Challenge Overview
Topcoder is working with a group of researchers organized by the University of Chicago that are competing to understand a series of simulated environments. In the Disaster World program, we are looking for predictive models to better predict severity of a simulated hurricane as it relates to a data set of virtual actors and regions. This challenge asks you to analyze and predict where aid should be directed to maximise its effectiveness and how target actors should be directed to maximise their safety.
Background
It's hurricane season in an area along the coastline. The population is diverse with distinct regions. We want to direct the government on how to direct its aid to minimise the number of casualties and we want to direct target actors to maximise their safety.Task Detail
We have some initial datasets collected as follows:
Short-Term Prescription Challenge
Instance 20 - An Urban Area
Input
1. Initial Data Package: Covering the first six hurricanes of the season
2. HurricaneInput: Additional data for the seventh hurricane of the season, contained within InstanceVariableTable
3. TargetActor: An individual actor, specified by a RunDataTable entry with a VariableName of TargetActior and whose EntityIdx is of the form "ActorPost X Hurricane H", indicating actor labeled as participant X from the post-hurricane survey from hurricane H
Questions
1. ConstrainedPrescriptionCasualties
1. Question: To which region should the government direct its aid on each day?
2. Metric: Minimize number of people who die or are seriously injured during the hurricane (Casualties)
3. Format: Fields are Timestep and Region, where Region specifies to where the government’s aid should be directed at each Timestep
2. UnconstrainedPrescriptionCasualties
1. Question: What should the government do on each day?
2. Metric: Minimize Casualties
3. Format: Determined by TA2 based on desired prescription
2. Metric: Minimize Casualties
3. Format: Determined by TA2 based on desired prescription
3. IndividualPrescription
1. What should TargetActor do on each day during the new hurricane?
2. Metric: Severity of injury suffered by TargetActor during the hurricane
3. Format: Fields are Timestep and Action, where Action can be one of the following: evacuate, shelter, go home, or stay in current location
Long-Term Prediction Challenge 2. Metric: Severity of injury suffered by TargetActor during the hurricane
3. Format: Fields are Timestep and Action, where Action can be one of the following: evacuate, shelter, go home, or stay in current location
Instance 21
Input
1. Initial Data Package: Covering an entire hurricane season.
2. TargetActor: An individual actor, specified by a RunDataTable entry with a VariableName of TargetActor and whose EntityIdx is of the form "ActorPost X Hurricane H", indicating actor labels as participant X from the post-hurricane survey from hurricane H.
Questions
The period of interest for the following questions is the following hurricane season. The label of each question is the name of the TSV file in which to place your answer.
1. OffseasonPrescriptionCasualties
1. Question: What should the government do before the next hurricane season?
2. Metric: Minimize Casualties (in conjunction with #2)
3. Format: Determined by TA2 based on desired prescription
4. Example: Implement a tax policy. The TSV file would specify any conditions and percentages, such as the following tax on the minority ethnic group:
2. Metric: Minimize Casualties (in conjunction with #2)
3. Format: Determined by TA2 based on desired prescription
4. Example: Implement a tax policy. The TSV file would specify any conditions and percentages, such as the following tax on the minority ethnic group:
2. InSeasonPrescriptionCasualties
1. Question: What should the government do during the next hurricane season?
2. Metric: Minimize Casualties (in conjunction with #1)
3. Format: Determined by TA2 based on desired prescription
4. Example: Implement a monetary incentive. The TSV file would specify any conditions, such as the following incentive for not evacuating:
2. Metric: Minimize Casualties (in conjunction with #1)
3. Format: Determined by TA2 based on desired prescription
4. Example: Implement a monetary incentive. The TSV file would specify any conditions, such as the following incentive for not evacuating:
3. IndividualConditionsPrescription
1.Questions: Under what conditions should TargetActor evacuate, shelter, go home, or stay in current location?
2. Metric: Severity of injury suffered by TargetActor during the hurricane
2. Metric: Severity of injury suffered by TargetActor during the hurricane
3. Format: Fields are some number of field name and value combinations, specified as Field1, Value1, Field2, Value2, … as needed, and an Action to be taken by TargetActor whenever the given fields match the given values. For example, the following table would specify that TargetActor shelter when there is a hurricane of severity 3 or 4, evacuate when there is a hurricane of severity 5, and stay home otherwise:
Goal of This Challenge:
You are asked to build models and investigation code to fully document the answers to the questions above. Please do this in a Jupyter notebook.
Jupyter notebook
To make the Jupyter notebook easy to review, please ensure that you meet the following requirements:
- The data should be loaded from the exact file and folder structure provided in the data pack.
- Please provide a clear, single, configuration variable to allow us to change the location of the data for reviewer systems. Don’t hard-code the path to all the files.
Answer document
You should also provide a separate answer document, in addition to the Jupyter notebook(s) do not leave anything to be assumed here, no matter how trivial. This will be part of the review at the end of the challenge, so the more information you provide, and the better your documentation is, the better your chances of winning will be.
The answer document should clearly describe:
- Any assumptions you made with regards to the data, and why you decided to make those assumptions
- How you decided what data to use to answer each of the questions
- The actual answer to each question, in as detailed a manner as possible. Don’t be vague here - if the question is asking for a specific group or location, please clearly say the group or location that is your answer
- How you came up with the answer and the justification behind why you think it’s the best answer to the question. Please back this up with data obtained via data analysis and through the Jupyter Notebook code.
Submission
The final submission must include the following items.- A Jupyter notebook detailing:
- How the data is prepared and cleaned, from the tsv files
- How individual answers are analysed
Judging Criteria
Winners will be determined based on the following aspects:- Model Usability and data analysis (60%)
- Your submission will receive a subjective evaluation from the client team.
- Model Transparency (20%)
- How easy is it to understand your assumptions and analysis? Can we understand your methods and conclusions?
- Clarity of the Report (20%)
- Do you explain your proposed method clearly?
- Are assumptions correct and is documentation clear and precise?