessment Component: Quiz (Sessions 1–10)
CILO Alignment: CILO-1, CILO-2
AI Level: No AI
This assessment evaluates students’ foundational understanding of insurance principles, risk management, digital transformation, InsurTech innovations, and basic analytics concepts.
Instructions: – Answer objective, short analytical, and case-based questions – Topics include: insurance ecosystem, risk management, business models, InsurTech, digital transformation, and basic analytics concepts – Calculators are permitted; AI tools are not allowed
Deliverables: – Individual quiz responses – Demonstrated conceptual clarity and analytical accuracy
Evaluation Criteria:
| Criteria | Weightage | Description |
| Conceptual Understanding | 30% | Clarity of insurance and risk management fundamentals |
| Industry Awareness | 25% | Knowledge of Indian insurance market, InsurTech landscape, and regulations |
| Analytical Application | 25% | Correct application of basic analytics concepts to insurance scenarios |
| Ethical & Regulatory Awareness | 20% | Recognition of ethical and regulatory dimensions in insurance |
Appendix B: Insurance Analytics Dashboard Project
Aligned Internal Assessment Component: Dashboard Project (Sessions 11–20)
CILO Alignment: CILO-2, CILO-3
AI Level: AI-Assisted Idea Generation & Structuring
This assessment develops students’ ability to build interactive analytics dashboards that communicate insurance business insights effectively.
Instructions: – Select an insurance dataset (claims, policies, customer, or fraud data) – Build an interactive dashboard using Power BI, Python, or Looker Studio – Include at least 5 KPIs, 4 visualizations, and 2 filters/slicers – Provide business recommendations based on dashboard insights – AI tools may be used only for idea structuring and code assistance
Deliverables: – Functional dashboard file (Power BI / Python / Looker Studio) – Dashboard walkthrough document with interpretation of insights
Evaluation Criteria:
| Criteria | Weightage | Description |
| Data Preparation & Integration | 20% | Quality of data cleaning, transformation, and integration |
| Visualization Design | 25% | Clarity, relevance, and interactivity of visualizations |
| KPI Selection & Analysis | 25% | Appropriateness of KPIs and depth of analytical insights |
| Business Interpretation | 20% | Quality of business recommendations derived from data |
| Presentation & Professionalism | 10% | Overall polish, labeling, and usability of the dashboard |
Appendix C: Capstone Project — Comprehensive Insurance Analytics Solution
Aligned Internal Assessment Component: Capstone Project (Sessions 21–26)
CILO Alignment: CILO-2, CILO-3
AI Level: AI-Assisted Idea Generation & Structuring
This applied project integrates all skills developed during the course — data analysis, machine learning, visualization, and business communication — into a comprehensive insurance analytics solution.
Instructions: – Choose one project from the approved list (see Capstone Project Options) – Build a complete solution using appropriate tools (Python, Power BI, KNIME, ChatGPT) – Include data preprocessing, analysis, modeling, visualization, and business recommendations – Prepare a 10-minute presentation followed by 5-minute Q&A – AI tools may be used for idea structuring, code assistance, and debugging
Deliverables: – Complete project report with methodology, code/outputs, and business recommendations – Presentation slides – Live demonstration of the working solution
Evaluation Criteria:
| Criteria | Weightage | Description |
| Problem Definition & Approach | 15% | Clarity of problem statement and appropriateness of methodology |
| Technical Implementation | 30% | Quality of code, models, and analytics implementation |
| Insights & Business Recommendations | 25% | Depth of analytical insights and actionable business recommendations |
| Visualization & Communication | 15% | Quality of visualizations, presentation, and defense |
| Innovation & Ethical Considerations | 15% | Novelty of approach, awareness of limitations, and ethical considerations |
Integrated Synthetic Insurance Dataset Strategy
To ensure consistency across the course, a single integrated synthetic insurance dataset will be used throughout all modules:
| Table | Records | Description |
| Customer Table | 5,000 customers | Demographics, location, occupation, credit score |
| Policy Table | 10,000 policies | Policy type, premium, sum assured, tenure, product details |
| Claims Table | 20,000 claims | Claim amount, type, status, settlement date, fraud flag |
| Fraud Indicators Table | 5,000 records | Suspicious patterns, historical flags, audit trail |
| Cyber Incident Table | 2,000 incidents | Breach type, severity, loss amount, industry |
| Weather / Climate Data | 3,000 records | Rainfall, temperature, cyclone data for parametric insurance modeling |
The same dataset is reused across Excel, Power BI, Python, KNIME, and Looker Studio, creating a cohesive, industry-oriented learning experience.