AI & Machine Learning for Banking – From Theory to Practice
AI & Machine Learning for Banking – From Theory to Practice
13 – 14 April 2026 Malang Hotel Ibis Style
Description
Kecerdasan buatan (Artificial Intelligence/AI) dan Machine Learning (ML) telah menjadi pendorong utama transformasi digital di sektor perbankan. Bank dan lembaga keuangan menggunakannya untuk:
- Analisis risiko kredit dan scoring otomatis
- Fraud detection dan anti-money laundering (AML)
- Personalization layanan nasabah dan customer experience
- Optimasi portofolio investasi dan treasury management
Pendekatan AI/ML memungkinkan pengolahan data besar (big data) untuk pengambilan keputusan lebih cepat, akurat, dan prediktif, sambil meningkatkan efisiensi operasional. Modul ini mencakup teori dasar, arsitektur ML, hingga penerapan praktis di lingkungan perbankan.
Objectives
Setelah menyelesaikan modul ini, peserta diharapkan mampu:
- Memahami konsep dasar AI dan Machine Learning.
- Menjelaskan jenis-jenis ML: supervised, unsupervised, reinforcement learning.
- Mengidentifikasi use cases AI/ML di banking: kredit, fraud, customer insight, trading.
- Menyusun pipeline ML dari data preparation hingga deployment.
- Mengaplikasikan AI/ML untuk predictive analytics dan risk management.
- Memahami risiko, bias, dan compliance terkait implementasi AI/ML di bank.
Course outline
A. Dasar AI & Machine Learning
- Definisi AI dan ML, dan perbedaan dengan statistik tradisional
- Jenis ML: supervised, unsupervised, reinforcement learning
- Algoritma populer: regression, decision trees, random forest, neural networks
- Evaluation metrics: accuracy, precision, recall, ROC-AUC
B. Data for ML in Banking
- Data sources: transactional, behavioral, social, IoT/telemetry
- Data preprocessing: cleaning, feature engineering, normalization
- Handling imbalanced data dan missing values
- Privacy, compliance (GDPR, OJK), dan keamanan data
C. ML Use Cases in Banking
- Credit risk scoring dan predictive default
- Fraud detection: anomaly detection dan pattern recognition
- Customer analytics & personalization: churn prediction, recommendation
- Algorithmic trading & portfolio optimization
- Chatbots & NLP untuk layanan digital
D. ML Pipeline & Deployment
- Problem definition & data labeling
- Model selection, training, validation, testing
- Model deployment: batch vs real-time inference
- Monitoring & model drift management
E. Risk, Ethics & Compliance
- Bias detection dan fairness dalam ML
- Interpretability dan explainable AI (XAI)
- Regulatory requirements untuk AI di banking
- Cybersecurity risks terkait ML deployment
F. Tools & Platforms
- Python, R, TensorFlow, PyTorch
- Cloud ML services: AWS SageMaker, Azure ML, GCP AI Platform
- AutoML dan low-code ML platforms
G. Case Study & Practical Exercise
- Credit scoring dengan dataset mikrofinansial
- Fraud detection menggunakan transaksi digital
- Customer segmentation untuk kampanye pemasaran bank
- Deploying ML model di cloud dan monitoring performa
Participants
- Artificial Intelligence (AI)
- Machine Learning (ML)
- Data Analytics
- Data Science
- IT / System Development
- Digital Banking
- Risk Management
- Fraud Detection
- Customer Experience (CX)
- Product Development
- Strategic Planning
- Management
- Top Management / Executive
Method
- Pre-test
- Presentation
- Discussion
- Case study
- Post-test
Facilities
- Ruang Meeting Representatif
- Sertifikat Pelatihan Resmi
- Instruktur Profesional & Berpengalaman
- Training Kit Eksklusif
- Souvenir
- Pick Up Participant (Yogyakarta)
