blob: e06c2a8730075148385ff2cde445f6e3b9eee0a0 [file] [log] [blame]
---
layout: docs
---
<h1>Welcome to PredictionIO {{ site.pio_version }}</h1>
<p>
PredictionIO is an open source Machine Learning Server. It empowers programmers
and data scientists to build smart applications with data productively.
</p>
<p>
PredictionIO currently has 2 built-in recommendation engines. With them, you can
add the following features to your apps instantly:
</p>
<ul>
<li>predict user behaviors</li>
<li>offer personalized video, news, deals, ads and job openings</li>
<li>
help users to discover interesting events, documents, apps and restaurants
</li>
<li>provide impressive match-making services</li>
<li>and more....</li>
</ul>
<p>
A standard PredictionIO stack is built on top of solid open source technology,
such as Scala, Apache Spark, HBase and Elasticsearch.
<a href="/install/">Install PredictionIO</a> and give it a try!
</p>
<h2>Adding Machine Learning to your web or app quickly</h2>
<h3>For Web and App Developers...</h3>
<p>
PredictionIO comes with a few built-in predictive engines that you can use
out-of-the-box. No Machine Learning knowledge required. You may also customize
them to fit your specific application needs.
</p>
<h3>Learn how to use Built-in Engines</h3>
These few steps can get you familiar with PredictionIO's Built-in Engines
quickily.
<ul>
<li>
Read <a href="/tutorials/engines/quickstart.html">Using Built-in Engines:
Quick Start</a>.
</li>
<li>
Learn from some examples in <a href="/tutorials/engines">Tutorials
&amp; Samples</a>.
</li>
</ul>
<h2>Deploying your own algorithms on production</h2>
<h3>For Data Scientists and Algorithm Developers...</h3>
<p>
If built-in engines don't fit your need, you can also create a new engine and
deploy your own algorithm easily. PredictionIO server handles the heavy-lifting
for production deployment, so that you can focus on your unique prediction
challenges.
</p>
<h3>Learn how to build your own Engine</h3>
These few steps can get you familiar with PredictionIO's Engine buildng process.
<ul>
<li>Read <a href="/enginebuilders/">DASE Architecture Overview</a>.</li>
<li>
Building your first <a
href="/tutorials/enginebuilders/local-helloworld.html">"Hello World"</a>
engine.
</li>
</ul>