Get Predictions

Automatic Prediction of Your Data

Algorithms Will Come to You

If You Publish, They Will Come

The microprediction python client README explains how publishing numbers repeatedly initiates a fight between algorithms 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. There are numerous benefits to this approach.

No Signup

No sales folks to talk to, or email to surrender. Just use the Python client or call our API.

Assess Models

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?

  • 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?

 

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. 

Incentivize Top Talent

Offering reward money to get predictions has never been easier or more economical. You can offer compensation directly linked to your data streams. Join leading financial institutions who have discovered how easy this is. Our platform is programmatically self-governed, so you get efficient access to high-quality predictions on the cheap.

No Middleman

Avoid weeks of planning and setup time – one call to our API gets you started.

Zero Overhead

No agency costs means you can allocate higher incentives to attract talent.

Scalable Infrastructure

Reward mechanisms allow for more contributors to improve accuracy.

See current competitions offering prize money. It’s relatively painless and inexpensive to incentivize talent. 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

For detailed steps, see the Knowledge Center  for Python, R and Julia introductory tutorials. 

Python Module 1 R Module 1Knowledge Center

 

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!

Instructions

See our knowledge center to get answers to frequently asked questions about getting predictions. See the API documentation if you don't wish to use Python. 

 

 

 

Follow the Movement