Machine Learning Platform

GovTech Context

In recent years, we have seen tech getting used more and more by the government in various sectors like education, healthcare, agriculture, etc. There are a lot of success stories to celebrate there, but one big area which is more or less untapped is putting the huge amount of data they have to good use. Right use of the data can take these sectors to the next level!

Product Explanation

While there is a lot of data, it’s not easy to find people who can use that to good effect. The aim of this project is to build a platform that can be used by anyone to train models from these datasets, experiment between different models, deploy the better performing one and monitor the performance in production.

Features to be Implemented

Goal is to build an end-to-end machine learning solution to allow anyone to train, deploy, query and monitor different machine learning models for governance use-cases. Some features include:

1. Training datasets and features store
2. Integration with common ML models
3. Recurring model training and deployment pipeline
4. Dashboard to monitor models
5. APIs to query deployed models from various platforms

Learning Path

• TensorFlow
• PyTorch
• MLflow
• Metaflow
• Repo

Category	Rating
Difficulty	***
Risk/Exploratory	**
Core Development	**
Skills	Python, SQL, React, Machine Learning
Mentors	Ashish
Project size	200 hours