IIT Delhi Advanced Certification In Data Science And Decision Science - (Batch 04)

Module 1: Descriptive and Inferential Analysis

---

• Introduction to Data Science and Types of Data Management Enterprise Systems
• Data Visualisation - Methods and Approaches in Computer Human Interaction Principles

Learning Outcomes

• Develop knowledge about data manipulation in python
• Learn how to handle large volumes of data
• Build skills to implement machine learning using python
• Develop managerial inferences from Big Data

Module 2: Artificial Intelligence and Machine Learning

---

• Multidimensional Data handling, Regression, Unsupervised Machine Learning
• Predictive Analytics with AI/ML - Advanced Supervised and Unsupervised Machine Learning
• Machine Learning using Artificial Neural Networks and Fuzzy Set Theory
• Supervised ML - Decision Trees, Random Forest, SVM, Naïve Bayes Classifiers, Ensemble Learning

Learning Outcomes

• Learn the computational background of supervised machine learning algorithms
• Learn the computational background of unsupervised machine learning algorithms

Module 3: AI/ML for Big Data and Cognitive Science

---

• Machine Learning using Deep Learning and Convoluted Neural Networks
• NLP in Social Media Analytics - Sentiment Analysis, Text Summarisation, Topic Modelling, LDA, Network Analytics
• Network Science with Graph Theory, hands on exercises with small networks data
• Generative Artificial Intelligence and Chatbots, Large Language Models using Deep Learning

Learning Outcomes

• Build blocks for computer vision
• Understand how large-scale graphs operate in internet ecosystems
• Understand how web search and social networks operate on user generated data
• Learn to design Chatbots

Module 4: AI/ML for Managers

---

• Data model building for ML and Big Data applications - Boston City Case Study
• Governance of AI/ML - Fairness, Accountability, Transparency, Ethics, UX & Regulations
• UI driven Python (Orange), Supervised and Unsupervised Machine Learning
• Generative Artificial Intelligence, Conversational AI and Prompt Engineering
• Reinforcement Learning and Federated learning

Learning Outcomes

• Understand governance of AI/ML systems in enterprises
• Learn the evolution of code based to no-code environments for data scientists
• Master emerging machine learning paradigms for future

Module 5: Data Science Learning Enrichment & Assessment

---

• Data Science Capstone Project - Unsupervised and Supervised Machine Learning Implementations
• Individual Evaluation on Data Science and Machine Learning

Learning Outcomes

• Learn how to deploy AI/ML algorithms for data science projects
• Develop understanding on futuristic issues for data science professional

Module 1: Overview to Decision Science

---

• Understanding Main Pillars of Business Decision Science and Heuristics/Meta-Heuristics/AI
• Central Limit Theorem, Distributions, Dispersion, Population, Sample, T Test, Z Test, Chi Square Test
• Comparing Multiple Groups - ANOVA, MANOVA
• Linear Algebra - Matrix Operations, Determinants, Vectors and Eigen values

Learning Outcomes

• Understand the main pillars of Decision Science viz. Prescriptive, Predictive and Descriptive Decision Science
• To provide basics on Statistics to understand the main pillars of Decision Science

Module 2: Prescriptive Decision Science

---

• Introduction to Linear Programming (Single Objective) and solving using Solver/ LINGO
• Sensitivity Analysis using Solver/LINGO
• Goal Programming (Multiple Objectives) Using Solver/LINGO
• Application of LP/NLP in Business Decisions through Case Study

Learning Outcomes

• Understand Prescriptive Decision Science
• Develop Prescriptive models using examples
• Solve Prescriptive models
• Explain the use of Excel solver and LINGO packages in solving the prescriptive models
• Discuss practical cases to show application of Prescriptive Decision Science

Module 3: Predictive Decision Science

---

• Time Series Analysis (Moving Average, Exponential)
• Time Series Analysis (Holtz and Winter-Holts Model)
• Auto Regressive Integrated Moving Average Models

Learning Outcomes

• Understand Predictive Decision Science
• Discuss time series methods in Predictive Decision Science
• Learn regression methods in Predictive Decision Science

Module 4: Multi Criteria Decision Science

---

• Multi Criteria Decision Making: ISM, DEMATEL, AHP
• Multi Criteria Decision Making: IRP, ANP, TOPSIS

Learning Outcomes

• Understand Descriptive Decision Science
• Discuss popular Descriptive Decision Science using practical examples

Module 5: Decision Science Learning Enrichment & Assessment

---

• Decision Science Case Study Approaches
• Decision Science Capstone Project
• Individual Evaluation on Decision Science

Learning Outcomes

• Group case study presentations
• Demonstrate the real-life applications of all pillars of Decision Science
• Individual evaluation

Data Science: Students would be shared datasets with large volume of data. On that dataset, first the students need to demonstrate skills surrounding feature selection. Subsequently students need to run algorithms for unsupervised algorithms. Lastly on the data set, students need to demonstrate applications of multiple supervised machine learning algorithms and evaluate these algorithms for their suitability, given the context of the data / case setting. Project implementation may be undertaken in a combination of SPSS/PSPP, Python and Orange.

Decision Science: Participants would be exposed to all three pillars of decision science viz. prescriptive, predictive and descriptive decision making through various modules under decision science. To easily implement the concepts, practical examples would be discussed through case study-based capstone project. These tools and techniques would be discussed using Excel, Excel Solver, Python, and LINGO.