BigML News, Issue #11, October 2014
BigML - Machine learning made easy



In this issue:
  • BigML Summer Release:  Anomaly Detection and More!
  • – the world’s first predictive apps & APIs conference
  • BigML Down Under!
  • Programmatic Machine Learning in Action: Leveraging BigML’s client-side predictions 
  • Predicting Box Office Success with BigML
  • Using BigML & to predict Kindle reviews
BigML Summer Release:  Anomaly Detection and More!
BigML issued our Late Summer Release last week, which includes several major enhancements to our platform.  Leading off the release is Anomaly Detection, which can help automate a number of predictive tasks for fraud detection, security, quality control, diagnoses and more.
Also included in the release are support for model clustersmissing splitsclient-side predictions and more!  Learn more about these exciting new features here. – The World’s First Predictive Apps & API Conference
Last year, Mike Gualtieri of Forrester sagely stated that “Predictive Apps are the next big thing in app development,” and we couldn’t agree more.  As developers and internal IT groups around the world begin to focus more on adding predictive elements to internal and external applications and services, BigML is proud to be a co-sponsor of - the first international conference on predictive APIs and apps.
The conference will take place immediately before Strata Europe, from November 17-18 in Barcelona, and is being shaped by a program committee of global experts in machine learning and app development. 

The sessions themselves will be BS-free – so you can expect to get very practical and information on how to build predictive apps, rather than sitting through thinly veiled sales pitches. The first day will include Machine Learning tutorials  as well as Text Mining and Deep Learning tutorials and will conclude with a Hackathon fueled by code, beer and patatas bravas! On the second day of the conference you’ll hear expert perspectives from companies that are deploying a wide array of predictive apps.

So be sure to register today! And if you’re interested in speaking be sure to submit your proposal before October 8th.

BigML is very pleased to announce that we’ve launched a new service ( to better serve our customers in Australia & New Zealand.  This service will contain all of the content and functionality of our, but will provide faster performance as well as some localized content (e.g., local events and local training opportunities).  In addition, we’re very excited to detail a unique alliance that BigML has launched with a leading data intelligence company in the region, GCS Agile.

Learn more about these latest activities here, including some workshops during the weeks of October 13 and 20 where you can get hands-on perspective from the BigML and GCS Agile teams.

Programmatic Machine Learning in Action: Leveraging BigML’s client-side predictions
There are now multiple ways to leverage BigML’s predictions within a web browser.  For starters, check out the second of two posts on how to leverage BigML’s API to build a predictive Chrome extension to predict Kiva loan success:
In addition, new client-side predictions make it easier than ever to explore the influence of each field in your models, ensembles or clusters. Whereas you previously had to rebuild predictions for each set of variables, you can now simply change your fields’ inputs and see the predicted output change in realtime!  In addition, the prediction form also includes the relative importance of each field so you can quickly select or de-select them for your predictions.

Predicting Box Office Success with BigML
Movie studios spend millions of dollars in research and marketing to ensure optimal turnout for its new releases.  Predicting box office results has always been tricky, but Xtream IT Labs has tapped into the power of machine learning and BigML studios can take some of the guesswork out of the equation.  Learn more in this exciting guest blog post.

Using BigML & to predict Kindle reviews
BigML and have a natural synergy, with a common focus on helping users of all skillsets to gain more understanding from data.  Check out this post on how we used to pull data on reviews of nearly 60,000 Kindle books, and then leveraged BigML’s powerful text analytics to assess key words associated with positive reviews.  Here’s a hint on the outcome:  if you want a positive review for a Kindle title, you should look to a higher power.
Interested in becoming a BigML partner?  Contact us at for more information.

Our mailing address is:
BigML, Inc
2851 NW 9th Street
Suite D, Conifer Plaza Building
Corvallis, Oregon 97330

Add us to your address book

Copyright © 2014 BigML, Inc, All rights reserved.