We begin the new year with two exciting talks!!
Practical Scaling: How to Use Simple Tools to Create and Implement Complex Modeling Systems
Speaker: James Piette
It is almost impossible in today's Data Science landscape to not be overwhelmed by the volume of new, latest-and-greatest modeling techniques and automated solutions. Even after sifting through these products to find what is applicable and not snake oil, the time needed to learn the necessary processes for implementation can be a costly proposition. This talk serves as a response to this development, and is based on a thesis loosely tied to the Pareto Principle: choose a solution(s) that require 20% of the effort to get to 80% of the perfect solution, and then rely on real-world feedback to capture the remaining edge. It will cover fitting and implementation of machine learning models like boosted trees and GAMs on medium-sized data (< 100M rows) using simple SQL and bash scripts in a quick-response (< 1m) environment.
James Piette received his Ph.D in statistics from Wharton while also co-founding a tech company with a fellow Penn grad in sports analytics (Krossover). He has worked in a variety of industries like credit (LendUp) and private equity (Two Six Capital) and more recently, was a partner at a fund that invests in professional athletes (x10 Capital). Currently, James serves as Managing Partner for Blue Lacy Group, a quant hedge fund in sports betting, and is the Director of Data Science at Reputation.com, an online reputation management software company.
Empowering Customer-Facing Teams with Voice-Based AI
Speakers: Yev Meyer and Nabin Mulepati
AI Suggest Voice, an AI based solution for customer-facing teams, listens to customer-agent interactions and recommends verified knowledge to agents in real-time so they can confidently answer questions from customers, resolve complex issues faster and provide white-glove service that truly delights.
AI Suggest Voice is a cloud-native solution built on top of multiple Guru microservices working in tandem. In this talk, the speakers will discuss the overall architecture of AI Suggest Voice and some of the lessons learned in making it all work in real-time and at scale. They will cover how they stream audio to our speech-to-text API over a persistent websocket connection and how we leverage state-of-the-art machine learning models and natural language processing techniques to detect speech, transcribe it to text in real-time, and use that text to suggest contextual knowledge
Yev Meyer is a Senior Data Scientist at Guru. Prior to Guru, Yev led and contributed to product data science teams at VC-backed startups Curalate and RJMetrics. He holds a PhD in Computational Neuroscience from Columbia University, where he studied dendritic processing and multisensory encoding in spiking neural circuits.
Nabin Mulepati is a Senior Machine Learning Engineer at Guru. Prior to Guru, Nabin led engineering at Port Payments Co. Port was a small startup that spun out from a successful exit of Ticketleap, a Phillly startup, in 2017. He holds a B.Sc. in Computer Science and Mathematics from Susquehanna University, where he worked with reinforcement learning to develop neural network based controllers for mobile robots.
Event Sponsor: Guru (www.getguru.com)
Guru is a knowledge network that knows when, how, and where to deliver knowledge to you without you having to look for it. With Guru, you don’t just manage your knowledge; you create a network out of company's collective intelligence. Using AI, Guru suggests relevant knowledge to you in real-time in every application you work in. The more you use Guru, the smarter it gets