Vista Analytics appearing on international television with Kathy Ireland? Addressing the issue of Concept Drift during discovery through the application of Artificial Intelligence? Pushing the boundaries of discovery processes through committed research and development? Building an industry-leading team of experts in Forensics, Dispute Technology and Machine Learning?
Read on to discover what is happening at Vista Analytics!
This August, co-founder Michael Faraci traveled to the famed iHeart Studios in Burbank, CA to tape a segment for Wordwide Business with kathy ireland®. Our show airs Sunday, December 10th at 5:30 PM EST on Bloomberg International and Fox Business News as sponsored content. During the segment, Mike and Kathy discuss the changing face of litigation data analytics, and Vista’s continuing commitment to innovation using machine learning. Mike also explores Vista’s role as a true partner to our clients, never leveraging “shrink-wrapped” technologies to churn through data, but rather working closely with our clients to develop custom solutions that deliver deeper insights than our competitors can provide. If you can’t tune in Sunday, a highlight reel and the full-length interview are available now on our website.
This December 12th, Mike travels to Boston with data scientist Yihua Shi Astle to see her present at the 2017 IEEE International Conference on Big Data. Our submission—co-authored by Yihua, Dr. Xuning Tang, and co-founder Craig Freeman—is entitled “Application of Dynamic Logistic Regression with Unscented Kalman Filter in Predictive Coding” and was selected for presentation by the most respected data scientists and Ph.Ds. in the world (with only a 20% acceptance rate) and is a testament to Vista’s groundbreaking work in litigation technology research. The paper addresses the issue of Concept Drift during discovery, which from our perspective deals with two things. First, the language used over the course of years as well as the terms are continually changing. Second, while the attorneys are reviewing the documents throughout discovery, their understanding and knowledge of the documents changes over time also. Thus if an attorney builds one model at the beginning of the process and doesn’t take into account this Concept Drift, the set of responsive documents is completely inaccurate by the conclusion. Our approach learns new patterns at a faster rate, renders better accuracy and recall, and requires a reduced labeling cost in terms of computer performance, which when combined makes it potentially a superior alternative in updating predictive coding models. With our ensemble approach to machine learning capabilities, we are a now able to address the issue of Concept Drift in a manner that our competitors cannot. The full paper along with our other thought leadership pieces and articles is available now on our website.
On the innovation front, Vista remains committed to changing the state of dispute technologies. Our continued exploration of machine learning capabilities and big data science, and the manner by which they can be applied to the discovery process, will continue to widen the gap between our capabilities and those of our competitors. By focusing on emerging industry trends, then driving innovation through research to address those trends, all while delivering solutions with an ensemble approach to the latest tools, Vista Analytics will continue to differentiate itself. The added bonus to this company philosophy is that it will attract and help retain the top minds across our core disciplines. From forensics and dispute technology, to machine learning and big data science, we have found that the best and brightest people gravitate to the most rewarding challenges and the most supportive cultures.
In addition to our investments in building up our talented team, we have also made significant investments in our infrastructure. By leveraging the best in public cloud platforms, including AWS and Azure, we are able to keep our costs competitive and our solutions scalable, all while maintaining incredibly rapid deployments.
Contact us today to discuss any particular challenges you may be facing, or to learn more about our ongoing R&D initiatives.