Alok Gupta

Head of Data Science & ML, DoorDash · 1 appearance on the record.

computed by AI from the episodes · how this works → · full disclaimer →

Alok Gupta is the Head of Data Science and Machine Learning at DoorDash. He built and scaled DoorDash's data science organization and oversaw its machine learning infrastructure.

14statements → 3claims → 0claims resolved → 4.07/5average certainty → 1.36/5average debate potential → ≈4.5/5argument clarity, estimated →

3 not checkable as stated how the 3 claims stand · each chip opens the sources

3 assertions · 3 insights · 8 disclosures · every statement was checked. The predictions and assertions are the 3 claims: statements the public record can support or contradict. 0 are resolved, and 3 name no date, number or outcome precise enough to check. Everything else (opinions, insights, what ifs, disclosures) can never be settled by the record, so it carries no assessment.

The record, in short

What the tape says about how Alok argues and how the claims held up. Everything they said, and everything said about them, is in the tabs below.

How they sound: speaking style how? →

242 words/min while actually speaking · 40 um and uh per 1k words

No argument clarity score for Alok Gupta: only 4 usable question→answer exchanges on raw tape (a fair score needs 8+). We do not score a sample that small. Roundtable and news formats yield far fewer direct exchanges than interviews. Their coarse estimate from 4 raw tape exchanges is ≈4.5/5, shown at half point precision because the sample is small.

Measured by listening to the audio itself: 3,172 words across 1 episode of raw-level tape, transcribed verbatim with every um and uh kept, each one attributed only where the alignment onto our timed stream is unambiguous. These are measurements of speaking style. We do not rank them: across this corpus, fluency and argument quality are nearly uncorrelated (ρ≈0.2), and smooth talking does not signal clear thinking. How it's measured →

What they said14 Episodes1

Everything Alok Gupta said on the MAD Podcast that made the record, most notable first. Filter by type, assessment or year in the ledger →

Disclosure

DoorDash aims to offer white-label infrastructure services modeled after AWS

“I think we would like to think of ourselves as an infrastructure company. That's right. Where we build products and services to help us in the things we're trying to do, but ultimately we get them to a stage of maturity and robustness through experimenting on …”

Alok Gupta Feb 1, 2021 ▶ 3:02 Fireside Chat: Alok Gupta (Head of Data Science & ML, DoorDash) with Matt Turck (Partner, FirstMark)

Insight

Problem framing is the hardest part of the machine learning lifecycle

“I think right at the start of a project is probably, and probably the hardest and most impactful part of the life cycle of the model. I think I prefer to call it sort of data-driven software because it could ultimately be it could be something other than a mod…”

Alok Gupta Feb 1, 2021 ▶ 4:08 Fireside Chat: Alok Gupta (Head of Data Science & ML, DoorDash) with Matt Turck (Partner, FirstMark)

Disclosure

DoorDash commits raw training scripts instead of pickled machine learning models

“Instead of building a model and pickling it or whatever a conversion package you want to use, we commit the actual training script to our model library.”

Alok Gupta Feb 1, 2021 ▶ 7:42 Fireside Chat: Alok Gupta (Head of Data Science & ML, DoorDash) with Matt Turck (Partner, FirstMark)

Disclosure

Deploying ML models to production at DoorDash requires data science approval

“It is perfectly acceptable for anyone at DoorDash to Build a machine learning model, but if they want to put it into production, they need approval or a review from someone like a data scientist or machine learning engineer.”

Alok Gupta Feb 1, 2021 ▶ 17:45 Fireside Chat: Alok Gupta (Head of Data Science & ML, DoorDash) with Matt Turck (Partner, FirstMark)

Insight

Training dedicated models for distinct cohorts beats fitting general models

“If there's a strong enough use case for a different cohort or segment like new users, typically it'll make more sense just to train a new model rather than trying to shoehorn it into a general model.”

