MLOps Conference
On DataOps, productionizing ML models, and running experiments at scale.
SK
Sandilya Konduri
@sandilya
Leveraging ML algorithms to deliver faster in an extremely chaotic environment
Submitted Jul 14, 2021
Ecommerce in our country has come quite some distance and along with it has been successful in reshaping customer expectations and his/her perception of hygiene & delight. Speedy delivery now has become a base expectation of today’s customer. Add a certain set of categories , the need for quicker SLA just escalates higher.
In this battle to improve on the faster delivery aspirations , eKart has leveraged a ML algorithm to calculate SLA and simulate this for the future.
This talk is a sneak peak into the approach that we’ve taken on this problem statement.
In this talk , you will learn about -
- Importance of Customer Speed in the context of ecommerce in India in 2021
- The complexity of network run by a large scale ecommerce supply chain like eKart
- How we are leveraging ML to solve for this problem
- High level architecture overview of how the systems are designed
- Choices we’ve taken on anomalies encountered in the ML output , given the criticality of the output metric
- “Sense & Response” how we’re powering an ability for the system & stakeholders to react to these changes
Agenda -
- Importance of SLA , shift in buyer trend in India
- An overview of the components of the ML Algorithm used for computing the SLA + the simulation algorithm
- Architecture view of the solution
- Deep dive on the anomalous situations encountered & reactions taken by the system -
- Look forward simulation
- Infeasible inputs
- Simulation result exceeding guardrails
- Alerts on moderate anomalies
- Overall impact achieved
Who should attend this -
- Product Managers especially the ones in Supply Chain
- Data Scientists + OR enthusiasts
- People interested in applications of GraphDB
bharadwaaj.rajan@flipkart.com ; sandilya.konduri@flipkart.com
Comments
Hybrid access (members only)
Hosted by
Jump starting better data engineering and AI futures
Supported by
Scribble Data builds feature stores for data science teams that are serious about putting models (ML, or even sub-ML) into production. The ability to systematically transform data is the single biggest determinant of how well these models do. Scribble Data streamlines the feature engineering proces…
more
Promoted
Deep dives into privacy and security, and understanding needs of the Indian tech ecosystem through guides, research, collaboration, events and conferences. Sponsors: Privacy Mode’s programmes are sponsored by:
more
{{ gettext('Login to leave a comment') }}
{{ gettext('Post a comment…') }}{{ errorMsg }}
{{ gettext('No comments posted yet') }}