Q: What surprised you most as an engineer about the work you did that you'll be telling us about in your talk?
Prabhat Jha: Building text classification algorithms in a generic way is really hard. We had to narrow down our problem to a smaller subset to get a meaningful result with a reasonable amount of effort.
Q: What do you think a listener will get out of this this talk vs. other talks on distributed data processing and data versioning that they've previously heard?
Prabhat Jha: Versioning best practices from traditional software development do not apply to machine learning because models are part of code. As you create ML models based on training data, and as you change the algorithms and code behind the models, you will have different versions of models that you have to be aware of when thinking about versioning.
Q: Is there any additional back-story about you and your company that you want our audience to know?
Prabhat Jha: Wootric has collected millions of customer feedback data points in last 3 years from most of the verticals and industries you can think of. In particular, SaaS and DevOps are our sweet spot.
About the Startups Track
The data-oriented Startups Track at DataEngConf features dozen of startups forging ahead with innovative approaches to data and new data technologies. We find the most interesting startups at the intersection of ML, AI, data infrastructure and new applications of data science and highlight them in technical talks by their CTOs and lead engineers who are building these platforms.