Programme Content
Session 1 – Fundamentals of BFS and Data Science:
Overview of BFS, supervised, unsupervised, semi-supervised, and reinforcement learning.
Session 2 – Data Ecosystem in Banking and ML Lifecycle:
Data quality, data preparation, feature engineering, model selection, training, validation, deployment, monitoring, and continuous improvement.
Session 3 – Fundamentals and Hands-on applications of EDA in BFS:
Banking KPI visualization, risk data compression and interpretation.
Session 4 – Fundamentals and Hands-on applications of Supervised MLs for BFS:
RF, SVM, NB, and ANN for loan default prediction, AML alerts, and fake review detection.
Session 5 – Fundamentals and Hands-on applications of Unsupervised MLs for BFS:
K-Means, K-Modes, Hierarchical, and DBSCAN for customer segmentation and wealth management.
Session 6 – Fundamentals and Hands-on applications of Deep Learning for BFS:
RNN and Bi-LSTM for predicting insurance cross-selling, fraud sequence, AML monitoring, and compliance analytics.
Session 7 – Fundamentals and Hands-on applications of recommendation systems for BFS:
Content-based Filtering and Collaborative Filtering for personalized banking offers and investment recommendations.
