Inspiration
When businesses have so much data at their disposal, why not make the best out of it? So I thought why not embed the power of ML into monday.com!
Whether you are a marketing professional looking to see if a specific customer is worth pursuing, or a salesperson trying to maximize your profit this quarter, this app covers all your needs!
What it does
A simple interface to train and use ML models without writing a single line of code!
- User selects the board to be used as the dataset.
- Select relevant features according to their business needs, and the target metric.
- Train model.
- Provide input values to predict!
How I built it
- Fetch board data using monday's GraphQL API.
- Fetch column names(features)
- Create dataset matrix
- Train ML models in the browser using ml.js
Challenges I ran into
- Initially faced some issues while working with GraphQL, as it was my first time, but then found it to be really convenient!
Accomplishments that I'm proud of
- A fully functional app that has business value!
What I learned
- Using a framework to build apps for the business sector
- Using GraphQL
- Following design principles
What's next for ML magic
- Add advanced algorithms
- Give users the option to choose hyperparameters for training models
- Add unsupervised learning(clustering) .
Log in or sign up for Devpost to join the conversation.