Projects / AI Innovation Challenge

Crisis Impact Forecaster for Empowering Humanitarian Decisions

Project Kickoff: September 26


Featured Image

Developing an AI-driven system to predict missing data points using historical datasets, enhancing data analysis capabilities, and improving decision-making processes across various sectors. In this 8-week challenge, you will join a collaborative team of 50 AI engineers from all around the world.

The problem

Humanitarian organizations face significant challenges in effectively predicting and responding to rapidly evolving crises. The complexity and unpredictability inherent in humanitarian situations often hinder timely and accurate decision-making. Specifically, analysts struggle to anticipate developments in ongoing crises, particularly when new risks emerge or existing risks escalate. This difficulty in forecasting can lead to inadequate preparedness and response, exacerbating the vulnerability of affected populations.

Impact of the Problem:

  • Delayed Response: Insufficient predictive capabilities can result in delayed responses to crises, leading to prolonged suffering and potentially higher mortality rates among vulnerable populations.
  • Inefficient Resource Allocation: Without a clear understanding of potential future scenarios, humanitarian efforts may suffer from misallocation of resources. This inefficiency can lead to either over-resourcing in some areas while leaving critical needs unmet in others.
  • Increased Vulnerability of Populations: The inability to foresee and act upon emerging risks means that vulnerable groups remain at heightened risk during crises. Early identification and mitigation of such risks are crucial to protecting these populations.
  • Operational Inefficiencies: Lack of accurate forecasting can lead to operational inefficiencies within humanitarian organizations. These inefficiencies can strain both financial and human resources, diminishing the effectiveness of response efforts.
  • Loss of Credibility: Failure to accurately predict and manage humanitarian emergencies can damage the credibility of organizations. This can lead to decreased confidence among donors and stakeholders, impacting funding and cooperation.

To address these challenges, this Proof of Concept (PoC) aims to develop and deploy a predictive system for ACAPS analysts. This system will integrate internal ACAPS datasets with external authoritative data sources to enhance the organization’s predictive capabilities. By assessing current conditions in the context of historical data and forecasting potential future risks based on early trends and discussions across various platforms, the system will:

  • Provide ACAPS analysts with forward-looking insights, improving their ability to create high-quality reports and make informed decisions.
  • Encourage the consideration of emerging trends that might typically be overlooked, ensuring a comprehensive analysis of potential risks.
  • Improve the accuracy of predictions regarding future conflicts and other humanitarian issues, thereby guiding more effective and timely responses.

Ultimately, by enhancing ACAPS’ analytical capabilities, the project seeks to guide the humanitarian sector toward more proactive and impactful interventions, potentially reducing the adverse effects on vulnerable populations.

The goals

The ultimate objective of this project is to develop and deploy an advanced AI-driven system to predict missing data points, enhancing data analysis processes across various applications. This initiative will involve the integration of historical data and AI modeling techniques to create a system that not only predicts data gaps but also provides a user-friendly interface for interacting with these predictions. The project will unfold over several key milestones, each planned to ensure the successful development and deployment of this transformative technology:

  • Data Preparation: Finalize project scope and requirements, gather and preprocess historical data for model training, and set up project infrastructure and development environment.
  • Initial Model Development: Develop initial AI models for predicting missing data points, conduct preliminary testing to adjust model accuracy, and begin designing the basic user interface for interacting with model predictions.
  • Model and Interface Refinement: Integrate AI models with the prototype system, develop the basic user interface including functionalities for data input and viewing predictions, and conduct a mid-project review to refine the models and UI based on feedback.
  • Review and Final Adjustments: Finalize AI models and user interface design, conduct extensive testing and validation of the Proof of Concept (PoC), and prepare the initial draft of the Testing and Validation Report.
  • Final Review and Project Completion: Implement final adjustments based on testing outcomes, finalize all project documentation including development and model documentation, prepare for the final review, and stakeholder presentation.
  • Stakeholder Presentation and Planning for Future Development: Conduct the final project review with stakeholders, present the PoC, gather final feedback, complete and deliver the Testing and Validation Report, and plan next steps for scaling and further development.

Thus, this project aims to deliver an innovative AI-driven solution that significantly enhances the capability to handle and predict missing data within datasets. By providing a more efficient, accurate, and user-friendly system, this initiative promises substantial benefits in improving data completeness and reliability, ultimately contributing to more informed decision-making processes.

Why join? The uniqueness of Omdena AI Innovation Challenges

A collaborative experience you never had in your working life! For the next eight weeks, you will build AI solutions to make a real-world impact and go through an entire data science project lifecycle. This covers problem scoping, data collection, and preparation, as well as modeling for deployment.

And the best part is that you will join a global and collaborative team of changemakers. Omdena AI Challenges are not a competition or hackathon but a real-world project that will take your experience of what is possible through collaboration to a new level.

Find more information on how an Omdena project works

First Omdena Project?

Join the Omdena community to make a real-world impact and develop your career

Build a global network and get mentoring support

Earn money through paid gigs and access many more opportunities



Your Benefits

Address a significant real-world problem with your skills

Get hired at top companies by building your Omdena project portfolio (via certificates, references, etc.)

Access paid projects, speaking gigs, and writing opportunities



Requirements

Good English

A very good grasp in computer science and/or mathematics

(Senior) ML engineer, data engineer, or domain expert (no need for AI expertise)

Programming experience with Python

Understanding of Machine Learning, and/or Data Analysis



This challenge is hosted with our friends at
Logo


Application Form
3 women standing and 1 woman sitting in a wheelchair in front of many flags from different countries. These women are part of Fight For Right - a DLO that WID assisted in crisis response.
AI-Driven Resource Identification and Matching System
Thumbnail Image
Soil Nutrient Prediction for Enhanced Fertilizer Recommendations
Thumbnail Image
Crisis Impact Forecaster for Empowering Humanitarian Decisions

Become an Omdena Collaborator

media card
Visit the Omdena Collaborator Dashboard Learn More