Kompetensi

Data Science

Machine Learning and Predictive Analytics

This course prepares you to take the knowledge gained and apply it to their own respective data mining problems, solving them quickly and easily First part in this course will introduce the overview of a basic analytic process while second part brings in more complicated cases extended from first part The lessons learnt will be applicable to areas such as customer analytics, targeted marketing, social media analytics, fraud detection, predictive maintenance, resource management, etc

Course Objective

1. Melaksanakan proses penyediaan data yang asas.
2. Menghasilkan model ramalan.
3. Menjalankan penilaian kualiti model mengikut kriteria yang bersesuaian.
4. Mempraktikkan model ramalan analitik yang dihasilkan
5. Menjalankan proses analitis lanjutan.

Course Outcomes

1. Perform common data preparations
2. Build sophisticated predictive models
3. Evaluate model quality with respect to different criteria
4. Deploy analytical predictive models
5. Apply more sophisticated analytical approaches

Course Outline

1. Overview
   • Business Scenario
   • Analytics Taxonomy & Hierarchy
   • CRISP-DM
   • Data Analytics in the Enterprise
2. EDA: Exploratory Data Analysis
   • Loading Data
   • Quick Summary Statistics
   • Visualizing Data & Basic Chart
3. Data Preparation
   • Basic ETL (Extract, Transform, and Load)
   • Data Types and Transformations
   • Handling Missing Values
   • Handling Attribute Roles
   • Normalization and Standardization
   • Filtering Examples and Attributes
4. Predictive Model’s Algorithms
   • K-Nearest Neighbors
   • Naive Bayes
   • Linear Regression
   • Decision Tree
5. Model Construction and Evaluation
   • Machine Learning Theory: Bias, Variance, Overfitting and Underfitting
   • Split and Cross Validation
   • Applying Models
   • Optimization and Parameter Tuning
   • Evaluation Methods & Performance Criteria
6. Additional Workshops
   • Outlier Detection
   • Random Forests
   • Ensemble Modeling