Risk Flow Academy
← Back to Academy

Curriculum

1
.
Intake Method
This module explores the role of internal and external data sources in digital risk processing. It covers different data types, examines data enrichment techniques and introduces the five pillars of data analytics strategy, offering insight into how data shapes decision-making and risk assessment.
View moduleNotify when available
Chapters:
2
.
Classification
This module offers a thorough introduction to classification systems and taxonomy design, crucial for efficient data management. It encompasses fundamental concepts, strategies, and iterative methods for optimising taxonomies, aiming to improve classification accuracy and usability.
View moduleNotify when available
Chapters:
3
.
Extraction
This module is a comprehensive guide to implementing data extraction techniques. It covers foundational concepts, deployment strategies, and optimization methods to meet specific success criteria. Emphasising practical methodologies and best practices, it ensures effective data extraction.
View moduleNotify when available
Chapters:
4
.
Validation
This module explores validation in classification tasks, covering principles, approaches, and techniques. It examines methods for evaluating classification steps and results, emphasising practical application and critical analysis for robust validation practices.
View moduleNotify when available
Chapters:
5
.
Data Sources
This module explores the role of internal and external data sources in digital risk processing. It covers different data types, examines data enrichment techniques and introduces the five pillars of data analytics strategy, offering insight into how data shapes decision-making and risk assessment.
View moduleNotify when available
Chapters:
6
.
Risk Flows
This module offers a deep dive into digitization's impact on risk processing workflows. It covers existing digital workflows, highlights the benefits of continuous optimization, and discusses the influence of digital workflows on productivity and broker experience.
View moduleNotify when available
Chapters:
7
.
Schema
This module provides a guide to creating schemas, extractors, and workflows for data extraction and processing. It includes information on the submission process to ensure accurate and effective data extraction workflows.
View moduleNotify when available
Chapters:
8
.
Outputs
This module offers an exploration of output connectors in digital risk processing , highlighting the significance of "Human in the Loop" for data accuracy and examines the functionalities of the Console: Inbox, focusing on its role in managing exceptions.
View moduleNotify when available
Chapters:
1
.
Introducing Cytora

Intake Method

1
.
Introduction to Classification

Classification

1
.
Introduction to Validation

Validation

1
.
Introduction: Digitising the Workflow

Risk Flows

1
.
Introduction to Schema

Schema

1
.
The Role of Data in the Underwriting Process

Data Sources

1
.
Output connectors

Outputs

1
.
Introduction to Extraction

Extraction

2
.
How the Input process begins

Intake Method

2
.
Automated LLM (Large Language Models) Driven Technology

Classification

2
.
Approaches and Techniques used in the Validation Process

Validation

2
.
Digital risk processings: the existing workflows

Risk Flows

2
.
Creating a Schema

Schema

2
.
Data Standardisation

Data Sources

2
.
Console: Inbox

Outputs

2
.
Challenges and Complexities in Extraction

Extraction

3
.
Challenges experienced in receiving and collecting items

Intake Method

3
.
Triage in Classification

Classification

3
.
Evaluation of the Classification Steps

Validation

3
.
Continuous Optimisation: what do digital workflows solve

Risk Flows

3
.
Question Block

Schema

3
.
Answer Block

Schema

3
.
Data Integration

Data Sources

3
.
Concept: Human in the Loop

Outputs

3
.
Maximising the value of digitized risk data

Extraction

4
.
Input Methods

Intake Method

4
.
Accuracy in Classification

Classification

4
.
Evaluation of Results

Validation

4
.
Productivity and Broker Experience

Risk Flows

4
.
Creating an Extractor

Schema

4
.
The Four Types of Data

Data Sources

4
.
Exceptions

Outputs

4
.
Best Practices for Data Extraction

Extraction

5
.
Application Programming Interface (API)

Intake Method

5
.
Creating a Workflow

Schema

5
.
Data vs Inferred Data

Data Sources

5
.
Defining a Taxonomy

Classification

5
.
Leveraging Digital Risk Processing platforms for Data Extraction

Extraction

6
.
Fully Digitised Intake

Intake Method

6
.
Uploading submissions for training

Schema

6
.
Where data comes from

Data Sources

6
.
Achieving an Optimal Taxonomy

Classification

7
.
Training an Extractor

Schema

7
.
Where inferred data comes from

Data Sources

7
.
Cytora Configuration of Classification and Extraction

Classification

8
.
Submissions

Schema

8
.
Data Enrichment

Data Sources

9
.
The Five Pillars of Data Analytics Strategy in Insurance

Data Sources

By using this website you agree to our cookie policy
Okay