Full 16-Session Syllabus
Integrated 8-week (16-session) Data Science & AI curriculum matrix with learning outcomes, credit hours, and SKKNI No. 299/2020 units.
This document contains the comprehensive syllabus for the Data Science & Artificial Intelligence learning program, compiled by Mahendar Dwi Payana, referencing SKKNI No. 299 of 2020 and the Thematic Academy curriculum of DTS Kominfo RI with STEI ITB.
16-Session Curriculum Matrix
| Session | Topic | Learning Outcome | SKKNI Unit Code | Hours |
|---|---|---|---|---|
| 01 | Modern Computing Environment Setup & AI Tools | Prepare a Python 3.10+ interpreter, virtual environments (venv/conda), JupyterLab, VS Code, Google Colab, and GPU acceleration (CUDA/MPS). | Computing Foundations | 2 JP Class 4 JP Self-study |
| 02 | AI Fundamentals, Technology & Applications | Understand the 4 AI definition paradigms, PEAS intelligent agent architecture, 7 task-environment types, problem-solving taxonomy, Industry 4.0 ecosystem, and Stranas KA 2020–2045. | AI Foundations | 2 JP Class 4 JP Self-study |
| 03 | Data-Driven Data Science Methodology | Master industry methodologies (CRISP-DM, KDD, SEMMA, TDSP), 21 SKKNI No. 299/2020 units, and an integrated Python case study on DKI 2016 infant immunization data. | AI Methodology | 2 JP Class 4 JP Self-study |
| 04 | Tools for Data Science | Master Python advantages, IDE/Colab ecosystem, Git/GitHub, 6 core libraries, NumPy vectorization vs. list TypeError, and analysis of Tab.csv and pmp_2020_baru.csv. | Numeric Computing | 2 JP Class 4 JP Self-study |
| 05 | Business Understanding & AI Project Planning | Formulate AI vs. automation, end-to-end ML paradigms, asymmetric financial cost analysis, and real AI project design (Tata Global stock & autonomous vehicles). | J.62DMI00.001.1J.62DMI00.002.1J.62DMI00.003.1 | 2 JP Class 4 JP Self-study |
| 06 | Data Understanding (Non-Visualization) | Master Stevens’ 4 scales, 3 structured data models, multi-source data acquisition techniques, non-visual descriptive statistics, and case studies on car characteristics and EPL players. | J.62DMI00.004.1J.62DMI00.005.1 | 2 JP Class 4 JP Self-study |
| 07 | Exploratory Data Analysis & Statistical Visualization | Master variable vs. statistical visualization, one-way ANOVA F-test (car wheel drive), and complete 5 official statistics notebook exercises. | J.62DMI00.005.1 | 2 JP Class 4 JP Self-study |
| 08 | Data Preparation: Object Selection, Cleaning & Validation | Determine data objects via sampling (probability vs. non-probability), handle imbalanced datasets (SMOTE), 3 feature selection techniques (Chi2, Extra Trees, Heatmap), and clean real datasets (British Library, University Towns, Olympics). | J.62DMI00.006.1J.62DMI00.007.1J.62DMI00.008.1 | 2 JP Class 4 JP Self-study |
| 09 | Numeric Data Construction & Transformation | Perform normalization, standardization (MinMax, Robust, Standard Scaler), and distribution transformation (Log, Box-Cox, Yeo-Johnson). | J.62DMI00.009.1 | 2 JP Class 4 JP Self-study |
| 10 | Feature Engineering, Encoding, Data Integration & Labeling | Perform categorical encoding (One-Hot, Dummy, Target), table integration (Merge & Join), PCA feature extraction, Pseudo-Labelling, feature selection, and label assignment. | J.62DMI00.009.1J.62DMI00.010.1J.62DMI00.011.1 | 2 JP Class 4 JP Self-study |
| 11 | Modeling Scenarios & Supervised Classification | Design validation scenarios (Train-Validation Split, K-Fold, Scikit-learn Pipeline) and train/tune classification models (Logistic Regression, SVM, Decision Tree, Naive Bayes, KNN, AdaBoost) on the Iris dataset. | J.62DMI00.012.1J.62DMI00.013.1 | 2 JP Class 4 JP Self-study |
| 12 | Numeric Regression Modeling | Train simple & multiple linear regression, polynomial/non-linear regression, SVR, Decision Tree, and Random Forest Regression; test Gauss-Markov assumptions and evaluate with MAE/MSE/RMSE/R². | J.62DMI00.013.1 | 2 JP Class 4 JP Self-study |
| 13 | Unsupervised Learning & Clustering | Perform unsupervised data segmentation using K-Means++, Hierarchical Agglomerative, DBSCAN, and Silhouette evaluation. | J.62DMI00.013.1 | 2 JP Class 4 JP Self-study |
| 14 | Deep Learning & Artificial Neural Networks | Understand Perceptron, Multilayer Perceptron, activation functions, Backpropagation, gradient descent, adaptive learning rate (Adam), and apply ANN, CNN (Conv/Pooling), and RNN with Scikit-learn & Keras. | J.62DMI00.013.1 | 2 JP Class 4 JP Self-study |
| 15 | Model Evaluation & Diagnostic Review | Evaluate model performance via Confusion Matrix, Precision/Recall/F1, ROC-AUC, PR-Curve, Log Loss, regression metrics (MAE/MSE/RMSE/R²), clustering metrics (Silhouette/Davies-Bouldin), model comparison (McNemar’s Test), and feature interpretation with SHAP. | J.62DMI00.014.1J.62DMI00.015.1 | 2 JP Class 4 JP Self-study |
| 16 | Web Model Deployment & MLOps | Understand deployment concepts & patterns (static, dynamic on-device/on-server), Single/Silent/Canary strategies, reproducibility, model serialization (pickle/H5), and deploy Linear Regression & ANN models to the web (Flask/Heroku, FastAPI/Streamlit) with drift monitoring. | J.62DMI00.016.1J.62DMI00.017.1 | 2 JP Class 4 JP Self-study |
Credit Hour Distribution
- Total Sessions: 16 Sessions (8 Weeks / Saturday & Sunday)
- Synchronous Live Sessions: 16 sessions × 2 JP = 32 JP
- Self-Paced Learning (Hands-on & LMS): 16 sessions × 4 JP = 64 JP
- Total Learning Load: 96 Credit Hours (JP) (@ 45 minutes/JP)
Data Science & AI Curriculum Portal
A structured knowledge base and 16-session Data Science & AI syllabus by Mahendar Dwi Payana, aligned with SKKNI No. 299 of 2020.
Capstone Project Guide
Comprehensive guidelines for the Data Science & AI Capstone Project based on real organizational problems, data ethics, and deployment to the public cloud.