Make Predictions

Real-world challenges where you're in charge and recognized for your effort.

Live Updating Data

These are real-world challenges, many of which directly impact operations, where you can hone practical skills. 

  • Perfect the use of online algorithms
  • Find relevant exogenous data for your models
  • Sharpen your competence in maintaining and improving models

Ready to start?

Python Module 1 R Module 1

 

 

Stay in Control

Your autonomy is essential to us as we democratize prediction. There’s no need to register and you can operate with complete anonymity.

Easy to Get Started

See the knowledge center for short video tutorials explaining how to run the default algorithm (which crawls from data stream to data stream) and then improve it. 

Immediate Feedback

Get feedback on each and every data point instantly as it arrives.  See how your predictions rank versus other fiercely competing algorithms over time. 

Endless Possibilities

For example, your algorithms could even create their own data streams - to improve ingredients or assess prediction residuals. 

New Streams Arriving

Your algorithm will automatically find new things to predict, as more companies use the prediction API. 

The Winner Is... card with colorful background with defocused lights

Plug Your Library or Service

You can use your crawlers set_repository method to create a badge on the leaderboard that links to your code. Let people see where it is most useful. 

Microprediction encourages cooperative competition, but at the end of the day this is a meritocracy. Show them what you've got. 

How do I Start? card with a urban background

Set Your Algorithm Loose

You can put any predictive method to work here by  

  1. Subclassing MicroCrawler in the microprediction package
  2. Modifying its sample method
  3. Running it indefinitely

See details steps in the Python video modules. 

Python Module 1

You can also use R, with more support coming soon. 

R Module 1

 

Mechanic lying and working under car at the repair garage

Diagnose Your Models

Predict data streams that you generate yourself. Use your competitors to alert you to shifts in regimes or model drift. 

Use z-streams for outlier or anomaly detection. See our blog article on interpreting emotions during the Presidential debates - quick work because it takes advantage of the fact that all data streams are automatically standardized. 

 

Frequently Asked Questions

See our knowledge center to get answers to frequently asked questions about getting predictions.

Follow the Movement

Connect with an innovative community that’s changing the world of prediction.