Hack the Recovery Data Science Challenge 2022

A Series of Global Data Science Challenges

Why Hack the Recovery?

In 2022, as citizens get vaccinated and governmental restrictions are lifted, citizens have started to increase their social activities. These activities have opened up a variety of jobs. As the economy heads towards a strong recovery, predicting unemployment becomes more important than ever to analyze people that are still left behind. Indiana Department of Workforce Development (DWD) now partners with IronHacks to provide you will real world data in Indiana to predict the unemployment trend in the area. To eliminate the impact of unemployment on individuals and the society, governments and corporations need to understand how much and where people are most economically impacted.

IronHacks is different from a typical 24 hours - 48 hours hackathon. You will have 3 weeks time to develop your model. The evaluation style of IronHacks allows you to make changes to your models in multiple sprints (phases). You will get to submit several times before the hack ends to get feedback on your performance in the hack.

Your Tasks in Hack the Recovery

The hack is all about monitoring and comparing unemployment levels in the state of Indiana. Wondering about the profiles of the people who are likely to make unemployment claims? This data science challenge will ask participants to predict the unemployment claims in Indiana using real world data. We preprocessed large, actual, granular datasets from our partner and we will stream them in real-time so that you can work with almost real-time data. The submission should contain predictive statistical models that you have tried.

We ask you to predict the number of unemployment claims using historical data provided by DWD, as well as demographics data. The data are unique: they are big, they are granular, and they are real, and streamed in real-time. You are given variables such as race, education, categories of employers, week number, etc. Your task is to predict the total unemployment claims for a specific census tract in Indiana in a specific week. Using such data, your predictions will inform citizens as well as decision-makers like the State of Indiana, the Department of Workforce Development, and others about the potential impact of unemployment to the state.

Note: Even if you are not an expert in modeling temporal data at the start of the competition you should not shy away from participation. A visual inspection of the data and some data exploration analysis (DEA) will indicate that even a simple model may offer a good starting point. To make it up to the highest rank of the participants, we encourage you to explore and try different models! This is a fantastic learning opportunity.

How will participants be evaluated?

In past competitions, each participant’s notebook was evaluated in several dimensions with a focus on learning, exploration and creativity. So in this respect IronHacks is different from other competitions that are only focused on performance only. Examples are:

  • The accuracy of your analysis (e.g. the prediction accuray measured with the mean squared error or the correct descriptive analysis for a simpler challenge).
  • Your learning effort and creativity in exploring a variety of different data and models
  • The usefulness of the presentation and interpretation of your data/models in a final interactive report.

More details on the evaluation criteria will be released at the start of the competition.

What is the timeline?

Hack the Recovery

This challenge opens for registration on November 2022. The last date to accept the rules is 15 November, 2022. More details can be found after the registration to the challenge on www.ironhacks.com

Who is eligible?

Everybody who:

  1. speaks English
  2. is older than 16 years and
  3. has programming skills in Python

So what are you waiting for?

Why should you participate?

There are range of benefits for participating in the challenge.

  • Prizes: Most of our challenges have prizes for the best individuals as well as the best teams. For example, in the Spring-Summer Challenge 2021 we will reward the top 5 submissions with Amazon giftcards. The rank will be based on the quality (accuracy) as well as the exploration effort/creativity of the participant submission. The total prize money varies and can range up to $5000.
  • Certificates: Every participant will receive a digital certificate for participation with logos of the sponsors.
  • Jobs Ready: Looking for a job? Your work in this hack can be a portfolio that showcases your problem-solving abilities. What’s more valuable to employers than being able to solve real-world problems creatively?
  • Showcases: We will share the winning solutions on the website.
  • Learning experience: As we have learned from prior participants, the iterative IronHacks process (see more here) combined with the tools and features of the IronHacks platform offers a unique learning experience that is distinct from those you might have experienced on other sites (e.g. Kaggle.com)

And do not forget - your contribution is essential to fight unemployment.

This long-term hack is a unique opportunity to help the society tackle the challenges of unemployment and help companies find the right talents that are out there. With such predictions, you also have the opportunity to help the state and leaders to use the outcome of your models to monitor and predict economic impact. More details can be found in the task statement when it is released at the start of the competition.

Check out what others are saying:

“The excitement to know how my model would perform after every round kept me enthused till the end! These predictions can give insights into social distancing norms and implement necessary precautions."

Feny Patel (Purdue University), 1st Place August 2020 Challenge

“My greatest experience was being able to try on algorithms I never use. I also had the freedom to experiment, instead of defaulting to certain known models due to crunching code within 24 hours like typical hackathons."

Harsha Pavuluri (Purdue University), 2nd Place August 2020 Challenge

What are you waiting for? Get started…

  1. Sign-up on our platform.

  2. Register for the upcoming challenge.

  3. Send us a note if you have questions here