OralPresentation_TeamStochastic(FINAL_Turn in)x

Download Report

Transcript OralPresentation_TeamStochastic(FINAL_Turn in)x

CSTEP
Cluster Sampling for
Tail Estimation of
Probability
Project Team and Faculty
Created by:
Alan Chandler
Nathan Wood
Eric Brown
Temourshah Ahmady
Faculty Advisor:
Dr. James Schwing
Client:
Dr. Yvonne Chueh
Project Overview
 Project
Title:
Scenario Reduction
Technique for Stochastic
Financial Modeling: A
Distance-Clustering
Sampling Tool Giving Tail
Probability Estimation
Tail Probability Estimation
 Actuarial
sciences
 Randomly generated “scenarios”
represent financial rate changes
over h years
{i1, i2, i3, i4, i5, i6, i7, i8, i9…ih)
 Each
population of scenarios
typically more than 10,000
Cluster Sampling
 Cluster
sampling identifies
representative scenarios of
extreme cases and their
probability
 50 to 100 samples
desired
 Nested sampling
Extreme scenarios
Sampling Methods
 Three
methods used to identify
representative samples (pivots)
 Significance Method
 Euclidean Distance
Method
 Present Value
Distance Method
Clustering Algorithm
 Euclidean
Distance Method and
Present Value Distance Method
Sample
Sample
Sample
Sample
Sample
Sample
Problem to Solve
 Insurance
firms, as well as
actuarial research
 Populations stored in
spreadsheets
 Macros within spreadsheets
used to calculate samples
Problem to Solve
 Macros
are:
 Too slow
 Difficult to implement
 A hassle to use
 Provide
a stand-alone desktop
application that is user-friendly
and efficient
Basic Design
 Waterfall
Process Model
Requirements
Design
Construction
Testing
Installation
 Programming
Prototype
languages
 C# – Graphical User Interface
 C++ – Sampling algorithm
 Lua – Formula scripts
Project Requirements
 Use
Cases
Example Use Case
 Process
New Data
 Import data
 Select formula
 Choose parameters
 Start processing
 Export Data
Three Stages of Completion
 Stage
1:
 Import universe, read in
scenario data
 Apply distance formula to
universe
 Output to new spreadsheet
Three Stages of Completion
 Stage
2:
 Import universe, read in
scenario data
 Apply distance formula to
universe
 Edit formula constants to users
needs
 Output to new spreadsheet
Three Stages of Completion
 Stage
3:
 Import universe, read in
scenario data
 Edit universe from program
 Use nested samples
 Apply distance formula to
universe
 Edit formulas to users needs
 Output to new spreadsheet
Nonfunctional Requirements
 Performance
Constraints
 Size of input
 Time to process
 Memory available
 Other
Constraints
 Windows (XP, Vista, 7)
 Numeric precision
Prototype Demo…
Quality Assurance and
Risk Management
 Client
acceptance of prototype
and requirements
 Present the prototype to the client
 Received client’s feedback about
the prototype
 Modified the project based on
client’s feedback
 Client approved the final version of
the prototype and requirements
Risk Analysis
 Unexpected
events: (illness,
injuries, family problems)
 Project does not meet client
needs and expectations
 Project falls behind
Risk Analysis
 Strategies
to mitigate the risk
 Efficient and effective team work
 Good communication with client and
advisor
 Ensuring that at least two members
can perform a specific task
Wrapping Up
 Creating
a project for tail
estimation probability is
feasible
 Collecting requirements
 Learning about project
 Design decisions
Question and Answer