Project from :
- Akshay S G - Shiv Nadar University , Chennai
- Surya S - Shiv Nadar University , Chennai
- You need to have a postgre database created with the values of the Indian Startup.csv file loaded into it.
- Install all required libraries
We connect SQL database(PostgreSQL) with our /code app.py file which is then preprocessed and the data is used in our machine learning model.
The same preprocessed data is used as training dataset for our machine learning algorithm.
In this algorithm we take in 2 or more feataures of the data set and derive a similarity matrix comparing those constrains(Cosine similarity) to find the most accurate/similar startups for the investors.
The front end of this project is done mostly with streamlit module of python database from postgreSQL and streamlit is connceted using psycog2.