PMT APP is a project to predict poverty levels in Costa Rica for allocation of aids by IDB.Our project helps to identify the proper vulnerablilty of the family, so they could be given aid accordingly.
Here's the backstory: Many social programs have a hard time making sure the right people are given enough aid. It’s especially tricky when a program focuses on the poorest segment of the population. The world’s poorest typically can’t provide the necessary income and expense records to prove that they qualify.
In Latin America, one popular method uses an algorithm to verify income qualification. It’s called the Proxy Means Test (or PMT). With PMT, agencies use a model that considers a family’s observable household attributes like the material of their walls and ceiling, or the assets found in the home to classify them and predict their level of need.
While this is an improvement, accuracy remains a problem as the region’s population grows and poverty declines. To improve on PMT, the IDB (the largest source of development financing for Latin America and the Caribbean) has given this dataset and challenge to improve predcition of Poverty level so that the people who actually need the aid get it and everyone can work towards greater good.
Beyond Costa Rica, many countries face this same problem of inaccurately assessing social need. Source : Kaggle
Powered By MLOps
We aim to help the IDB(Inter American development bank) to identify poverty levels and make sure aid is provided to those in need and make a good impact and help the social cause of uplifting the underprivileged in Latin America
With MLOPS we created a pipline, which ingests data from a server and then cleans the data and transforms it and trains the model,saves the model and serves the model as an API
We can call the API served by MLOPS to get solution for our problem in real time, feed the inputs and get the result.This helps us deliver a good solution for the social problem
How we built it
- We used MLOps to create a pipeline for our model.
- We imported the data,cleaned it , transformed it and trained it.
- After this we serve our model
- We call the API from our UI to get the vulnerability level of the household based on input parameters
Accomplishments we are proud of
- Building a complete MLOps pipeline
- Building a UI to test it and present it and show real life implementation