I recently had the opportunity to participate in a panel discussion Hire-101 by HackerEarth, organized by the folks at HackerEarth. You can find a recording of this session below. I am also sharing...
Black Lives Matter
As I see many of the peaceful #BLM protests being met with violence at the hands of law enforcement, I am reminded of Gandhi, the oscar winning 1982 film by Richard Attenborough that introduced th...
All about machine learning - a "Breaking 404" podcast with HackerEarth
HackerEarth is a community of over 4 million developers who participate in online hackathons and programming challenges in preparation for a career in the tech industry. Several prominent companies...
Dynamic Talks - ML Driven Sales and Marketing for Everyone
The good folks at Grid Dynamics have been scheduling meetups filled with interesting talks in a range of topics spanning data science, machine learning and AI. I had the opportunity to attend one o...
Salesforce Engineering Blog - ML Driven Sales and Marketing for Everyone
My team and I wrote a two part blog on the product we have been working on for the past couple of releases (Behavior Scoring for Pardot Einstein) and published it in the Salesforce Engineering blog...
Einstein for Sales - Under the Hood (Dreamforce 2019 Breakout Session)
We got a chance to allow our customers to peek under the hood of the machine learning pipelines powering a variety of features in Sales Cloud Einstein and Pardot Einstein. While this is the 4th tim...
Scalable in-database machine learning with PL/Python (Postgres Open Silicon Valley 2017)
I presented a talk on scalable in-database machine learning using PL/Python at Postgres Open Silicon Valley. As a fan and long time Postgres users, I have greatly benefited by leveraging PL/Python ...
Data Science Driven Software Product Innovation
My colleague Regunathan and I presented our work on using data science to sessionize and analyze customer logins of our large financial sector clients and uncover both anomalies as well as patterns...
Operationalizing Data science Models on Pivotal Stack
I co-wrote a blog on how we operationalize data science models on the Pivotal stack by leveraging in-database scalable methods for model training and stream processing functions in Apache Geode for...
Building machine learning models at scale for data parallel problems on Pivotal's MPP databases
Using a clever trick in leveraging static dictionaries in PL/Python, we can easily scale ML models from popular libraries like scikit-learn or XGBoost for data parallel problems. You can read the f...