Understand the people's needs, resources and capacities as fast and thoroughly as possible. When a disaster occurs, humanitarian organizations have hard time collecting and analyzing data to understand the needs of the affected people in a fast way, so they can have a fast response and send help to the needed ones in the needed areas.

What it does

That’s why we are creating a tool that automates the collection and analyzation of data and also comparing it to the previously collected one so that this organizations can come to a more accurate solution, faster and with much less effort.

How we built it

We have designed a Front end using react.js and collected the responses at backend. We have also applied Machine learning models to interpret the meaning out the text that is generated using this tool. We used technologies like react.js, my sql, python, pandas, numpy.

Challenges we ran into

Right now the process is, they collect the data physically, through interviews, focus group discussions, and surveys with the affected people and mostly the collection is paper-based. Then with the help of some analysis tools they compare the existing dada with the newly collected ones and generate a report based on the analysis. Then they send their help according to that report. Here the concern is a long time to finish the whole process from data collection to analysis. Because after a disaster strikes, field access is often difficult. So our target was to reduce this time and collect and analysed data efficiently and thereby producing faster, cheaper and richer RGA that is Rapid Gender Analysis.

Accomplishments that we're proud of

In the frontend we wanted to show the generated report after all the information are saved in the database. We also planned at first to train AI tool to analyse the data. But due to lack of time, we could not manage to do that and tried a simpler approach instead. We as a team worked really heard during these days, if we will get more time we can present as an app RGA that is Rapid Gender Analysis for PlanBørnefonden. But we all very proud of what we have achieved as of now and thanks to all members from Climate Hackathon for this wonderful opportunity.

What we learned

Most importantly, we have worked as a team and we learnt to work together with a concrete plan. We distributed the whole project into 4 different areas and each of us took care of their own. But at the same time we shared our constructive feedback and helped each other throughout the way.

What's next for Automation of tools & Impact Analysis: PlanBørnefonden

We have only analyzed one of the many tools and generated report based on that only. The next step is to continue analyzing all the tools and generate a more efficient, detailed and dynamic report.

Share this project: