PASS BA Marathon: December Edition 2016
Analyzing Healthcare Open Data with Power BI
Event Date: 14-12-2016 17:00 - Category: Breakout Session (60 minutes) - Track: Analyze & Interpret
Speaker(s): Dan English
Title: Analyzing Healthcare Open Data with Power BI
Big Data Analytics with SparkR
Event Date: 14-12-2016 18:00 - Category: Breakout Session (60 minutes) - Track: Analyze & Interpret
Speaker(s): Jen Underwood
Title: Big Data Analytics with SparkR
SparkR, an R package that provides an interface with Apache Spark, leverages Spark’s powerful distributed computation engine to enable exploration, data analysis, and data science on big data sets. In this session, we will introduce SparkR. We will also demonstrate how to get started using SparkR for interactively querying data, building predictive user defined functions and running large scale machine learning with MLlib.
Disrupt the static nature of BI with Predictive Anomaly Detection
Event Date: 14-12-2016 19:00 - Category: Breakout Session (60 minutes) - Track: Analyze & Interpret
Speaker(s): Uri Maoz
Title: Disrupt the static nature of BI with Predictive Anomaly Detection
The static nature of BI today result business insight latency, that cost companies millions of dollars. Data-centric companies like web-based businesses, digital advertising, fintech and IoT need to gain crucial real time business incident detection in order to optimize their business performance. Join Uri to learn how this can be achieved using Predictive Anomaly Detection approach. Uri will share advantages and challenges in implementing Anomaly Detection approach, Industry benchmark and Customers case studies
Using R to Clean and Transform Small Data
Event Date: 14-12-2016 20:00 - Category: Breakout Session (60 minutes) - Track: Analyze & Interpret
Speaker(s): Mark Wilcock
Title: Using R to Clean and Transform Small Data
Big data yes, dark data perhaps but small data – really? Small data is high value data which is often the key numbers or performance indicators that are used by senior management to guide the business. It has been collected at great effort and expense but usually supplied in format that is not conducive to analysis, reporting or visualisation. Using a few examples based on real life case studies we’ll look how R can transform and clean this data. This is a practical session with lots of example of R code. So if the veracity, variety and value of data are more important aspects than volume and velocity then this session will be of interest to you.
Visualizing Multiple Time Series with R in Power BI
Event Date: 14-12-2016 21:00 - Category: Breakout Session (60 minutes) - Track: Visualize & Inform
Speaker(s): Bill McLellan
Title: Visualizing Multiple Time Series with R in Power BI
Power BI and R together offer an enjoyable way for business users to quickly consume complex analytical insights. Outside the business domain, the same tools are available for visualizing public data of cultural interest. The open source Correlates of War (COW) project has been gathering datasets that track all militarized conflicts since the early 1800s along with other time-indexed factors like religion, ideology, and economic power. Do these time series correlate in meaningful ways? What would it look like to visually tell the story of 200 years of global conflict? Using a tabular model linked to these online csv files, I provide examples of where out-of-the-box visualizations in Power BI suffice and where custom modeling and visualization in R get us further.
Real World Predictive Analytics
Event Date: 14-12-2016 22:00 - Category: Breakout Session (60 minutes) - Track: Discover & Integrate
Speaker(s): Miguel Molina-Cosculluela, Diwakar Rajagopal
Title: Real World Predictive Analytics
Join us in this session to explore how predictive analytics is being used in the real world. We will look at generic use cases such as predicting student attrition in universities to explore the challenges and solutions to some of the commonly found predictive analytics scenarios.