Eğitmen: Dr. H. Sait Ölmez
Eğitimin İçeriği:
- Introduction to Machine Learning
- General terminology for Machine Learning
- Types of Machine Learning
- A Primer on Exploratory Data Analysis (EDA) and Data Visualization Techniques
- Data types
- Importance of visualizing data
- Tools and techniques used in data visualization
- Data Pre-processing for Machine Learning
- Assessing the data quality, data cleaning and preparation
- Data Sampling (random, stratified, and cluster sampling)
- Variable transformation techniques
- Feature Engineering
- Dealing with Outliers
- Dealing with Missing Data
- Dealing with Imbalanced Data
- Logistic Regression
- Model Accuracy and Bias-Variance Tradeoff
- Challenges in estimating the predictive accuracy
- Concepts of under-fitting and over-fitting (bias vs variance)
- Model accuracy
- Model selection and validation techniques
- Confusion matrix and other accuracy metrics
- Naïve-Bayes Classifiers
- Instance-based Models: k Nearest Neighbors (kNN)
- Decision Trees
- Ensemble Learning Methods
- Why does an ensemble of weak learners work?
- Methods used in Ensemble Learning
- Bagging (Bootstrap Aggregating)
- Random Forest Classifier
- Extreme Trees
- Boosting
- Adaboost (ADAptive BOOSTing)
- Gradient Boosting (GB)
- Support Vector Machines (SVM)
- Unsupervised Learning: Clustering
- Major clustering approaches
- Methods of Clustering
- k–Means Clustering
- Hierarchical Clustering
- Density-based clustering
- What to use when?
Note: Numerous examples will be conducted throughout the course using Python and its related libraries (numpy, pandas, scipy, scikit-learn)
Eğitimin Hedef Kitlesi: Kurum içinde “Veri Analisti” ve/veya “Veri Bilimci” olarak çalışanlar, zaman serileri ile tahmin çalışmaları yapan analistler (quant’lar).
Eğitimin Seviyesi: Orta-İleri
Eğitim Süresi: 12 gün
Ek Bilgiler: Katılımcıların Python programlama dilini pratik seviyede kullanabildikleri ve temel seviyede İstatistik birikimleri bulunduğu varsayılmaktadır.