Pelatihan ini sangat sesuai bagi profesional yang ingin mendapatkan pemahaman tentang penggunaan machine learning (ML) untuk manajamen risiko pada perusahaan Anda. Sekarang ini ML telah mengambil perhatian di berbagai kalangan dunia. Kebutuhan data scientist yang memahami pemodelan ML semakin besar. Melalui pelatihan ini, peserta diharapkan mendapatkan pengetahuan yang lebih mendalam mengenai bagaimana menganalisis data yang sedemikian besar (big data) pada industri keuangan, memahami metodologi fundamental ML, deep learning and neural networks dari pendekatan kuantitatif, bagaimana metode ML dapat diterapkan pada perusahaan Anda, mencari tahu aplikasi ML pada berbagai risiko utama pada perusahaan Anda serta melakukan berbagai pemodelan real ML yang dilengkapi dengan contoh langkah demi langkah dengan menggunakan program R dan Python dalam bentuk web app & mobile app.

Adapun topik bahasan meliputi:

Introduction to AI, ML, R and Python: Artificial Intelligence (AI), Machine Learning (ML), R & Python Programming Language, Applications of Machine Learning

Techniques of Machine Learning: Supervised Learning, Unsupervised Learning, Semi-supervised and Reinforcement Learning, Representation Learning

Data Management: Data Preparation, Big Data Management, Infrastructure and Technology, Dimensionality Reduction

Math Review: Concepts of Linear Algebra, Eigen Values, Vectors and Decomposition, Introduction to Calculus, Probability and Statistics, Principal Component Analysis (PCA)

Regression: Linear Regression, Ridge, Lasso, Elastic-Net Regression

Classification: Linear Regression, Ridge, Lasso, Elastic-Net Regression, Meaning and Types of Classification, Logistic Regression (LR), K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Decision Tree (CART), Bagging & Random Forest (RF), Boosting

Unsupervised Learning: Clustering: Clustering Algorithms, K-means Clustering

Introduction to Deep Learning: Meaning and importance of Deep Learning, Artificial Neural Networks (ANN), TensorFlow

Machine Learning for Credit Risk: Credit Risk Components: PD, LGD, EAD, Credit Scoring vs Credit Rating, Application Scoring, Behavioural Scoring, Exploring The Credit Data, Histogram & Outliers, Missing Data, Splitting the Dataset, Cross Validation, Overfitting Problem, Creating a Confusion Matrix, Estimate the PD using Logistic Regression, Credit Risk Prediction with SVM, CART, RF, Evaluating the Model, ROC Curve, AUC, Gini Coefficient, Practice R & Python Codes

Detecting Fraud Using Machine Learning: Exploratory Data Analysis (EDA), Summarize Dataset, Visualize Dataset, Classifications Algorithms, LR, LDA, KNN, CART, SVM, RF, Make Predictions, Evaluating the Model, Kappa, Practice R & Python Codes

Other Applications of Machine Learning: Application to Market Risk & Liquidity Risk, Early Warning Indicators, Identify Customer Transactions, Practice R & Python Codes