ML Platform Challenges and Applications at Freshworks


Duration: 25 mins
Swaminathan Padmanabhan
Senior Director, Datascience

In this talk, we will start by describing the three major challenges faced by the Machine Learning team at Freshworks. This includes a) Multi-tenancy, b) Interpretability, and c) Multi-lingual ML models. Every ML feature or capability that we provide gets consumed by tens of thousands of our business customers, and in-turn by their end-users. We, therefore, design our ML systems to scale for millions of end-users, and every ML feature is managed like a portfolio. Our business customers span several diverse industries including Finance, retail, healthcare, real estate, and education; and their end-users speak various languages.

By attending this talk, you will understand value proposition that we have enabled for these businesses by leveraging AI to optimize their sales processes, revenue and customer LTVs. Our hope is you will be able to take these learnings back to using it at your work.

You may also be interested in

180 mins
Beyond Managing Your Manager

The deep-dive workshop presents why conflicts with your manager are inevitable based on differences in priorities and perspectives, and how...

25 mins
Designers + Developers = Best Friends Forever?

How is the relationship between your design team and your development team? Is it highly functional? Or 'just professional'? Maybe...

25 mins
Writing Professionally

The most important thing you do in your job is write. It's in every email you send, every commit you...

180 mins
Leading a Team of Subject Matter Experts with Confidence

As a leader, it is impossible to be an expert on all aspects of your delivery - this is why...

50 mins
All That Glitters Ain't Gold

Let’s use Kafka, everywhere! Let’s try event driven architecture! How about Rust for this service? Let’s use Elixir for this!...

50 mins
Imposter Syndrome: Overcoming Self-Doubt in Success

Impostor Syndrome is the domain of the high achiever. Those who set the bar low are rarely it’s victim. What...