Alok Gupta Feb 1, 2021 ▶ 22:56 Fireside Chat: Alok Gupta (Head of Data Science & ML, DoorDash) with Matt Turck (Partner, FirstMark)

Disclosure

Grocery expansion turns DoorDash from a three- to four-sided marketplace

“The food delivery is a three-sided. You're right. There's the merchant, the consumer, and the dasher. As we start to branch out into grocery delivery, convenience delivery, it becomes a four-sided where we introduce a picker as well.”

Alok Gupta Feb 1, 2021 ▶ 1:11 Fireside Chat: Alok Gupta (Head of Data Science & ML, DoorDash) with Matt Turck (Partner, FirstMark)

Disclosure

DoorDash standardized its core machine learning platform on LightGBM and PyTorch

“We landed on using a framework that enables tree-based models. And we picked light GBM for that after trying a few different packages and also deep learning. And for that, we then used PyTorch. And so we started with those two core libraries.”

Alok Gupta Feb 1, 2021 ▶ 6:29 Fireside Chat: Alok Gupta (Head of Data Science & ML, DoorDash) with Matt Turck (Partner, FirstMark)

Disclosure

DoorDash, Airbnb, and Lyft all sought a centralized machine learning stack

“I would say at all three places, there was a desire for a centralized stack so that iterative improvements sort of helped all models.”

Alok Gupta Feb 1, 2021 ▶ 11:13 Fireside Chat: Alok Gupta (Head of Data Science & ML, DoorDash) with Matt Turck (Partner, FirstMark)

Insight

Consolidating training and serving data is the feature store holy grail

“And so a way to create a feature store whereby we can consolidate the training data with the prediction serving time data is a common sort of holy grail for all the companies I've been at in their pursuit.”

Alok Gupta Feb 1, 2021 ▶ 11:58 Fireside Chat: Alok Gupta (Head of Data Science & ML, DoorDash) with Matt Turck (Partner, FirstMark)

Assertion Not checkable as stated

DoorDash's data science team grew from six to thirty in 18 months

“We, so a year and a half ago when I joined we had six, five or six people on the team. We're now at almost 30 people a year and a half later”

Alok Gupta Feb 1, 2021 ▶ 13:14 Fireside Chat: Alok Gupta (Head of Data Science & ML, DoorDash) with Matt Turck (Partner, FirstMark)

Disclosure

DoorDash plans to double its data science team in 2021

“And this year we want to double, so to get to 50 plus people.”

Alok Gupta Feb 1, 2021 ▶ 13:20 Fireside Chat: Alok Gupta (Head of Data Science & ML, DoorDash) with Matt Turck (Partner, FirstMark)

Disclosure

DoorDash shortened ML model lookback from four weeks to one during COVID

“Whereas in the past for an assignment algorithm, we might have looked back four weeks. We changed it to one week.”

Alok Gupta Feb 1, 2021 ▶ 19:49 Fireside Chat: Alok Gupta (Head of Data Science & ML, DoorDash) with Matt Turck (Partner, FirstMark)

Assertion Not checkable as stated

DoorDash's ML feature store is mostly homegrown and uses Apache Flink

“It's mostly homegrown. We're using some technologies like Flint for one of some of our real time feature aggregation, data aggregation, but mostly it's homegrown.”

Alok Gupta Feb 1, 2021 ▶ 20:41 Fireside Chat: Alok Gupta (Head of Data Science & ML, DoorDash) with Matt Turck (Partner, FirstMark)

Assertion Not checkable as stated

DoorDash runs Databricks on AWS S3 and ingests data from Snowflake

“We run a Databricks on S-III, but we pull data into Databricks from Snowflake, so we have a connection between the two.”

Alok Gupta Feb 1, 2021 ▶ 21:24 Fireside Chat: Alok Gupta (Head of Data Science & ML, DoorDash) with Matt Turck (Partner, FirstMark)

Appearances (1)

Episode	Date	Speaking time
Fireside Chat: Alok Gupta (Head of Data Science & ML, DoorDash) with Matt Turck (Partner,	Feb 1, 2021	18m

Alok Gupta

The record, in short

How they sound: speaking style how? →

Appearances (1)

Turn any episode into a week of clips.