Back in the 1970s, to get a sneak peek of the future, you turned to Ouija boards, Magic 8 balls, Tarot cards, and fortune tellers (both the gypsy and the folded-paper versions). Without predictive analytics, behavioral profiling and data mining, you were forced to rely on crystal balls and gut instinct to inform your decisions.
Not so, today. With scalable, repeatable processes, mine data for trends and patterns that shine light on future markets, potential customers, healthcare diagnoses, fraud vulnerabilities and more. Check out these resources that describe how to use technology to turn big data into reliable indicators of future trends.
- Big data roundup: Don’t miss the weekly newsletter, a weekly collection of the top resources on big data and analytics technology
- Predict user requests for web content using R and InfoSphere Streams: Analyze web server logs to model how users navigate a website and predict what content will be requested next. Explore a sample solution that uses InfoSphere Streams and R to continuously issue predictions based on the model
- Use InfoSphere Streams as a sensory interface to Watson: Watson is a powerful technology for solutions involving natural language. However, some data is not in the form of text. Find out how to use InfoSphere Streams to enable Watson to use sensor data.
- Leverage Python, SciKit and text classification for behavioral profiling: Learn how to build a behavioral profile model for customers based on text attributes of previously purchased product descriptions. With SciKit, a powerful Python-based machine learning package for model construction and evaluation, learn how to build and apply a model to simulated customer product purchase histories.
- Create a business intelligence and analytics service in Ruby with BLU Acceleration on BlueMix: The BLU Acceleration Service available in IBM BlueMix provides a powerful, easy-to-use and agile platform for business intelligence and analytics. See how easy it is to incorporate the BLU Acceleration service into your application so that you can focus on your application.
- Harvest machine data using Hadoop and Hive: Machine data can come in many different formats and quantities. Weather sensors, fitness trackers and even air-conditioning units produce massive amounts of data. Read about the challenges and solutions for supporting the consumption of massive machine data sets that use big data technology and Hadoop.
- Use the BlueMix JSONDB service instead of MongoDB: The MEAN (MongoDB-Express-Angular-Node.js) software stack is gaining in popularity. JEAN is used as a nickname for a stack that uses JSONDB instead of MongoDB, to indicate that the service of storing JSON documents is generic, not specific to a single DBMS. Learn how easy it is to convert an application built on a MEAN stack to a JEAN application. Fork an existing application, modify the code locally in the Eclipse IDE, and deploy the new app to BlueMix.
- Introduction to YARN: Apache Hadoop 2.0, one of the most popular tools for big data processing, offers several revolutionary features, including Yet Another Resource Negotiator (YARN), HDFS Federation and a highly available NameNode, which makes the Hadoop cluster much more efficient, powerful and reliable. Discover the advantages YARN provides over the previous version of the distributed processing layer in Hadoop.
- Recognize physical activity on mobile phones with IBM Worklight and IBM SPSS Modeler: See how to detect and track the physical activity of mobile phone users. This article provides techniques to clean training data, select features, choose the best classification algorithm and validate the model.
- Build applications with the IBM DataCache service: Improve the performance of an application built on the Codename: BlueMix environment by using the IBM DataCache service.
- Create an application inventory with AppScan Enterprise: Learn how to build a centralized, authoritative inventory of all the applications in your enterprise and track their security posture and compliance status from IBM Security AppScan Enterprise.