Advanced AI Course with Data Analytics and Machine Learning (Level 1)

Duration: 60 hours

Delivery Mode: Hybrid (Theory + Hands-on + Self-Study) 

Tools: Python, Pandas, NumPy, Scikit-learn, Matplotlib/Seaborn, KNIME, Jupyter

Fees: 24999/-

Syllabus  

WEEK 1: Data Analytics Fundamentals & Statistics 

Day 1 – Business Analytics Foundation 

• Introduction to Business & Data Analytics 

• Case Studies and Use Cases in Industry 

• Data-driven Decision Making 

• Types of Data, Scales of Measurement 

Day 2 – Descriptive Statistics & Probability 

• Mean, Median, Mode, Variance, Std Dev 

• Probability Theory Basics 

• Probability Distributions: ◦ Normal, Binomial, Poisson 

Day 3 – Sampling and Inference 

• Sampling Techniques 

• Central Limit Theorem 

• Confidence Intervals 

• Hypothesis Testing: Z-test, Chi-Square Test 

Day 4 – Correlation, Regression & Outliers 

• Correlation & Covariance 

• Pearson Correlation 

• Simple Linear Regression 

• Detecting Outliers, Skewness 

Day 5 – Tools & Hands-On 

• Python Setup for Analytics 

• Pandas, NumPy, Matplotlib, Seaborn 

• Exploratory Data Analysis Lab 

WEEK 2: Machine Learning Concepts and Feature Engineering 

Day 6 – ML in a Nutshell 

• Types of ML: Supervised, Unsupervised 

• ML Workflow: From Data to Model 

• Applications in Finance, Health, Marketing 

Day 7 – Data Preparation & Cleaning 

• Handling Missing Values 

• Data Normalization & Scaling 

• Feature Encoding: Label & One-hot 

• Outlier Removal Techniques 

Day 8 – Feature Engineering & Dimensionality Reduction 

• Feature Creation & Selection 

• PCA (Principal Component Analysis) 

• t-SNE for Data Visualization 

• Introduction to KNIME 

Day 9 – Supervised ML Algorithms 

• Linear Regression (Ridge/Lasso) 

• Logistic Regression 

• Decision Trees, Oblique Trees 

• KNN and SVM 

Day 10 – Hands-On Lab 

• Preprocessing Pipeline 

• Model Training and Evaluation using Scikit-learn 

• Cross-validation, Overfitting Control 

WEEK 3: Advanced ML Algorithms & Evaluation 

Day 11 – Ensemble Learning 

• Random Forests 

• Bagging vs. Boosting 

• Gradient Boosting (XGBoost, LightGBM) 

Day 12 – Unsupervised Learning 

• K-Means, DBSCAN 

• Clustering Evaluation Metrics 

• Association Rules & Apriori Algorithm 

Day 13 – Recommender Systems & Time Series 

• Content-based & Collaborative Filtering 

• Intro to Time Series Forecasting (ARIMA) 

Day 14 – Anomaly Detection 

• Isolation Forest 

• Use Case: Fraud & Intrusion Detection 

• Hands-on Implementation 

Day 15 – Model Metrics & Evaluation 

• Confusion Matrix, Precision, Recall 

• F1 Score, ROC-AUC • MSE, RMSE, MAE 

• Use of these metrics in real-world decisions 

WEEK 4: Applications, Deployment & Capstone 

Day 16 – Real-Time ML & Model Deployment 

• Model Serving Concepts 

• REST APIs, Batch vs Real-Time Scoring 

• Model Monitoring Day 17 – Capstone Planning & Case Study Brief 

• Credit Card Fraud Detection 

• Intrusion Detection System 

• Business Recommendation System 

Day 18–19 – Capstone Execution 

• Data Preparation 

• Model Selection 

• Evaluation & Optimization 

Day 20 – Capstone Review & Certification 

• Group Presentations 

• Model Walkthroughs 

• Feedback and Industry Readiness Evaluation 

• Final Assessment & Certification Distribution Self-Study (Parallel Learning – Daily) 

• Readings: “Hands-On ML with Scikit-Learn, Keras, and TensorFlow” 

• Exercises: Kaggle Competitions & Public Datasets 

• Mini Projects: Exploratory Analysis, Model Training 

• Metrics Interpretation & Confusion Matrix Deep Dive Outcome: 

• Build, evaluate, and deploy end-to-end machine learning pipelines 

• Analyze business data using statistical and machine learning techniques 

• Deliver industry-relevant solutions using Python-based ML stack