Inspiration
Data science has been historically a code base approach when tackling financial problems it is time to lower the scale and make statistics evaluations accessible for everyone.
What it does
It compares different variables to predict inflation in Mexico.
How we built it
Using the following technologies:
- Mongo
- Express
- React
- Node
- Python
- Flask
- Sklearn
Challenges we ran into
Dealing with the different ways in which data arrived.
Accomplishments that we're proud of
Arranging different datasets and finding statistically significant correlations. Being able to predict the inflation rates in the country and the possibility to apply that knowledge for a better decision making.
What we learned
- Cleaning is very important to make predictions
- The importance of understanding information and change it in order to make a good model
What's next for Financial Oracle
- Clean code
- Uploading different datasets
- Usage of containers for portability
- Implementing different forecast approaches
- Enhance data parsing
Built With
- css
- express.js
- flask
- html5
- javascript
- mongodb
- node.js
- python
- react
- recharts
- sklearn
Log in or sign up for Devpost to join the conversation.