Data Request Ideation - Disaster World

Topcoder is working with a group of researchers that are competing to understand a series of simulated environments.   There are four of these environments: Urban World, Conflict World, Power World, and Disaster World. Each “world” is defined by a set of data but the full range of possible variables used to develop the simulated worlds isn’t disclosed to working groups in advance.  The research teams have to propose and request useful data and then justify how it would be collected in the target environment.
 

In this challenge, we’re asking the Topcoder Community to review the research requests that have been previously submitted by the research team for the Disaster World and to suggest additional variables that should be considered/included in analysis of these simulated world.  If you had to model behavior of agents in this environment what would you want to know? And crucially, how would you obtain that information?

 

We’re attaching 3 documents to this challenge:

1. Challenge Description.pdf - This document outlines the world parameters at a high level and the data that has been already provided.

2. Data Description.pdf - This document provides details about each field.

3. C - Disaster World Requests - This is document is a compilation of all the previous research requests and questions.  

 

There are two types of variables, stable variables and changeable variables. Stable variables do not change as time passes, while changeable variables are those which change over time. These variables only apply to Actor-pre tables and Actor-post tables. Only the following variables are changeable:

• Time

• Severity/Risk

• Dissatisfaction

• Evacuated

• Shelter

• Injured

• Wealth

 

Final Predictive Goals: Given all these data of 6 hurricanes, the Disaster World research team will develop a model to predict the outcomes for a new hurricane.

Short-term Predictions

1. Global Prediction

   1. How many people will be casualties (dying or suffering a serious injury) during the new hurricane?

   2. How many people will evacuate at least once during the new hurricane?

2. Local Prediction

   1. Which regions will suffer the highest/lowest percentage of casualties?

   2. Which regions will have the highest/lowest percentage of evacuations?

3. Individual Prediction

   1. Will TargetActor be injured or die during the new hurricane?

   2. Will TargetActor evacuate during the new hurricane?

4. Counterfactual Prediction

   1. How would your answers to questions 1-3 change if all of the area’s shelters became unusable at the end of the last hurricane in the IDP and remained unusable throughout the Hurricane Input period?

 

    Long-term Predictions

1. Global Prediction

   1. How many people will die?

   2. How many people will evacuate at least once?

2. Local Prediction

   1. Which regions will suffer the highest/lowest percentage of deaths?

   2. Which regions will have the highest/lowest percentage of residents who evacuate at least once?

3. Individual Prediction

   1. Will TargetActor survive the following hurricane season?

   2. How many times will TargetActor evacuate during the following hurricane season?

4. Counterfactual Prediction

   1. How would your answers to questions 1-3 change if, after the IDP season ends, but before the following season begins, the government taxes everyone (decreasing everyone’s wealth by 10%), thus enabling a 50% increase its aid impact during the following season?

 

The following research requests have been approved and the Disaster World team has been provided with data for the following research request and questions:

 

 

Final Submission Guidelines

Evaluation Criteria:

 

This challenge will be subjectively evaluated.   But we’ll be using the following criteria to evaluate your suggestions:

 

1. Originality - Your suggestion for a variable isn’t helpful if is has been previously suggested in the Disaster World Request Document or has already been provided.

2. Practicality of Collection Method - In addition to suggesting data, a constraint that our team is under is the ability to collect the data.  Note that in the research requests, the collection methodology is specified. Please include this.

3. Relevance - Fundamentally, we’re trying to model the movement of agents around these regions to determine whether they will evacuate in the face of danger.  The suggested variables should inform this analysis. Please describe how the proposed variable would be used in modeling this environment.

 

Submission:

 

Please submit an excel document with the following columns:

 

Variable Name

Description

Collection Method

Analytical Value/Usage

 

Prizes:  ($3000 first prize)

For this challenge, we’ll be paying a $150 for each relevant variable and associated collection method that the research team wants to include in their research requests.���