Get Predictions

If You Publish, Algorithms Will Come

The publishing docs explain how to send numbers to microprediction using the Python client, the R language or the API directly. This act initiates a fight between hundreds of algorithms authored by different people that watch microprediction.org. If you'd like these algorithms to serve you, the create_a_stream.py example might be the fastest way to get going. Here's a video demonstrating creation of a data stream in under ten minutes. Once this is done, you can sit back and wait for the algorithms to arrive.

Free

No sales folks to talk to, or email to surrender.  This is an experiment you are welcome to join. 

Model Residuals

A swarm of fiercely competing algorithms can try to predict your model errors. 

Cross-Pollinating Results

Algorithms can utilize existing streams or exogenous data.

Continuous Improvement

Predictions improve as new data, models and talent become available.

Caucasian business hand holding megaphone with white sparkles on a grunge background

Model Residual Analysis

A key use for this public prediction API is the ongoing performance analysis of private models used on private data. In this pattern, you publish the difference between your prediction model and the revealed truth. Have you ever wondered:

  • Are your in-house models any good?
  • What's correlated to your errors?
  • What algorithms could be stacked with your existing model to improve performance? 
  • Is your in-house model's performance degrading over time?
  • Are you leaking P/L on Thursdays after 2pm? 

The sooner you publish your "noise", the sooner you'll discover if there is a signal you are missing. 
Happy young woman sitting on the floor with crossed legs and using laptop on gray background

Discover Top Talent

Finding capable data scientists today is difficult. By seeking predictions that fit your organization’s needs, Microprediction can help you uncover the kind of talent you’re seeking. Every Microprediction challenge has its own leaderboard which can help filter contributors with the most appropriate skill sets for your organization. 
If your organization is interested in setting up reward payments, please contact us.
 
Businessman with laptop and energy explosion on background concept

Tutorials

Why wait? 

  1. Make yourself a key
  2. Publish a data value
  3. Keep publishing your data regularly

Python Module 1   R Module 1

See also the documentation.

 

What Can You Expect?

Microprediction systematically evaluates and combines competing prediction models against your data for four time horizons:

  • 1 minute ahead
  • 5 minutes ahead
  • 15 minutes ahead
  • One hour ahead.

You’ll be able to retrieve the following:

  • Cumulative distribution functions for each time horizon
  • Additional, second level information taking the form of so-called "z-streams".

See An Introduction to Z-Streams for explanation of the mechanics, and Tears of Joy, our blog article illustrating how useful z-streams can be. The swarming algorithms don’t just predict your data. They also predict how other algorithms will predict your data -- feedback for more accurate predictions! 

Stay Informed