The Download: Tech Talks by the HPCC Systems Community, Episode 23

Presented by

HPCC Systems

About this talk

Join us as we continue this series of webinars specifically designed for the community by the community with the goal to share knowledge, spark innovation, and further build and link the relationships within our HPCC Systems community. Featured speakers include: Jeremy Meier and David Noh, both Undergraduate Students at Clemson University - An Investigation into Time Series Analysis Over the past several months, our team has worked closely with a dataset having roughly 16,000 total observations, recording both the date and balance in financial data. Focusing on individual accounts with a size of around 400 observations, our first goal was to compare statistical metrics and techniques used commonly in time series analysis on the given data sets. We dove deep into two major industry standard methods for understanding and predicting on a dataset. Using insights learned from these observations, we hope to better predict future balances in the dataset, as well as find any anomalies or misbehavior in the data in order to provide business value. Roger Dev, Sr Architect, LexisNexis Risk Solutions - TextVectors - Machine Learning for Textual Data Text Vectorization allows for the mathematical treatment of textual information. Words, phrases, sentences, and paragraphs can be organized as points in high-dimensional space such that closeness in space implies closeness of meaning. HPCC Systems' new TextVectors module supports vectorization for words, phrases, or sentences in a parallelized, high-performance, and user-friendly package. Allan Wrobel, Consulting Software Engineer, LexisNexis Risk Solutions - ECL Tips and Tricks: Leveraging the power of HPCC Systems. Using AGGREGATE. The ECL built-in function AGGREGATE has been seen by many in the community as ‘complex’ and as such has been underused. However in using AGGREGATE you can be sure you’re playing to the strengths of HPCC Systems.

Related topics:

More from this channel

Upcoming talks (0)
On-demand talks (49)
Subscribers (2149)
HPCC Systems is an open source Big Data analytics solution for businesses of all sizes, allowing them to improve critical time to results and decisions. Subscribe to our channel to keep informed of the latest HPCC Systems events.