The Fifth Elephant 2019

Gathering of 1000+ practitioners from the data ecosystem

Tickets

MetaConfig driven FeatureStore with Feature compute & Serving Platform powering Machine Learning @MakeMyTrip

Submitted by Piyush (@piykumar) on Monday, 3 June 2019

Session type: Full talk of 40 mins

Abstract

Developing Personalization platform for improving customer experience of millions of Indian travellers
- FeatureStore with Feature compute & Serving
- Why Feature Catalog cannot be an afterthought, Metadata analysis is Key to succeed in transforming development of pipelines with eye on Data Quality!
- Microservices is not only about services only its more about Data, we call it Data APIs
- Lessons learned from the Growth projects(personalization, wallet/discounting, Gamification

Outline

MakeMyTrip - India’s #1 online travel platform having more than 70% of the traffic from mobile apps embarked on a journey to revolutionize its customer experience by building a scalable, personalized, machine learning based platform which powers onboarding, in-funnel and post-funnel engagement flows, such as ranking, dynamic pricing, persuasions, cross-sell and propensity models.
For a company like MakeMyTrip, the next wave of consumer growth is driven and powered by data products for personalization, context-aware mobile experiences. Having a better data architecture to ingest user activity streams (events), processing and data APIs enable a foundation for real-time feature generation for machine learning models.

Topics include:

  • Why common feature-store, removing dataset fragmentation caused by usecase-by-usecase approach!
  • Productionizing ML via standardization : MetaConfigs & FeatureCatalog | Reducing Data-Tech Debt
  • Developing Real-Time Serving store over Spark Streaming, Kafka, RocksDB, Akka HTTP Data APIs
  • Lifecycle of feature generation | Online(Near Real-Time) & Historical(Batch) Compute
  • Consistent Feature Engineering & Model Deployment for DSA: DataScience Automation

As Technology we leverage Kafka, Spark (Streaming, SQL), Scala, Python, AWS (S3, EMR, Glue and other services), DRUID, Hive, Presto, Cassandra, RocksDB, Redis, Akka HTTP

Speaker bio

Piyush Kumar
Head, Data Platform Engineering, MakeMyTrip
Serving as Director, Data Platform Engineering for India’s largest Online Travel Group (MakeMyTrip) with over a decade of experience in building large-scale high-performance systems and developing & architecting Data Products.
He has been part of the e-commerce Industry throughout his career in various technology leadership roles across different domains like comparison shopping, travel, marketplaces and managed teams in Website Operations, Security Operations & BigData.
In the past had co-founded startup Advisor Healthcare with a unique “Virtual Hospital” concept, based on marketplace model - where it enabled digital interactions between healthcare providers and patients.
Currently leading key strategic initiatives in data services/products for Personalization, context aware mobile experiences, Customer Segmentation and developing engagement platform over BigData systems.

Slides

https://docs.google.com/presentation/d/1MCdsekLIFO2LyXS7lgKfEqJizz1T8Nm74XKTrkR69mY/edit?usp=sharing

Comments

  • Abhishek Balaji (@booleanbalaji) Reviewer 5 months ago

    Hi Piyush,

    Thank you for submitting a proposal. We need to see detailed slides and a preview video to evaluate your proposal. Your slides must cover the following:

    • Problem statement/context, which the audience can relate to and understand. The problem statement has to be a problem (based on this context) that can be generalized for all.
    • What were the tools/frameworks available in the market to solve this problem? How did you evaluate these, and what metrics did you use for the evaluation? Why did you pick the option that you did?
    • Explain how the situation was before the solution you picked/built and how it changed after implementing the solution you picked and built? Show before-after scenario comparisons & metrics.
    • What compromises/trade-offs did you have to make in this process?
    • What is the one takeaway that you want participants to go back with at the end of this talk? What is it that participants should learn/be cautious about when solving similar problems?

    We need your updated slides and preview video by Jun 17, 2019 to evaluate your proposal. If we do not receive an update, we’d be moving your proposal for evaluation under a future event.

    • Piyush (@piykumar) Proposer 5 months ago

      Hello Abhishek, pls. checkout slides (link added in slides section), do let me know in case more details are required now. Thanks a lot!
      ~/Piyush

      • Abhishek Balaji (@booleanbalaji) Reviewer 5 months ago

        Thanks for the slides, Piyush.

        Here are my comments:

        • The proposal still lacks the problem definition. What is the problem you’re trying to solve? Right now you jump stright into your platform, without introducing the fundamental problem.

        • The presentation needs to be updated to explain why the solution was picked, what the alternatives were, why you made the build/buy decision, and more as mentioned in the previous comment.

        Without answering the questions, the presentation would not be useful for the audience at The Fifth Elephant, since it reads like documentation and doesnt not talk about the journey in picking this solution, which is what is valuable for the audience.

        Do take the time till June 17 to work on your slides and update them. Meanwhile, we’d also need a preview video. The video is a 2 min self recorded video, where you talk about the problem you’re trying to solve and what you’d be covering in your talk.

  • Abhishek Balaji (@booleanbalaji) Reviewer 5 months ago

    Marked as rejected since the proposer hasnt responded & slides are not accessible. Will be considered for a future conference if the content is updated.

Login with Twitter or Google to leave a comment