Description
Credit Risk and AI Applications Training is a 5-day live online or in-person program on using data science and machine learning approaches in credit risk analysis. The content ranges from the fundamentals of artificial intelligence and data science to data preparation, modeling, and evaluation with Python. The curriculum includes financial analysis on a credit risk data set and applying different machine learning models to financial data.
The program aims to convey the core concepts of credit risk management, show where artificial intelligence and machine learning techniques can be applied, examine evaluation and modeling processes, and discuss the advantages and potential challenges of these technologies. The curriculum also covers CRISP-DM, exploratory data analysis, RFM analysis, real-time model use, and transferring models to other applications.
Who Should Attend?
- Banking sector professionals
- Data scientists and analysts
- Information technology and software development teams
- Managers looking for innovative solutions in banking
Outline
Fundamentals of Artificial Intelligence
- What is Artificial Intelligence?
- What are the Application Areas of Artificial Intelligence? Real Life Examples.
- What are the Applications of Artificial Intelligence in the Financial Sector?
- The Future and Approaches of Artificial Intelligence.
Fundamentals of Data Science
- What is Data Analysis? What Can Be Done with Data Analysis?
- What is Data Science?
- What are the Elements of Data Science?
- How Do the Stages of Extracting Useful Information from Data Work? (Data Analytics)
- Application Examples of Data Analytics in the Financial Sector
How Data Science is Applied in the Business Process Cycle
- CRISP-DM Methodology
Machine Learning
- What is Machine Learning? How Does Machine Learning Work?
- What are the Differences Between Machine Learning and Traditional Programming?
- What are the Types of Machine Learning?
- In Which Areas Do Machine Learning Algorithms Provide Solutions?
- The Future of Machine Learning
- Application Examples of Machine Learning in the Financial Sector
Deep Learning
- What is Deep Learning? How Does Deep Learning Work?
- Differences Between Machine Learning and Deep Learning
- Application Examples of Deep Learning in the Financial Sector
CRM Analytics
- What is CRM Analytics?
- What is RFM Analysis?
- What is the Relationship Between Machine Learning and CRM Analytics?
Developing Data Science Applications with Python
- Overview of the Python Programming Language
- Development Environments Used for Developing Programs with Python
- Basics of the Python Programming Language
Data Literacy
- Loading/Reading Data Sets from Files (Excel, CSV, etc.)
- Data Representation
- Understanding Data Dimensions
- Sampling in Data
- Data Types
- Basic Statistical Information
Data Preparation and Cleaning
- Understanding Data
- Viewing and Selecting Features
- Sorting and Grouping
- Operations on Features
- Operations on Observations
- Data Filtering
- Missing Data
- Duplicate Data
- Data Transformation Operations
- Detecting Outliers
- Data Visualization
Data Analysis Exercises on Financial Data Sets
- Financial Analysis on Credit Risk Data Set
- Analysis on Temporal Data Set (fetching and analyzing data from Yahoo Finance)
Developing Data Science (Artificial Intelligence) Applications – Machine Learning
Basic Concepts and Terminology
- Problem Types (Regression, Classification)
- Model
- Splitting the Data Set into Training and Test Sets
- Overfitting
- Model Validation
Types of Learning
- Supervised Learning
- Unsupervised Learning
- Reinforcement Learning
Feature Engineering
- Outlier Detection
- Data Cleaning
- Data Transformation (encoding, scaling)
- Data Reduction
- Feature Extraction
Methods for Evaluating the Success of Machine Learning Models
- Confusion Matrix
- R2 Score
- F1 Score
- AUC-ROC Curve
- Mean Absolute Error (MAE)
- Mean Squared Error (MSE)
Scikit-Learn Module and Machine Learning
Machine Learning Algorithms/Models on Financial Data Sets and Application Development
Regression Models (Theory, Model, Prediction)
- Simple Linear
- Multiple Linear
Classification Models (Theory, Model, Prediction)
- Classification with Logistic Regression
- Classification with K-Nearest Neighbors (KNN)
- Classification with Decision Trees (CART)
- Classification with Support Vector Machines (SVM)
Clustering Models (Theory, Model, Prediction) (Unsupervised Learning Application)
- Clustering with K-Means Algorithm
- Hierarchical Clustering
Boosting (Prediction) Models (Theory, Model, Prediction)
- Gradient Boosting
- XGBoost
- LightGBM
RFM (Recency, Frequency, Monetary) Analysis within CRM Analytics
- Customer Segmentation with RFM Analysis
- Clustering with K-Means (K-Means Clustering)
Real-Time (Streaming Data) Machine Learning Application
- Developing a Prediction Application for an ML Model with Data Pulled from an Online Database (Firebase)
Saving and Transferring Machine Learning Models to Other Applications
- Methods for Using Data Science Models in Different Applications
- Model Transfer with Pickle
- Model Transfer with Joblib
- Converting to Native Code with m2cgen
Prerequisites
No prerequisites are listed on the current training page. You can confirm whether prior knowledge of Python, data science, or credit risk is needed when you submit your training request.
Those who want a separate starting point for Python can explore the Python Programming for Financiers Training page. This training is not a published prerequisite for the credit risk program.
To get a training plan and price quote for your organization, you can fill out the Contact Form on this page. For other ways to get in touch, you can use the BlueMark Academy contact page.
Frequently Asked Questions
How many days does the Credit Risk and AI Applications Training last?
The training lasts 5 days.
Is the training delivered online?
Yes. The training format is listed as live online or in person.
Who is the training suitable for?
The target audience is banking professionals, data scientists, analysts, IT and software development teams, and managers looking for innovative solutions in banking.
Does the training cover Python and machine learning?
Yes. The curriculum includes data science applications with Python, scikit-learn, regression, classification, clustering, and boosting models.
Is there hands-on work on a credit risk data set?
Yes. The financial data sets section includes financial analysis on a credit risk data set.
What are the prerequisites for the training?
No prerequisites are listed on the current training page. You can confirm the required prior knowledge when you submit your training request.